| { |
| "best_global_step": 300, |
| "best_metric": 0.70836127, |
| "best_model_checkpoint": "/data2/kdd/crag/cjz/output/task3_dpo_gt6_task2_gt30.3+task3gt5_0.1vp/v0-20250611-011957/checkpoint-300", |
| "epoch": 0.2860633511129652, |
| "eval_steps": 300, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0009535445037098841, |
| "grad_norm": 9.156327247619629, |
| "learning_rate": 3.7735849056603773e-06, |
| "logits/chosen": -0.6435090899467468, |
| "logits/rejected": -0.6501147150993347, |
| "logps/chosen": -12.8789701461792, |
| "logps/rejected": -12.67190170288086, |
| "loss": 1.3995760679244995, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7064292430877686, |
| "rewards/accuracies": 0.0, |
| "rewards/chosen": 0.0, |
| "rewards/margins": 0.0, |
| "rewards/rejected": 0.0, |
| "step": 1, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.0019070890074197682, |
| "grad_norm": 3.750561237335205, |
| "learning_rate": 7.547169811320755e-06, |
| "logits/chosen": -0.5811247229576111, |
| "logits/rejected": -0.5784763693809509, |
| "logps/chosen": -11.550155639648438, |
| "logps/rejected": -10.463687896728516, |
| "loss": 1.1846946477890015, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4915475845336914, |
| "rewards/accuracies": 0.0, |
| "rewards/chosen": 0.0, |
| "rewards/margins": 0.0, |
| "rewards/rejected": 0.0, |
| "step": 2, |
| "train_speed(iter/s)": 0.005627 |
| }, |
| { |
| "epoch": 0.002860633511129652, |
| "grad_norm": 9.728832244873047, |
| "learning_rate": 1.1320754716981132e-05, |
| "logits/chosen": -0.6211333274841309, |
| "logits/rejected": -0.6250367760658264, |
| "logps/chosen": -13.265661239624023, |
| "logps/rejected": -17.363025665283203, |
| "loss": 1.4022446870803833, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7087438106536865, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": 0.0019078836776316166, |
| "rewards/margins": -0.0005585900507867336, |
| "rewards/rejected": 0.002466473262757063, |
| "step": 3, |
| "train_speed(iter/s)": 0.005589 |
| }, |
| { |
| "epoch": 0.0038141780148395364, |
| "grad_norm": 4.456181049346924, |
| "learning_rate": 1.509433962264151e-05, |
| "logits/chosen": -0.6295092105865479, |
| "logits/rejected": -0.6310409307479858, |
| "logps/chosen": -20.259197235107422, |
| "logps/rejected": -15.924739837646484, |
| "loss": 1.4261250495910645, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7309765815734863, |
| "rewards/accuracies": 0.4375, |
| "rewards/chosen": -0.003216111334040761, |
| "rewards/margins": -0.003784709610044956, |
| "rewards/rejected": 0.0005685988580808043, |
| "step": 4, |
| "train_speed(iter/s)": 0.005576 |
| }, |
| { |
| "epoch": 0.004767722518549421, |
| "grad_norm": 5.137070178985596, |
| "learning_rate": 1.8867924528301888e-05, |
| "logits/chosen": -0.6352660059928894, |
| "logits/rejected": -0.6393146514892578, |
| "logps/chosen": -11.320538520812988, |
| "logps/rejected": -18.213350296020508, |
| "loss": 1.3472224473953247, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.659798800945282, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": 0.009231260977685452, |
| "rewards/margins": 0.011925339698791504, |
| "rewards/rejected": -0.0026940787211060524, |
| "step": 5, |
| "train_speed(iter/s)": 0.005563 |
| }, |
| { |
| "epoch": 0.005721267022259304, |
| "grad_norm": 4.738046169281006, |
| "learning_rate": 2.2641509433962265e-05, |
| "logits/chosen": -0.621586799621582, |
| "logits/rejected": -0.6225624680519104, |
| "logps/chosen": -13.36612319946289, |
| "logps/rejected": -12.092449188232422, |
| "loss": 1.2847044467926025, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.593052089214325, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": 0.001901240088045597, |
| "rewards/margins": 0.0050404006615281105, |
| "rewards/rejected": -0.0031391603406518698, |
| "step": 6, |
| "train_speed(iter/s)": 0.005557 |
| }, |
| { |
| "epoch": 0.0066748115259691885, |
| "grad_norm": 4.152891159057617, |
| "learning_rate": 2.641509433962264e-05, |
| "logits/chosen": -0.6192730665206909, |
| "logits/rejected": -0.6235961318016052, |
| "logps/chosen": -12.630643844604492, |
| "logps/rejected": -15.917936325073242, |
| "loss": 1.2920165061950684, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5905699133872986, |
| "rewards/accuracies": 0.4375, |
| "rewards/chosen": 0.016993187367916107, |
| "rewards/margins": -0.008502829819917679, |
| "rewards/rejected": 0.025496022775769234, |
| "step": 7, |
| "train_speed(iter/s)": 0.005538 |
| }, |
| { |
| "epoch": 0.007628356029679073, |
| "grad_norm": 4.160374641418457, |
| "learning_rate": 3.018867924528302e-05, |
| "logits/chosen": -0.6182655692100525, |
| "logits/rejected": -0.6189552545547485, |
| "logps/chosen": -10.698919296264648, |
| "logps/rejected": -14.148299217224121, |
| "loss": 1.0840333700180054, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3833664357662201, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -0.006827078759670258, |
| "rewards/margins": 0.02289848029613495, |
| "rewards/rejected": -0.0297255702316761, |
| "step": 8, |
| "train_speed(iter/s)": 0.005529 |
| }, |
| { |
| "epoch": 0.008581900533388956, |
| "grad_norm": 7.751194953918457, |
| "learning_rate": 3.39622641509434e-05, |
| "logits/chosen": -0.5885738134384155, |
| "logits/rejected": -0.5893712043762207, |
| "logps/chosen": -14.677619934082031, |
| "logps/rejected": -19.348114013671875, |
| "loss": 1.4759101867675781, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7508934140205383, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": -0.06757626682519913, |
| "rewards/margins": -0.03109188750386238, |
| "rewards/rejected": -0.036484383046627045, |
| "step": 9, |
| "train_speed(iter/s)": 0.005546 |
| }, |
| { |
| "epoch": 0.009535445037098841, |
| "grad_norm": 5.425357818603516, |
| "learning_rate": 3.7735849056603776e-05, |
| "logits/chosen": -0.6194073557853699, |
| "logits/rejected": -0.6175965666770935, |
| "logps/chosen": -16.864004135131836, |
| "logps/rejected": -13.315808296203613, |
| "loss": 1.264159083366394, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5726930499076843, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -0.03342372551560402, |
| "rewards/margins": 0.05060018226504326, |
| "rewards/rejected": -0.08402392268180847, |
| "step": 10, |
| "train_speed(iter/s)": 0.005559 |
| }, |
| { |
| "epoch": 0.010488989540808725, |
| "grad_norm": 4.181962013244629, |
| "learning_rate": 4.150943396226415e-05, |
| "logits/chosen": -0.6295148730278015, |
| "logits/rejected": -0.6311144232749939, |
| "logps/chosen": -17.622665405273438, |
| "logps/rejected": -22.323240280151367, |
| "loss": 1.1960029602050781, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4701622426509857, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -0.05372938886284828, |
| "rewards/margins": -0.0011130962520837784, |
| "rewards/rejected": -0.05261629447340965, |
| "step": 11, |
| "train_speed(iter/s)": 0.00555 |
| }, |
| { |
| "epoch": 0.011442534044518608, |
| "grad_norm": 3.3646111488342285, |
| "learning_rate": 4.528301886792453e-05, |
| "logits/chosen": -0.6567115783691406, |
| "logits/rejected": -0.6585782170295715, |
| "logps/chosen": -11.29936408996582, |
| "logps/rejected": -18.29203987121582, |
| "loss": 1.1115467548370361, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4559721350669861, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": 0.08929000794887543, |
| "rewards/margins": 0.12125876545906067, |
| "rewards/rejected": -0.03196876123547554, |
| "step": 12, |
| "train_speed(iter/s)": 0.005551 |
| }, |
| { |
| "epoch": 0.012396078548228493, |
| "grad_norm": 3.79887318611145, |
| "learning_rate": 4.9056603773584906e-05, |
| "logits/chosen": -0.5698614716529846, |
| "logits/rejected": -0.5705659985542297, |
| "logps/chosen": -16.54460906982422, |
| "logps/rejected": -16.52007484436035, |
| "loss": 1.2756099700927734, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6095594167709351, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.08876940608024597, |
| "rewards/margins": 0.0944020226597786, |
| "rewards/rejected": -0.005632609128952026, |
| "step": 13, |
| "train_speed(iter/s)": 0.005543 |
| }, |
| { |
| "epoch": 0.013349623051938377, |
| "grad_norm": 3.3852715492248535, |
| "learning_rate": 5.283018867924528e-05, |
| "logits/chosen": -0.5822104811668396, |
| "logits/rejected": -0.5813897848129272, |
| "logps/chosen": -15.234231948852539, |
| "logps/rejected": -15.407049179077148, |
| "loss": 1.2322038412094116, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6042034029960632, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.1384495347738266, |
| "rewards/margins": 0.16144631803035736, |
| "rewards/rejected": -0.022996775805950165, |
| "step": 14, |
| "train_speed(iter/s)": 0.005541 |
| }, |
| { |
| "epoch": 0.014303167555648262, |
| "grad_norm": 2.7666451930999756, |
| "learning_rate": 5.660377358490566e-05, |
| "logits/chosen": -0.5926915407180786, |
| "logits/rejected": -0.5929235816001892, |
| "logps/chosen": -14.370649337768555, |
| "logps/rejected": -14.672292709350586, |
| "loss": 1.268752098083496, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5840609669685364, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.13987205922603607, |
| "rewards/margins": 0.04084888845682144, |
| "rewards/rejected": 0.09902316331863403, |
| "step": 15, |
| "train_speed(iter/s)": 0.005545 |
| }, |
| { |
| "epoch": 0.015256712059358146, |
| "grad_norm": 3.996248960494995, |
| "learning_rate": 6.037735849056604e-05, |
| "logits/chosen": -0.6161852478981018, |
| "logits/rejected": -0.6143717169761658, |
| "logps/chosen": -17.775665283203125, |
| "logps/rejected": -16.12677001953125, |
| "loss": 1.3597179651260376, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7031959295272827, |
| "rewards/accuracies": 0.59375, |
| "rewards/chosen": 0.14894011616706848, |
| "rewards/margins": 0.10105747729539871, |
| "rewards/rejected": 0.047882646322250366, |
| "step": 16, |
| "train_speed(iter/s)": 0.005542 |
| }, |
| { |
| "epoch": 0.01621025656306803, |
| "grad_norm": 3.343315601348877, |
| "learning_rate": 6.415094339622641e-05, |
| "logits/chosen": -0.5822757482528687, |
| "logits/rejected": -0.5849615931510925, |
| "logps/chosen": -11.210283279418945, |
| "logps/rejected": -17.080455780029297, |
| "loss": 1.1165493726730347, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4471588432788849, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": 0.13627491891384125, |
| "rewards/margins": 0.07742398977279663, |
| "rewards/rejected": 0.058850936591625214, |
| "step": 17, |
| "train_speed(iter/s)": 0.005542 |
| }, |
| { |
| "epoch": 0.017163801066777912, |
| "grad_norm": 2.5265791416168213, |
| "learning_rate": 6.79245283018868e-05, |
| "logits/chosen": -0.5711070895195007, |
| "logits/rejected": -0.5730242729187012, |
| "logps/chosen": -14.197075843811035, |
| "logps/rejected": -15.04891586303711, |
| "loss": 1.1029906272888184, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.45255714654922485, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.1637343168258667, |
| "rewards/margins": 0.1597798466682434, |
| "rewards/rejected": 0.0039544664323329926, |
| "step": 18, |
| "train_speed(iter/s)": 0.005535 |
| }, |
| { |
| "epoch": 0.0181173455704878, |
| "grad_norm": 4.558610916137695, |
| "learning_rate": 7.169811320754717e-05, |
| "logits/chosen": -0.572235643863678, |
| "logits/rejected": -0.5743283629417419, |
| "logps/chosen": -9.268120765686035, |
| "logps/rejected": -12.118350982666016, |
| "loss": 1.1668801307678223, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5335167646408081, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.19031290709972382, |
| "rewards/margins": 0.15231794118881226, |
| "rewards/rejected": 0.03799496963620186, |
| "step": 19, |
| "train_speed(iter/s)": 0.005519 |
| }, |
| { |
| "epoch": 0.019070890074197683, |
| "grad_norm": 3.7134947776794434, |
| "learning_rate": 7.547169811320755e-05, |
| "logits/chosen": -0.585778534412384, |
| "logits/rejected": -0.5890673398971558, |
| "logps/chosen": -8.275850296020508, |
| "logps/rejected": -16.348182678222656, |
| "loss": 1.0512793064117432, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.39501887559890747, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": 0.1688304841518402, |
| "rewards/margins": 0.12996332347393036, |
| "rewards/rejected": 0.03886716440320015, |
| "step": 20, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.020024434577907566, |
| "grad_norm": 3.5586955547332764, |
| "learning_rate": 7.924528301886794e-05, |
| "logits/chosen": -0.5529674291610718, |
| "logits/rejected": -0.5549667477607727, |
| "logps/chosen": -14.883947372436523, |
| "logps/rejected": -19.51848793029785, |
| "loss": 1.2289440631866455, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5555365085601807, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": 0.06489060074090958, |
| "rewards/margins": 0.08113954961299896, |
| "rewards/rejected": -0.016248945146799088, |
| "step": 21, |
| "train_speed(iter/s)": 0.005523 |
| }, |
| { |
| "epoch": 0.02097797908161745, |
| "grad_norm": 2.970125913619995, |
| "learning_rate": 8.30188679245283e-05, |
| "logits/chosen": -0.5630563497543335, |
| "logits/rejected": -0.5648879408836365, |
| "logps/chosen": -9.709285736083984, |
| "logps/rejected": -14.605964660644531, |
| "loss": 1.0496439933776855, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4030095934867859, |
| "rewards/accuracies": 0.59375, |
| "rewards/chosen": 0.13459333777427673, |
| "rewards/margins": 0.13257721066474915, |
| "rewards/rejected": 0.0020161233842372894, |
| "step": 22, |
| "train_speed(iter/s)": 0.005527 |
| }, |
| { |
| "epoch": 0.021931523585327333, |
| "grad_norm": 3.7449333667755127, |
| "learning_rate": 8.679245283018869e-05, |
| "logits/chosen": -0.5388307571411133, |
| "logits/rejected": -0.5379776954650879, |
| "logps/chosen": -20.206819534301758, |
| "logps/rejected": -10.312554359436035, |
| "loss": 1.3675460815429688, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7346486449241638, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.22365330159664154, |
| "rewards/margins": 0.19076848030090332, |
| "rewards/rejected": 0.032884806394577026, |
| "step": 23, |
| "train_speed(iter/s)": 0.005527 |
| }, |
| { |
| "epoch": 0.022885068089037217, |
| "grad_norm": 4.3556928634643555, |
| "learning_rate": 9.056603773584906e-05, |
| "logits/chosen": -0.5620133876800537, |
| "logits/rejected": -0.5651191473007202, |
| "logps/chosen": -13.681132316589355, |
| "logps/rejected": -17.737977981567383, |
| "loss": 1.427290439605713, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7979669570922852, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.20859572291374207, |
| "rewards/margins": 0.19208168983459473, |
| "rewards/rejected": 0.01651405170559883, |
| "step": 24, |
| "train_speed(iter/s)": 0.005528 |
| }, |
| { |
| "epoch": 0.023838612592747103, |
| "grad_norm": 2.59773850440979, |
| "learning_rate": 9.433962264150944e-05, |
| "logits/chosen": -0.5109421014785767, |
| "logits/rejected": -0.5130017995834351, |
| "logps/chosen": -11.422687530517578, |
| "logps/rejected": -19.77487564086914, |
| "loss": 1.0190178155899048, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3792160749435425, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": 0.17286184430122375, |
| "rewards/margins": 0.1656832993030548, |
| "rewards/rejected": 0.007178528234362602, |
| "step": 25, |
| "train_speed(iter/s)": 0.005528 |
| }, |
| { |
| "epoch": 0.024792157096456987, |
| "grad_norm": 3.2465970516204834, |
| "learning_rate": 9.811320754716981e-05, |
| "logits/chosen": -0.4895856976509094, |
| "logits/rejected": -0.490243524312973, |
| "logps/chosen": -8.71623420715332, |
| "logps/rejected": -7.8305277824401855, |
| "loss": 1.0329375267028809, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3276180028915405, |
| "rewards/accuracies": 0.4375, |
| "rewards/chosen": 0.13548454642295837, |
| "rewards/margins": 0.014407174661755562, |
| "rewards/rejected": 0.12107735872268677, |
| "step": 26, |
| "train_speed(iter/s)": 0.005523 |
| }, |
| { |
| "epoch": 0.02574570160016687, |
| "grad_norm": 2.9056291580200195, |
| "learning_rate": 0.0001018867924528302, |
| "logits/chosen": -0.5098599195480347, |
| "logits/rejected": -0.5105721950531006, |
| "logps/chosen": -17.795873641967773, |
| "logps/rejected": -13.080977439880371, |
| "loss": 1.1328891515731812, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4805879294872284, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.18526741862297058, |
| "rewards/margins": 0.11028175055980682, |
| "rewards/rejected": 0.07498566806316376, |
| "step": 27, |
| "train_speed(iter/s)": 0.005528 |
| }, |
| { |
| "epoch": 0.026699246103876754, |
| "grad_norm": 3.9831905364990234, |
| "learning_rate": 0.00010566037735849057, |
| "logits/chosen": -0.5249112844467163, |
| "logits/rejected": -0.5256497859954834, |
| "logps/chosen": -9.17713737487793, |
| "logps/rejected": -16.791439056396484, |
| "loss": 1.0309749841690063, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49379563331604004, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.26130685210227966, |
| "rewards/margins": 0.4484291970729828, |
| "rewards/rejected": -0.1871223747730255, |
| "step": 28, |
| "train_speed(iter/s)": 0.00553 |
| }, |
| { |
| "epoch": 0.027652790607586637, |
| "grad_norm": 3.447692394256592, |
| "learning_rate": 0.00010943396226415095, |
| "logits/chosen": -0.46926626563072205, |
| "logits/rejected": -0.474046528339386, |
| "logps/chosen": -10.564407348632812, |
| "logps/rejected": -13.679093360900879, |
| "loss": 1.0266515016555786, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4402708113193512, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.25625136494636536, |
| "rewards/margins": 0.27123552560806274, |
| "rewards/rejected": -0.014984178356826305, |
| "step": 29, |
| "train_speed(iter/s)": 0.005529 |
| }, |
| { |
| "epoch": 0.028606335111296524, |
| "grad_norm": 2.3513646125793457, |
| "learning_rate": 0.00011320754716981132, |
| "logits/chosen": -0.4841839671134949, |
| "logits/rejected": -0.4823201894760132, |
| "logps/chosen": -16.52553367614746, |
| "logps/rejected": -12.728946685791016, |
| "loss": 1.051925539970398, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5132753252983093, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.28733503818511963, |
| "rewards/margins": 0.3806324601173401, |
| "rewards/rejected": -0.09329745918512344, |
| "step": 30, |
| "train_speed(iter/s)": 0.00553 |
| }, |
| { |
| "epoch": 0.029559879615006408, |
| "grad_norm": 2.8920440673828125, |
| "learning_rate": 0.0001169811320754717, |
| "logits/chosen": -0.4617501497268677, |
| "logits/rejected": -0.4629114866256714, |
| "logps/chosen": -9.827648162841797, |
| "logps/rejected": -11.787566184997559, |
| "loss": 1.0702807903289795, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4221873879432678, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": 0.12683041393756866, |
| "rewards/margins": 0.20381762087345123, |
| "rewards/rejected": -0.07698723673820496, |
| "step": 31, |
| "train_speed(iter/s)": 0.005529 |
| }, |
| { |
| "epoch": 0.03051342411871629, |
| "grad_norm": 3.150108575820923, |
| "learning_rate": 0.00012075471698113207, |
| "logits/chosen": -0.46168380975723267, |
| "logits/rejected": -0.45957043766975403, |
| "logps/chosen": -14.481122970581055, |
| "logps/rejected": -12.509255409240723, |
| "loss": 1.1068114042282104, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4239238202571869, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.07766711711883545, |
| "rewards/margins": 0.11046308279037476, |
| "rewards/rejected": -0.03279596567153931, |
| "step": 32, |
| "train_speed(iter/s)": 0.005524 |
| }, |
| { |
| "epoch": 0.03146696862242618, |
| "grad_norm": 4.185500621795654, |
| "learning_rate": 0.00012452830188679244, |
| "logits/chosen": -0.4712987542152405, |
| "logits/rejected": -0.47331178188323975, |
| "logps/chosen": -13.179000854492188, |
| "logps/rejected": -19.023120880126953, |
| "loss": 1.3572198152542114, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7039042711257935, |
| "rewards/accuracies": 0.59375, |
| "rewards/chosen": 0.17201806604862213, |
| "rewards/margins": 0.16012105345726013, |
| "rewards/rejected": 0.011897009797394276, |
| "step": 33, |
| "train_speed(iter/s)": 0.005529 |
| }, |
| { |
| "epoch": 0.03242051312613606, |
| "grad_norm": 3.005161762237549, |
| "learning_rate": 0.00012830188679245283, |
| "logits/chosen": -0.4754801392555237, |
| "logits/rejected": -0.4769393503665924, |
| "logps/chosen": -11.273967742919922, |
| "logps/rejected": -16.496191024780273, |
| "loss": 1.0072283744812012, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.41234296560287476, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.22565320134162903, |
| "rewards/margins": 0.27443331480026245, |
| "rewards/rejected": -0.04878011345863342, |
| "step": 34, |
| "train_speed(iter/s)": 0.005526 |
| }, |
| { |
| "epoch": 0.033374057629845945, |
| "grad_norm": 5.103848457336426, |
| "learning_rate": 0.0001320754716981132, |
| "logits/chosen": -0.44018203020095825, |
| "logits/rejected": -0.44089382886886597, |
| "logps/chosen": -15.832134246826172, |
| "logps/rejected": -19.550304412841797, |
| "loss": 1.2559186220169067, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5793285965919495, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.09596908837556839, |
| "rewards/margins": 0.11671226471662521, |
| "rewards/rejected": -0.020743174478411674, |
| "step": 35, |
| "train_speed(iter/s)": 0.005527 |
| }, |
| { |
| "epoch": 0.034327602133555825, |
| "grad_norm": 4.321141719818115, |
| "learning_rate": 0.0001358490566037736, |
| "logits/chosen": -0.49340876936912537, |
| "logits/rejected": -0.49693170189857483, |
| "logps/chosen": -17.06662940979004, |
| "logps/rejected": -20.88056755065918, |
| "loss": 1.2329245805740356, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6244450807571411, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.2872624695301056, |
| "rewards/margins": 0.23183389008045197, |
| "rewards/rejected": 0.05542857572436333, |
| "step": 36, |
| "train_speed(iter/s)": 0.00553 |
| }, |
| { |
| "epoch": 0.03528114663726571, |
| "grad_norm": 3.112792491912842, |
| "learning_rate": 0.00013962264150943395, |
| "logits/chosen": -0.4647415578365326, |
| "logits/rejected": -0.4648529291152954, |
| "logps/chosen": -12.979642868041992, |
| "logps/rejected": -13.105558395385742, |
| "loss": 1.1428803205490112, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48155656456947327, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": 0.19289334118366241, |
| "rewards/margins": 0.169374018907547, |
| "rewards/rejected": 0.023519329726696014, |
| "step": 37, |
| "train_speed(iter/s)": 0.005535 |
| }, |
| { |
| "epoch": 0.0362346911409756, |
| "grad_norm": 4.363394260406494, |
| "learning_rate": 0.00014339622641509434, |
| "logits/chosen": -0.47051119804382324, |
| "logits/rejected": -0.4702276289463043, |
| "logps/chosen": -11.824732780456543, |
| "logps/rejected": -18.102703094482422, |
| "loss": 0.9977712631225586, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48080000281333923, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.35463425517082214, |
| "rewards/margins": 0.5215649008750916, |
| "rewards/rejected": -0.166930690407753, |
| "step": 38, |
| "train_speed(iter/s)": 0.005537 |
| }, |
| { |
| "epoch": 0.03718823564468548, |
| "grad_norm": 2.3291094303131104, |
| "learning_rate": 0.00014716981132075472, |
| "logits/chosen": -0.4471542239189148, |
| "logits/rejected": -0.44849908351898193, |
| "logps/chosen": -10.541170120239258, |
| "logps/rejected": -13.821127891540527, |
| "loss": 1.0517562627792358, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4245188236236572, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": 0.17497971653938293, |
| "rewards/margins": 0.2404995709657669, |
| "rewards/rejected": -0.06551986932754517, |
| "step": 39, |
| "train_speed(iter/s)": 0.005533 |
| }, |
| { |
| "epoch": 0.038141780148395366, |
| "grad_norm": 2.5439131259918213, |
| "learning_rate": 0.0001509433962264151, |
| "logits/chosen": -0.43407440185546875, |
| "logits/rejected": -0.4330942928791046, |
| "logps/chosen": -12.606916427612305, |
| "logps/rejected": -8.916302680969238, |
| "loss": 1.1393225193023682, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.500526487827301, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": 0.15790946781635284, |
| "rewards/margins": 0.28719791769981384, |
| "rewards/rejected": -0.129288449883461, |
| "step": 40, |
| "train_speed(iter/s)": 0.005533 |
| }, |
| { |
| "epoch": 0.039095324652105246, |
| "grad_norm": 2.752281904220581, |
| "learning_rate": 0.0001547169811320755, |
| "logits/chosen": -0.4207141399383545, |
| "logits/rejected": -0.42105770111083984, |
| "logps/chosen": -9.193354606628418, |
| "logps/rejected": -15.80713939666748, |
| "loss": 1.0188286304473877, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.41979092359542847, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.11082945019006729, |
| "rewards/margins": 0.3942355513572693, |
| "rewards/rejected": -0.2834060788154602, |
| "step": 41, |
| "train_speed(iter/s)": 0.005532 |
| }, |
| { |
| "epoch": 0.04004886915581513, |
| "grad_norm": 2.4327123165130615, |
| "learning_rate": 0.00015849056603773587, |
| "logits/chosen": -0.445608913898468, |
| "logits/rejected": -0.4462995231151581, |
| "logps/chosen": -8.890420913696289, |
| "logps/rejected": -9.104397773742676, |
| "loss": 1.0348408222198486, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4377897083759308, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.1634826809167862, |
| "rewards/margins": 0.28891459107398987, |
| "rewards/rejected": -0.12543192505836487, |
| "step": 42, |
| "train_speed(iter/s)": 0.005537 |
| }, |
| { |
| "epoch": 0.04100241365952501, |
| "grad_norm": 2.331282377243042, |
| "learning_rate": 0.00016226415094339625, |
| "logits/chosen": -0.4530089497566223, |
| "logits/rejected": -0.4580504298210144, |
| "logps/chosen": -7.02070426940918, |
| "logps/rejected": -22.712093353271484, |
| "loss": 0.876542329788208, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3533342182636261, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.29712867736816406, |
| "rewards/margins": 0.5244494676589966, |
| "rewards/rejected": -0.22732074558734894, |
| "step": 43, |
| "train_speed(iter/s)": 0.005538 |
| }, |
| { |
| "epoch": 0.0419559581632349, |
| "grad_norm": 2.865417003631592, |
| "learning_rate": 0.0001660377358490566, |
| "logits/chosen": -0.4700409770011902, |
| "logits/rejected": -0.4735233187675476, |
| "logps/chosen": -12.126070022583008, |
| "logps/rejected": -24.352678298950195, |
| "loss": 1.157395362854004, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5185694694519043, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.1286190301179886, |
| "rewards/margins": 0.2031334638595581, |
| "rewards/rejected": -0.07451442629098892, |
| "step": 44, |
| "train_speed(iter/s)": 0.005538 |
| }, |
| { |
| "epoch": 0.042909502666944786, |
| "grad_norm": 2.9107770919799805, |
| "learning_rate": 0.000169811320754717, |
| "logits/chosen": -0.45035916566848755, |
| "logits/rejected": -0.4494967758655548, |
| "logps/chosen": -17.021671295166016, |
| "logps/rejected": -16.504793167114258, |
| "loss": 1.2039690017700195, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5990548729896545, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.22049224376678467, |
| "rewards/margins": 0.25519850850105286, |
| "rewards/rejected": -0.03470626473426819, |
| "step": 45, |
| "train_speed(iter/s)": 0.005534 |
| }, |
| { |
| "epoch": 0.043863047170654666, |
| "grad_norm": 2.5569493770599365, |
| "learning_rate": 0.00017358490566037738, |
| "logits/chosen": -0.4576927423477173, |
| "logits/rejected": -0.4589836597442627, |
| "logps/chosen": -15.28840160369873, |
| "logps/rejected": -21.630834579467773, |
| "loss": 1.0875338315963745, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5480765104293823, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.2394683063030243, |
| "rewards/margins": 0.43596386909484863, |
| "rewards/rejected": -0.19649554789066315, |
| "step": 46, |
| "train_speed(iter/s)": 0.005534 |
| }, |
| { |
| "epoch": 0.04481659167436455, |
| "grad_norm": 2.6082468032836914, |
| "learning_rate": 0.00017735849056603776, |
| "logits/chosen": -0.44933271408081055, |
| "logits/rejected": -0.4535468816757202, |
| "logps/chosen": -13.067358016967773, |
| "logps/rejected": -25.21561622619629, |
| "loss": 0.9420796632766724, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.44500476121902466, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.3027465343475342, |
| "rewards/margins": 0.5848984122276306, |
| "rewards/rejected": -0.28215184807777405, |
| "step": 47, |
| "train_speed(iter/s)": 0.005534 |
| }, |
| { |
| "epoch": 0.04577013617807443, |
| "grad_norm": 2.8552000522613525, |
| "learning_rate": 0.00018113207547169812, |
| "logits/chosen": -0.44021791219711304, |
| "logits/rejected": -0.4409497380256653, |
| "logps/chosen": -13.639575958251953, |
| "logps/rejected": -19.479185104370117, |
| "loss": 1.0777249336242676, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5401443243026733, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2517797350883484, |
| "rewards/margins": 0.4618395268917084, |
| "rewards/rejected": -0.21005980670452118, |
| "step": 48, |
| "train_speed(iter/s)": 0.00553 |
| }, |
| { |
| "epoch": 0.04672368068178432, |
| "grad_norm": 2.530268430709839, |
| "learning_rate": 0.0001849056603773585, |
| "logits/chosen": -0.47215527296066284, |
| "logits/rejected": -0.47504734992980957, |
| "logps/chosen": -11.48988151550293, |
| "logps/rejected": -36.38770294189453, |
| "loss": 0.9700489640235901, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46057599782943726, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.21084292232990265, |
| "rewards/margins": 0.533352792263031, |
| "rewards/rejected": -0.32250988483428955, |
| "step": 49, |
| "train_speed(iter/s)": 0.005532 |
| }, |
| { |
| "epoch": 0.04767722518549421, |
| "grad_norm": 2.7035655975341797, |
| "learning_rate": 0.00018867924528301889, |
| "logits/chosen": -0.4868597388267517, |
| "logits/rejected": -0.4888378977775574, |
| "logps/chosen": -13.504924774169922, |
| "logps/rejected": -21.10767936706543, |
| "loss": 1.0414435863494873, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5301634669303894, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.18318726122379303, |
| "rewards/margins": 0.619285523891449, |
| "rewards/rejected": -0.43609827756881714, |
| "step": 50, |
| "train_speed(iter/s)": 0.005531 |
| }, |
| { |
| "epoch": 0.04863076968920409, |
| "grad_norm": 3.0783157348632812, |
| "learning_rate": 0.00019245283018867927, |
| "logits/chosen": -0.488979697227478, |
| "logits/rejected": -0.4920251965522766, |
| "logps/chosen": -6.389867305755615, |
| "logps/rejected": -23.881044387817383, |
| "loss": 0.7357016801834106, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.2519811689853668, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.22045277059078217, |
| "rewards/margins": 0.6349221467971802, |
| "rewards/rejected": -0.4144693613052368, |
| "step": 51, |
| "train_speed(iter/s)": 0.00552 |
| }, |
| { |
| "epoch": 0.049584314192913974, |
| "grad_norm": 2.936868906021118, |
| "learning_rate": 0.00019622641509433963, |
| "logits/chosen": -0.49481600522994995, |
| "logits/rejected": -0.4982725977897644, |
| "logps/chosen": -7.566017150878906, |
| "logps/rejected": -28.77280044555664, |
| "loss": 0.8173349499702454, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.2955441176891327, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.12177374958992004, |
| "rewards/margins": 0.6433938145637512, |
| "rewards/rejected": -0.5216200947761536, |
| "step": 52, |
| "train_speed(iter/s)": 0.005518 |
| }, |
| { |
| "epoch": 0.050537858696623854, |
| "grad_norm": 4.539004802703857, |
| "learning_rate": 0.0002, |
| "logits/chosen": -0.5527479648590088, |
| "logits/rejected": -0.5551312565803528, |
| "logps/chosen": -15.817987442016602, |
| "logps/rejected": -22.29538345336914, |
| "loss": 1.1207798719406128, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5884667038917542, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.18014809489250183, |
| "rewards/margins": 0.6673915982246399, |
| "rewards/rejected": -0.4872434735298157, |
| "step": 53, |
| "train_speed(iter/s)": 0.005519 |
| }, |
| { |
| "epoch": 0.05149140320033374, |
| "grad_norm": 4.143117904663086, |
| "learning_rate": 0.00019999950154813253, |
| "logits/chosen": -0.5354641675949097, |
| "logits/rejected": -0.5355905294418335, |
| "logps/chosen": -12.528202056884766, |
| "logps/rejected": -18.404970169067383, |
| "loss": 1.0412046909332275, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5650326609611511, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.17625540494918823, |
| "rewards/margins": 0.8302103877067566, |
| "rewards/rejected": -0.6539549827575684, |
| "step": 54, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.05244494770404363, |
| "grad_norm": 3.329041004180908, |
| "learning_rate": 0.00019999800619749922, |
| "logits/chosen": -0.5789484977722168, |
| "logits/rejected": -0.5782615542411804, |
| "logps/chosen": -14.283157348632812, |
| "logps/rejected": -24.138996124267578, |
| "loss": 1.0249700546264648, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5574489831924438, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.08275524526834488, |
| "rewards/margins": 0.9348181486129761, |
| "rewards/rejected": -0.8520628809928894, |
| "step": 55, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.05339849220775351, |
| "grad_norm": 13.451016426086426, |
| "learning_rate": 0.00019999551396300723, |
| "logits/chosen": -0.6104876399040222, |
| "logits/rejected": -0.6144217848777771, |
| "logps/chosen": -11.782422065734863, |
| "logps/rejected": -26.71551513671875, |
| "loss": 1.1726720333099365, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6291560530662537, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.0043334998190402985, |
| "rewards/margins": 0.6636021137237549, |
| "rewards/rejected": -0.6679355502128601, |
| "step": 56, |
| "train_speed(iter/s)": 0.005523 |
| }, |
| { |
| "epoch": 0.054352036711463395, |
| "grad_norm": 7.804044246673584, |
| "learning_rate": 0.00019999202486950177, |
| "logits/chosen": -0.5772112011909485, |
| "logits/rejected": -0.5761610865592957, |
| "logps/chosen": -23.908967971801758, |
| "logps/rejected": -30.196250915527344, |
| "loss": 1.3278322219848633, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7636411786079407, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.15834051370620728, |
| "rewards/margins": 0.4628582298755646, |
| "rewards/rejected": -0.3045177161693573, |
| "step": 57, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.055305581215173275, |
| "grad_norm": 7.5992913246154785, |
| "learning_rate": 0.00019998753895176575, |
| "logits/chosen": -0.6457486748695374, |
| "logits/rejected": -0.6466608047485352, |
| "logps/chosen": -10.734827041625977, |
| "logps/rejected": -32.13155746459961, |
| "loss": 1.0030261278152466, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5355030298233032, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.01070893183350563, |
| "rewards/margins": 0.7878642082214355, |
| "rewards/rejected": -0.7985730171203613, |
| "step": 58, |
| "train_speed(iter/s)": 0.005524 |
| }, |
| { |
| "epoch": 0.05625912571888316, |
| "grad_norm": 5.3810601234436035, |
| "learning_rate": 0.00019998205625451943, |
| "logits/chosen": -0.6111299991607666, |
| "logits/rejected": -0.6088098287582397, |
| "logps/chosen": -16.970266342163086, |
| "logps/rejected": -19.622106552124023, |
| "loss": 0.9686940908432007, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5118071436882019, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.15675117075443268, |
| "rewards/margins": 0.8334945440292358, |
| "rewards/rejected": -0.6767433881759644, |
| "step": 59, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.05721267022259305, |
| "grad_norm": 3.480093002319336, |
| "learning_rate": 0.00019997557683242004, |
| "logits/chosen": -0.5985093712806702, |
| "logits/rejected": -0.6007335186004639, |
| "logps/chosen": -14.120916366577148, |
| "logps/rejected": -24.104907989501953, |
| "loss": 0.9003526568412781, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.466304212808609, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.13193026185035706, |
| "rewards/margins": 1.0070805549621582, |
| "rewards/rejected": -0.8751502633094788, |
| "step": 60, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.05816621472630293, |
| "grad_norm": 3.3445444107055664, |
| "learning_rate": 0.00019996810075006117, |
| "logits/chosen": -0.6064149141311646, |
| "logits/rejected": -0.6075825691223145, |
| "logps/chosen": -10.57797622680664, |
| "logps/rejected": -21.275867462158203, |
| "loss": 0.9624521732330322, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.41281017661094666, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.06739869713783264, |
| "rewards/margins": 0.5023229122161865, |
| "rewards/rejected": -0.43492427468299866, |
| "step": 61, |
| "train_speed(iter/s)": 0.005519 |
| }, |
| { |
| "epoch": 0.059119759230012815, |
| "grad_norm": 5.101805210113525, |
| "learning_rate": 0.00019995962808197216, |
| "logits/chosen": -0.6019335985183716, |
| "logits/rejected": -0.6061650514602661, |
| "logps/chosen": -12.45846939086914, |
| "logps/rejected": -22.627965927124023, |
| "loss": 1.1021240949630737, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5154472589492798, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.0749291479587555, |
| "rewards/margins": 0.5026906728744507, |
| "rewards/rejected": -0.5776197910308838, |
| "step": 62, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.060073303733722695, |
| "grad_norm": 3.7086844444274902, |
| "learning_rate": 0.0001999501589126174, |
| "logits/chosen": -0.598800539970398, |
| "logits/rejected": -0.5973880887031555, |
| "logps/chosen": -16.170019149780273, |
| "logps/rejected": -24.100147247314453, |
| "loss": 0.9728513956069946, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4919710159301758, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.14402300119400024, |
| "rewards/margins": 0.7554571628570557, |
| "rewards/rejected": -0.6114341616630554, |
| "step": 63, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.06102684823743258, |
| "grad_norm": 6.82169246673584, |
| "learning_rate": 0.00019993969333639532, |
| "logits/chosen": -0.5916394591331482, |
| "logits/rejected": -0.5948237180709839, |
| "logps/chosen": -6.504903793334961, |
| "logps/rejected": -23.65030860900879, |
| "loss": 0.8641103506088257, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3815235197544098, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.06883495301008224, |
| "rewards/margins": 0.6778679490089417, |
| "rewards/rejected": -0.6090329885482788, |
| "step": 64, |
| "train_speed(iter/s)": 0.005524 |
| }, |
| { |
| "epoch": 0.06198039274114246, |
| "grad_norm": 6.41129207611084, |
| "learning_rate": 0.0001999282314576377, |
| "logits/chosen": -0.6117686033248901, |
| "logits/rejected": -0.6133745312690735, |
| "logps/chosen": -7.471805572509766, |
| "logps/rejected": -19.006999969482422, |
| "loss": 0.8599905371665955, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3879605829715729, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.15403376519680023, |
| "rewards/margins": 0.6219788193702698, |
| "rewards/rejected": -0.4679450988769531, |
| "step": 65, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.06293393724485236, |
| "grad_norm": 3.6126596927642822, |
| "learning_rate": 0.00019991577339060842, |
| "logits/chosen": -0.6491844654083252, |
| "logits/rejected": -0.6502828001976013, |
| "logps/chosen": -9.777487754821777, |
| "logps/rejected": -19.9858455657959, |
| "loss": 0.9987360835075378, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4526561498641968, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.14287549257278442, |
| "rewards/margins": 0.528179407119751, |
| "rewards/rejected": -0.38530388474464417, |
| "step": 66, |
| "train_speed(iter/s)": 0.005524 |
| }, |
| { |
| "epoch": 0.06388748174856224, |
| "grad_norm": 3.5133907794952393, |
| "learning_rate": 0.0001999023192595024, |
| "logits/chosen": -0.6023973822593689, |
| "logits/rejected": -0.6058337092399597, |
| "logps/chosen": -11.287931442260742, |
| "logps/rejected": -23.294925689697266, |
| "loss": 0.949726939201355, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49871301651000977, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.25335025787353516, |
| "rewards/margins": 0.7444449663162231, |
| "rewards/rejected": -0.491094708442688, |
| "step": 67, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.06484102625227212, |
| "grad_norm": 4.242381572723389, |
| "learning_rate": 0.00019988786919844436, |
| "logits/chosen": -0.577968955039978, |
| "logits/rejected": -0.584266185760498, |
| "logps/chosen": -7.122470378875732, |
| "logps/rejected": -23.440967559814453, |
| "loss": 0.825219988822937, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3752996325492859, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.28059279918670654, |
| "rewards/margins": 0.8312418460845947, |
| "rewards/rejected": -0.5506490468978882, |
| "step": 68, |
| "train_speed(iter/s)": 0.005524 |
| }, |
| { |
| "epoch": 0.065794570755982, |
| "grad_norm": 4.247474670410156, |
| "learning_rate": 0.00019987242335148757, |
| "logits/chosen": -0.6062893271446228, |
| "logits/rejected": -0.6092509031295776, |
| "logps/chosen": -9.965551376342773, |
| "logps/rejected": -16.18874740600586, |
| "loss": 1.0371503829956055, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4371563792228699, |
| "rewards/accuracies": 0.625, |
| "rewards/chosen": 0.08624501526355743, |
| "rewards/margins": 0.4600314795970917, |
| "rewards/rejected": -0.37378647923469543, |
| "step": 69, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.06674811525969189, |
| "grad_norm": 3.118610143661499, |
| "learning_rate": 0.0001998559818726122, |
| "logits/chosen": -0.651878297328949, |
| "logits/rejected": -0.6511794328689575, |
| "logps/chosen": -17.028488159179688, |
| "logps/rejected": -18.37329864501953, |
| "loss": 1.1015472412109375, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5589602589607239, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.17374631762504578, |
| "rewards/margins": 0.5566114187240601, |
| "rewards/rejected": -0.3828650414943695, |
| "step": 70, |
| "train_speed(iter/s)": 0.005526 |
| }, |
| { |
| "epoch": 0.06770165976340177, |
| "grad_norm": 3.3582799434661865, |
| "learning_rate": 0.00019983854492572394, |
| "logits/chosen": -0.615595281124115, |
| "logits/rejected": -0.6146353483200073, |
| "logps/chosen": -12.519451141357422, |
| "logps/rejected": -18.15428924560547, |
| "loss": 0.9180172085762024, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3709501624107361, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.09964233636856079, |
| "rewards/margins": 0.6540214419364929, |
| "rewards/rejected": -0.5543791651725769, |
| "step": 71, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.06865520426711165, |
| "grad_norm": 2.883702516555786, |
| "learning_rate": 0.00019982011268465243, |
| "logits/chosen": -0.5868794918060303, |
| "logits/rejected": -0.5905233025550842, |
| "logps/chosen": -14.138279914855957, |
| "logps/rejected": -27.953182220458984, |
| "loss": 1.0747126340866089, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46605974435806274, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.03510252386331558, |
| "rewards/margins": 0.6189652681350708, |
| "rewards/rejected": -0.5838626623153687, |
| "step": 72, |
| "train_speed(iter/s)": 0.005526 |
| }, |
| { |
| "epoch": 0.06960874877082154, |
| "grad_norm": 2.9610211849212646, |
| "learning_rate": 0.00019980068533314934, |
| "logits/chosen": -0.6018360257148743, |
| "logits/rejected": -0.6016470789909363, |
| "logps/chosen": -14.77442455291748, |
| "logps/rejected": -16.293825149536133, |
| "loss": 1.1167826652526855, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5493913888931274, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.20179376006126404, |
| "rewards/margins": 0.5395517945289612, |
| "rewards/rejected": -0.3377581536769867, |
| "step": 73, |
| "train_speed(iter/s)": 0.005526 |
| }, |
| { |
| "epoch": 0.07056229327453142, |
| "grad_norm": 3.1142945289611816, |
| "learning_rate": 0.00019978026306488668, |
| "logits/chosen": -0.5901756286621094, |
| "logits/rejected": -0.5861356258392334, |
| "logps/chosen": -12.717107772827148, |
| "logps/rejected": -19.3599796295166, |
| "loss": 0.9646521210670471, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.42209792137145996, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.19932276010513306, |
| "rewards/margins": 0.5936742424964905, |
| "rewards/rejected": -0.3943515419960022, |
| "step": 74, |
| "train_speed(iter/s)": 0.005525 |
| }, |
| { |
| "epoch": 0.0715158377782413, |
| "grad_norm": 2.8381545543670654, |
| "learning_rate": 0.00019975884608345476, |
| "logits/chosen": -0.5791196227073669, |
| "logits/rejected": -0.5793704390525818, |
| "logps/chosen": -11.382536888122559, |
| "logps/rejected": -17.99052619934082, |
| "loss": 1.0251520872116089, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5087648630142212, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.225914865732193, |
| "rewards/margins": 0.544399619102478, |
| "rewards/rejected": -0.3184847831726074, |
| "step": 75, |
| "train_speed(iter/s)": 0.005523 |
| }, |
| { |
| "epoch": 0.0724693822819512, |
| "grad_norm": 2.720726251602173, |
| "learning_rate": 0.0001997364346023603, |
| "logits/chosen": -0.5865166187286377, |
| "logits/rejected": -0.5875246524810791, |
| "logps/chosen": -14.62844467163086, |
| "logps/rejected": -26.72977638244629, |
| "loss": 0.9625909924507141, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5162026882171631, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2656521499156952, |
| "rewards/margins": 0.8063244819641113, |
| "rewards/rejected": -0.5406723022460938, |
| "step": 76, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.07342292678566108, |
| "grad_norm": 7.292218208312988, |
| "learning_rate": 0.0001997130288450242, |
| "logits/chosen": -0.5742957592010498, |
| "logits/rejected": -0.5747869610786438, |
| "logps/chosen": -15.201194763183594, |
| "logps/rejected": -21.86297607421875, |
| "loss": 1.2068696022033691, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7135031819343567, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.23197884857654572, |
| "rewards/margins": 0.7994663119316101, |
| "rewards/rejected": -0.5674874782562256, |
| "step": 77, |
| "train_speed(iter/s)": 0.005522 |
| }, |
| { |
| "epoch": 0.07437647128937096, |
| "grad_norm": 3.270038366317749, |
| "learning_rate": 0.00019968862904477935, |
| "logits/chosen": -0.5858986377716064, |
| "logits/rejected": -0.588924765586853, |
| "logps/chosen": -9.959943771362305, |
| "logps/rejected": -30.939224243164062, |
| "loss": 0.8423591256141663, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.42530590295791626, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.16566459834575653, |
| "rewards/margins": 1.2258960008621216, |
| "rewards/rejected": -1.060231328010559, |
| "step": 78, |
| "train_speed(iter/s)": 0.005518 |
| }, |
| { |
| "epoch": 0.07533001579308084, |
| "grad_norm": 4.3024821281433105, |
| "learning_rate": 0.00019966323544486818, |
| "logits/chosen": -0.6145219802856445, |
| "logits/rejected": -0.6170623898506165, |
| "logps/chosen": -15.870341300964355, |
| "logps/rejected": -31.39044952392578, |
| "loss": 0.8412056565284729, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4725872874259949, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3251492381095886, |
| "rewards/margins": 1.2906752824783325, |
| "rewards/rejected": -0.9655259251594543, |
| "step": 79, |
| "train_speed(iter/s)": 0.005516 |
| }, |
| { |
| "epoch": 0.07628356029679073, |
| "grad_norm": 5.5750732421875, |
| "learning_rate": 0.00019963684829844052, |
| "logits/chosen": -0.6042959094047546, |
| "logits/rejected": -0.6049582362174988, |
| "logps/chosen": -13.382628440856934, |
| "logps/rejected": -21.927295684814453, |
| "loss": 0.993065357208252, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49278005957603455, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.10083693265914917, |
| "rewards/margins": 0.7778795957565308, |
| "rewards/rejected": -0.6770426630973816, |
| "step": 80, |
| "train_speed(iter/s)": 0.005517 |
| }, |
| { |
| "epoch": 0.07723710480050061, |
| "grad_norm": 7.816519260406494, |
| "learning_rate": 0.0001996094678685508, |
| "logits/chosen": -0.5581300258636475, |
| "logits/rejected": -0.5570173263549805, |
| "logps/chosen": -16.26945686340332, |
| "logps/rejected": -28.130666732788086, |
| "loss": 1.1555508375167847, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5590921640396118, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": -0.22734299302101135, |
| "rewards/margins": 0.652872622013092, |
| "rewards/rejected": -0.8802156448364258, |
| "step": 81, |
| "train_speed(iter/s)": 0.005518 |
| }, |
| { |
| "epoch": 0.07819064930421049, |
| "grad_norm": 4.555399417877197, |
| "learning_rate": 0.00019958109442815553, |
| "logits/chosen": -0.562245786190033, |
| "logits/rejected": -0.5638425946235657, |
| "logps/chosen": -17.669172286987305, |
| "logps/rejected": -31.455379486083984, |
| "loss": 1.0409901142120361, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5925040245056152, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.18633463978767395, |
| "rewards/margins": 1.1558425426483154, |
| "rewards/rejected": -1.3421772718429565, |
| "step": 82, |
| "train_speed(iter/s)": 0.005517 |
| }, |
| { |
| "epoch": 0.07914419380792038, |
| "grad_norm": 4.788554668426514, |
| "learning_rate": 0.00019955172826011062, |
| "logits/chosen": -0.53816819190979, |
| "logits/rejected": -0.539014458656311, |
| "logps/chosen": -13.409234046936035, |
| "logps/rejected": -24.46169090270996, |
| "loss": 1.0504765510559082, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5079448819160461, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.030599184334278107, |
| "rewards/margins": 0.6909205317497253, |
| "rewards/rejected": -0.7215197086334229, |
| "step": 83, |
| "train_speed(iter/s)": 0.005518 |
| }, |
| { |
| "epoch": 0.08009773831163026, |
| "grad_norm": 2.9610979557037354, |
| "learning_rate": 0.00019952136965716846, |
| "logits/chosen": -0.5609460473060608, |
| "logits/rejected": -0.5607710480690002, |
| "logps/chosen": -15.43799114227295, |
| "logps/rejected": -20.685916900634766, |
| "loss": 0.9568982720375061, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49247080087661743, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2509080469608307, |
| "rewards/margins": 0.9044961333274841, |
| "rewards/rejected": -0.653588056564331, |
| "step": 84, |
| "train_speed(iter/s)": 0.005516 |
| }, |
| { |
| "epoch": 0.08105128281534014, |
| "grad_norm": 2.7049379348754883, |
| "learning_rate": 0.00019949001892197515, |
| "logits/chosen": -0.5431854128837585, |
| "logits/rejected": -0.5459212064743042, |
| "logps/chosen": -11.692042350769043, |
| "logps/rejected": -25.70047378540039, |
| "loss": 0.9204345941543579, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5127474069595337, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.16273778676986694, |
| "rewards/margins": 1.052358865737915, |
| "rewards/rejected": -0.8896210193634033, |
| "step": 85, |
| "train_speed(iter/s)": 0.005518 |
| }, |
| { |
| "epoch": 0.08200482731905002, |
| "grad_norm": 2.835888624191284, |
| "learning_rate": 0.00019945767636706728, |
| "logits/chosen": -0.5524388551712036, |
| "logits/rejected": -0.5518356561660767, |
| "logps/chosen": -9.604469299316406, |
| "logps/rejected": -18.570831298828125, |
| "loss": 0.7963011860847473, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.35101598501205444, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.20881126821041107, |
| "rewards/margins": 0.7979729771614075, |
| "rewards/rejected": -0.58916175365448, |
| "step": 86, |
| "train_speed(iter/s)": 0.005516 |
| }, |
| { |
| "epoch": 0.08295837182275992, |
| "grad_norm": 4.458975315093994, |
| "learning_rate": 0.00019942434231486902, |
| "logits/chosen": -0.5035311579704285, |
| "logits/rejected": -0.5041376352310181, |
| "logps/chosen": -12.906057357788086, |
| "logps/rejected": -21.71013641357422, |
| "loss": 0.9929911494255066, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5292322039604187, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.23509997129440308, |
| "rewards/margins": 0.7336819171905518, |
| "rewards/rejected": -0.49858203530311584, |
| "step": 87, |
| "train_speed(iter/s)": 0.005515 |
| }, |
| { |
| "epoch": 0.0839119163264698, |
| "grad_norm": 5.752819061279297, |
| "learning_rate": 0.0001993900170976888, |
| "logits/chosen": -0.5372301340103149, |
| "logits/rejected": -0.5387623310089111, |
| "logps/chosen": -12.41868782043457, |
| "logps/rejected": -23.16730499267578, |
| "loss": 0.9672287106513977, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4671844244003296, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.22129932045936584, |
| "rewards/margins": 0.8583503365516663, |
| "rewards/rejected": -0.637050986289978, |
| "step": 88, |
| "train_speed(iter/s)": 0.005516 |
| }, |
| { |
| "epoch": 0.08486546083017968, |
| "grad_norm": 3.0927765369415283, |
| "learning_rate": 0.00019935470105771598, |
| "logits/chosen": -0.5962197780609131, |
| "logits/rejected": -0.5928555130958557, |
| "logps/chosen": -15.36233139038086, |
| "logps/rejected": -16.967832565307617, |
| "loss": 1.0067566633224487, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5986248850822449, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.20106852054595947, |
| "rewards/margins": 0.8472704291343689, |
| "rewards/rejected": -0.6462019681930542, |
| "step": 89, |
| "train_speed(iter/s)": 0.005517 |
| }, |
| { |
| "epoch": 0.08581900533388957, |
| "grad_norm": 4.051328659057617, |
| "learning_rate": 0.00019931839454701743, |
| "logits/chosen": -0.5495755672454834, |
| "logits/rejected": -0.54953533411026, |
| "logps/chosen": -9.681739807128906, |
| "logps/rejected": -17.38517951965332, |
| "loss": 0.9176310896873474, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4568890631198883, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.18029510974884033, |
| "rewards/margins": 0.7410764694213867, |
| "rewards/rejected": -0.5607813596725464, |
| "step": 90, |
| "train_speed(iter/s)": 0.005516 |
| }, |
| { |
| "epoch": 0.08677254983759945, |
| "grad_norm": 2.651430368423462, |
| "learning_rate": 0.00019928109792753418, |
| "logits/chosen": -0.5709578990936279, |
| "logits/rejected": -0.5723389983177185, |
| "logps/chosen": -12.097832679748535, |
| "logps/rejected": -25.470287322998047, |
| "loss": 0.8452543020248413, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4146232008934021, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2571614384651184, |
| "rewards/margins": 0.9069947600364685, |
| "rewards/rejected": -0.6498332619667053, |
| "step": 91, |
| "train_speed(iter/s)": 0.005515 |
| }, |
| { |
| "epoch": 0.08772609434130933, |
| "grad_norm": 3.9205963611602783, |
| "learning_rate": 0.0001992428115710776, |
| "logits/chosen": -0.5633900761604309, |
| "logits/rejected": -0.5629602074623108, |
| "logps/chosen": -15.341146469116211, |
| "logps/rejected": -22.676523208618164, |
| "loss": 1.0960146188735962, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6228011846542358, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.2320929765701294, |
| "rewards/margins": 0.802864670753479, |
| "rewards/rejected": -0.5707716941833496, |
| "step": 92, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.08867963884501923, |
| "grad_norm": 2.4844846725463867, |
| "learning_rate": 0.00019920353585932578, |
| "logits/chosen": -0.5643666982650757, |
| "logits/rejected": -0.5697072148323059, |
| "logps/chosen": -7.112787246704102, |
| "logps/rejected": -29.775066375732422, |
| "loss": 0.7670912742614746, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3726654350757599, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.11930885910987854, |
| "rewards/margins": 1.221017837524414, |
| "rewards/rejected": -1.101709008216858, |
| "step": 93, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.0896331833487291, |
| "grad_norm": 3.3409717082977295, |
| "learning_rate": 0.00019916327118381982, |
| "logits/chosen": -0.5507174730300903, |
| "logits/rejected": -0.5550180673599243, |
| "logps/chosen": -6.935158729553223, |
| "logps/rejected": -26.466045379638672, |
| "loss": 0.8178773522377014, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3691931962966919, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": -0.014170083217322826, |
| "rewards/margins": 0.906183123588562, |
| "rewards/rejected": -0.9203532338142395, |
| "step": 94, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.09058672785243899, |
| "grad_norm": 3.8606507778167725, |
| "learning_rate": 0.0001991220179459597, |
| "logits/chosen": -0.5692034959793091, |
| "logits/rejected": -0.5723109841346741, |
| "logps/chosen": -9.636994361877441, |
| "logps/rejected": -28.736644744873047, |
| "loss": 0.7489418387413025, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.38759085536003113, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.1789592206478119, |
| "rewards/margins": 1.2420873641967773, |
| "rewards/rejected": -1.0631282329559326, |
| "step": 95, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.09154027235614887, |
| "grad_norm": 4.69579553604126, |
| "learning_rate": 0.00019907977655700054, |
| "logits/chosen": -0.5835409760475159, |
| "logits/rejected": -0.5857175588607788, |
| "logps/chosen": -8.839982032775879, |
| "logps/rejected": -26.350032806396484, |
| "loss": 0.8248448371887207, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4012177586555481, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.14620812237262726, |
| "rewards/margins": 1.2952075004577637, |
| "rewards/rejected": -1.1489993333816528, |
| "step": 96, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.09249381685985876, |
| "grad_norm": 3.4665541648864746, |
| "learning_rate": 0.00019903654743804833, |
| "logits/chosen": -0.6227341294288635, |
| "logits/rejected": -0.6252981424331665, |
| "logps/chosen": -11.844514846801758, |
| "logps/rejected": -29.124967575073242, |
| "loss": 0.8466665744781494, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3924159109592438, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": -0.03820016235113144, |
| "rewards/margins": 1.3871092796325684, |
| "rewards/rejected": -1.425309419631958, |
| "step": 97, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.09344736136356864, |
| "grad_norm": 13.193551063537598, |
| "learning_rate": 0.00019899233102005573, |
| "logits/chosen": -0.5675249695777893, |
| "logits/rejected": -0.571427583694458, |
| "logps/chosen": -11.932504653930664, |
| "logps/rejected": -29.481807708740234, |
| "loss": 1.3480544090270996, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.8751646280288696, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.04504670575261116, |
| "rewards/margins": 1.2038631439208984, |
| "rewards/rejected": -1.248909831047058, |
| "step": 98, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.09440090586727852, |
| "grad_norm": 13.958789825439453, |
| "learning_rate": 0.00019894712774381787, |
| "logits/chosen": -0.5426734685897827, |
| "logits/rejected": -0.5455094575881958, |
| "logps/chosen": -14.97989273071289, |
| "logps/rejected": -29.963254928588867, |
| "loss": 0.9666093587875366, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5926772356033325, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": -0.12036357820034027, |
| "rewards/margins": 1.3575993776321411, |
| "rewards/rejected": -1.4779632091522217, |
| "step": 99, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.09535445037098841, |
| "grad_norm": 3.8765738010406494, |
| "learning_rate": 0.00019890093805996793, |
| "logits/chosen": -0.5699120163917542, |
| "logits/rejected": -0.5716601014137268, |
| "logps/chosen": -18.304710388183594, |
| "logps/rejected": -37.15324783325195, |
| "loss": 1.0460050106048584, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6231843829154968, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.23249366879463196, |
| "rewards/margins": 1.3045672178268433, |
| "rewards/rejected": -1.5370607376098633, |
| "step": 100, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.0963079948746983, |
| "grad_norm": 3.2104878425598145, |
| "learning_rate": 0.00019885376242897258, |
| "logits/chosen": -0.5706620812416077, |
| "logits/rejected": -0.5722963213920593, |
| "logps/chosen": -14.833114624023438, |
| "logps/rejected": -30.274829864501953, |
| "loss": 1.1376781463623047, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.653939425945282, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.14056257903575897, |
| "rewards/margins": 1.1054493188858032, |
| "rewards/rejected": -0.9648867845535278, |
| "step": 101, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.09726153937840817, |
| "grad_norm": 2.326752185821533, |
| "learning_rate": 0.00019880560132112742, |
| "logits/chosen": -0.5489917993545532, |
| "logits/rejected": -0.5558469891548157, |
| "logps/chosen": -10.081119537353516, |
| "logps/rejected": -31.342273712158203, |
| "loss": 0.9489866495132446, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5341838002204895, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.08325084298849106, |
| "rewards/margins": 1.2551041841506958, |
| "rewards/rejected": -1.1718534231185913, |
| "step": 102, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.09821508388211805, |
| "grad_norm": 2.702747344970703, |
| "learning_rate": 0.0001987564552165524, |
| "logits/chosen": -0.5335314869880676, |
| "logits/rejected": -0.5375723838806152, |
| "logps/chosen": -6.767879962921143, |
| "logps/rejected": -26.971349716186523, |
| "loss": 0.7666488885879517, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3699600100517273, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.2037293165922165, |
| "rewards/margins": 1.2131260633468628, |
| "rewards/rejected": -1.0093967914581299, |
| "step": 103, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.09916862838582795, |
| "grad_norm": 3.298539638519287, |
| "learning_rate": 0.0001987063246051868, |
| "logits/chosen": -0.5586405992507935, |
| "logits/rejected": -0.5575414299964905, |
| "logps/chosen": -10.250675201416016, |
| "logps/rejected": -19.98495864868164, |
| "loss": 0.9064714312553406, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.38871869444847107, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.07911191880702972, |
| "rewards/margins": 0.7202980518341064, |
| "rewards/rejected": -0.6411861181259155, |
| "step": 104, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.10012217288953783, |
| "grad_norm": 3.7112255096435547, |
| "learning_rate": 0.00019865520998678458, |
| "logits/chosen": -0.5400758385658264, |
| "logits/rejected": -0.5405173301696777, |
| "logps/chosen": -16.44561004638672, |
| "logps/rejected": -24.691865921020508, |
| "loss": 1.1246851682662964, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6655758023262024, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.11685307323932648, |
| "rewards/margins": 0.8305923938751221, |
| "rewards/rejected": -0.713739275932312, |
| "step": 105, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.10107571739324771, |
| "grad_norm": 6.40952205657959, |
| "learning_rate": 0.0001986031118709093, |
| "logits/chosen": -0.548525333404541, |
| "logits/rejected": -0.5509157180786133, |
| "logps/chosen": -11.731019020080566, |
| "logps/rejected": -22.46083641052246, |
| "loss": 1.37913179397583, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7638791799545288, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.029659561812877655, |
| "rewards/margins": 0.5513206124305725, |
| "rewards/rejected": -0.5809801816940308, |
| "step": 106, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.1020292618969576, |
| "grad_norm": 5.338200092315674, |
| "learning_rate": 0.00019855003077692897, |
| "logits/chosen": -0.5491806268692017, |
| "logits/rejected": -0.5485914945602417, |
| "logps/chosen": -10.374083518981934, |
| "logps/rejected": -22.91812515258789, |
| "loss": 0.9197418689727783, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.42541149258613586, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.23835767805576324, |
| "rewards/margins": 0.8718117475509644, |
| "rewards/rejected": -0.6334540843963623, |
| "step": 107, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.10298280640066748, |
| "grad_norm": 4.72066593170166, |
| "learning_rate": 0.00019849596723401107, |
| "logits/chosen": -0.5481430888175964, |
| "logits/rejected": -0.552554190158844, |
| "logps/chosen": -14.082160949707031, |
| "logps/rejected": -25.61027717590332, |
| "loss": 1.2021526098251343, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6988036036491394, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.09246861189603806, |
| "rewards/margins": 0.8137391805648804, |
| "rewards/rejected": -0.7212705612182617, |
| "step": 108, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.10393635090437736, |
| "grad_norm": 2.7633321285247803, |
| "learning_rate": 0.00019844092178111702, |
| "logits/chosen": -0.508384108543396, |
| "logits/rejected": -0.5140159130096436, |
| "logps/chosen": -6.925086975097656, |
| "logps/rejected": -24.077953338623047, |
| "loss": 0.8022588491439819, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.41396474838256836, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.16561280190944672, |
| "rewards/margins": 1.0861924886703491, |
| "rewards/rejected": -0.9205797910690308, |
| "step": 109, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.10488989540808726, |
| "grad_norm": 2.4014365673065186, |
| "learning_rate": 0.00019838489496699704, |
| "logits/chosen": -0.5266930460929871, |
| "logits/rejected": -0.5241900682449341, |
| "logps/chosen": -15.143444061279297, |
| "logps/rejected": -18.07321548461914, |
| "loss": 0.8957412242889404, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5194482803344727, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.33800825476646423, |
| "rewards/margins": 1.0479741096496582, |
| "rewards/rejected": -0.7099659442901611, |
| "step": 110, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.10584343991179714, |
| "grad_norm": 3.5473034381866455, |
| "learning_rate": 0.0001983278873501845, |
| "logits/chosen": -0.5651346445083618, |
| "logits/rejected": -0.5652989149093628, |
| "logps/chosen": -13.63066291809082, |
| "logps/rejected": -21.72479820251465, |
| "loss": 1.070034146308899, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5245512127876282, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.1012478768825531, |
| "rewards/margins": 0.5533490180969238, |
| "rewards/rejected": -0.4521011710166931, |
| "step": 111, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.10679698441550702, |
| "grad_norm": 2.844266653060913, |
| "learning_rate": 0.00019826989949899048, |
| "logits/chosen": -0.5871210694313049, |
| "logits/rejected": -0.5863486528396606, |
| "logps/chosen": -10.202323913574219, |
| "logps/rejected": -17.968069076538086, |
| "loss": 0.9712742567062378, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4458525776863098, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.31141582131385803, |
| "rewards/margins": 0.6074751615524292, |
| "rewards/rejected": -0.29605934023857117, |
| "step": 112, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.1077505289192169, |
| "grad_norm": 3.325552225112915, |
| "learning_rate": 0.00019821093199149804, |
| "logits/chosen": -0.5867654085159302, |
| "logits/rejected": -0.590225338935852, |
| "logps/chosen": -14.67109489440918, |
| "logps/rejected": -31.97191619873047, |
| "loss": 0.8784574270248413, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5371198058128357, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.31997063755989075, |
| "rewards/margins": 1.1458133459091187, |
| "rewards/rejected": -0.8258427381515503, |
| "step": 113, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.10870407342292679, |
| "grad_norm": 2.5996289253234863, |
| "learning_rate": 0.00019815098541555646, |
| "logits/chosen": -0.6402957439422607, |
| "logits/rejected": -0.6378954648971558, |
| "logps/chosen": -12.175540924072266, |
| "logps/rejected": -20.870878219604492, |
| "loss": 0.9693875908851624, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5651832818984985, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3929046392440796, |
| "rewards/margins": 1.0991772413253784, |
| "rewards/rejected": -0.7062726020812988, |
| "step": 114, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.10965761792663667, |
| "grad_norm": 2.5734198093414307, |
| "learning_rate": 0.00019809006036877538, |
| "logits/chosen": -0.6097349524497986, |
| "logits/rejected": -0.6098358035087585, |
| "logps/chosen": -11.490409851074219, |
| "logps/rejected": -15.817056655883789, |
| "loss": 0.9781900644302368, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.502380907535553, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2869223654270172, |
| "rewards/margins": 0.795809268951416, |
| "rewards/rejected": -0.5088868737220764, |
| "step": 115, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.11061116243034655, |
| "grad_norm": 2.6200523376464844, |
| "learning_rate": 0.00019802815745851885, |
| "logits/chosen": -0.6539290547370911, |
| "logits/rejected": -0.6565437912940979, |
| "logps/chosen": -13.780235290527344, |
| "logps/rejected": -29.117767333984375, |
| "loss": 0.8663976192474365, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.406424343585968, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.24194149672985077, |
| "rewards/margins": 1.0130045413970947, |
| "rewards/rejected": -0.7710630893707275, |
| "step": 116, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.11156470693405644, |
| "grad_norm": 2.858734130859375, |
| "learning_rate": 0.00019796527730189936, |
| "logits/chosen": -0.6368309259414673, |
| "logits/rejected": -0.6411804556846619, |
| "logps/chosen": -12.20506477355957, |
| "logps/rejected": -22.50167465209961, |
| "loss": 0.9522262811660767, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5067539215087891, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.35891181230545044, |
| "rewards/margins": 0.9037349224090576, |
| "rewards/rejected": -0.5448231101036072, |
| "step": 117, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.11251825143776632, |
| "grad_norm": 3.5055670738220215, |
| "learning_rate": 0.0001979014205257715, |
| "logits/chosen": -0.6525743007659912, |
| "logits/rejected": -0.6540606021881104, |
| "logps/chosen": -15.675086975097656, |
| "logps/rejected": -24.1904239654541, |
| "loss": 1.0509792566299438, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5997871160507202, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.07162542641162872, |
| "rewards/margins": 1.1154685020446777, |
| "rewards/rejected": -1.0438430309295654, |
| "step": 118, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.1134717959414762, |
| "grad_norm": 3.984374761581421, |
| "learning_rate": 0.0001978365877667258, |
| "logits/chosen": -0.6372765302658081, |
| "logits/rejected": -0.6411250233650208, |
| "logps/chosen": -10.17730712890625, |
| "logps/rejected": -22.074499130249023, |
| "loss": 1.0653222799301147, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6034587025642395, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.198074609041214, |
| "rewards/margins": 1.0864827632904053, |
| "rewards/rejected": -0.8884081244468689, |
| "step": 119, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.1144253404451861, |
| "grad_norm": 3.182776689529419, |
| "learning_rate": 0.00019777077967108255, |
| "logits/chosen": -0.6417007446289062, |
| "logits/rejected": -0.6392112970352173, |
| "logps/chosen": -19.301258087158203, |
| "logps/rejected": -18.364166259765625, |
| "loss": 1.108437180519104, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5851361751556396, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.22438707947731018, |
| "rewards/margins": 0.5671754479408264, |
| "rewards/rejected": -0.3427883982658386, |
| "step": 120, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.11537888494889598, |
| "grad_norm": 3.537256956100464, |
| "learning_rate": 0.00019770399689488506, |
| "logits/chosen": -0.6460685729980469, |
| "logits/rejected": -0.6467642784118652, |
| "logps/chosen": -13.258935928344727, |
| "logps/rejected": -27.513343811035156, |
| "loss": 0.9472922682762146, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5081149935722351, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.23222729563713074, |
| "rewards/margins": 1.276731014251709, |
| "rewards/rejected": -1.0445036888122559, |
| "step": 121, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.11633242945260586, |
| "grad_norm": 3.096590280532837, |
| "learning_rate": 0.00019763624010389334, |
| "logits/chosen": -0.6088275909423828, |
| "logits/rejected": -0.6121100783348083, |
| "logps/chosen": -13.26574420928955, |
| "logps/rejected": -19.00273323059082, |
| "loss": 0.9677691459655762, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.507895290851593, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.22311073541641235, |
| "rewards/margins": 0.7144712209701538, |
| "rewards/rejected": -0.49136048555374146, |
| "step": 122, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.11728597395631574, |
| "grad_norm": 2.810216188430786, |
| "learning_rate": 0.0001975675099735774, |
| "logits/chosen": -0.6021947264671326, |
| "logits/rejected": -0.6030389070510864, |
| "logps/chosen": -8.321534156799316, |
| "logps/rejected": -17.207504272460938, |
| "loss": 0.8276495933532715, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3906245231628418, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.21257750689983368, |
| "rewards/margins": 0.894737958908081, |
| "rewards/rejected": -0.682160496711731, |
| "step": 123, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.11823951846002563, |
| "grad_norm": 2.6153383255004883, |
| "learning_rate": 0.0001974978071891104, |
| "logits/chosen": -0.6311705112457275, |
| "logits/rejected": -0.6307083964347839, |
| "logps/chosen": -10.833940505981445, |
| "logps/rejected": -22.41739273071289, |
| "loss": 0.8693855404853821, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4562944173812866, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.15080919861793518, |
| "rewards/margins": 1.2266969680786133, |
| "rewards/rejected": -1.0758877992630005, |
| "step": 124, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.11919306296373551, |
| "grad_norm": 3.493828535079956, |
| "learning_rate": 0.00019742713244536204, |
| "logits/chosen": -0.6434034109115601, |
| "logits/rejected": -0.6431565284729004, |
| "logps/chosen": -18.75763702392578, |
| "logps/rejected": -25.821609497070312, |
| "loss": 1.0967546701431274, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5587143898010254, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.0902448296546936, |
| "rewards/margins": 0.9879235029220581, |
| "rewards/rejected": -0.8976786732673645, |
| "step": 125, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.12014660746744539, |
| "grad_norm": 2.5747878551483154, |
| "learning_rate": 0.00019735548644689147, |
| "logits/chosen": -0.6225179433822632, |
| "logits/rejected": -0.6244460940361023, |
| "logps/chosen": -15.244443893432617, |
| "logps/rejected": -17.300045013427734, |
| "loss": 1.0364809036254883, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5735288858413696, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.416117787361145, |
| "rewards/margins": 0.7515360713005066, |
| "rewards/rejected": -0.3354182839393616, |
| "step": 126, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.12110015197115528, |
| "grad_norm": 3.198167562484741, |
| "learning_rate": 0.00019728286990794037, |
| "logits/chosen": -0.6006501317024231, |
| "logits/rejected": -0.6046801805496216, |
| "logps/chosen": -14.4312162399292, |
| "logps/rejected": -23.69890785217285, |
| "loss": 1.0553488731384277, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5887905955314636, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.162513867020607, |
| "rewards/margins": 0.9815673232078552, |
| "rewards/rejected": -0.8190534114837646, |
| "step": 127, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.12205369647486516, |
| "grad_norm": 3.224283456802368, |
| "learning_rate": 0.00019720928355242568, |
| "logits/chosen": -0.5655272006988525, |
| "logits/rejected": -0.5726292133331299, |
| "logps/chosen": -13.809501647949219, |
| "logps/rejected": -30.130277633666992, |
| "loss": 0.8311694264411926, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3935176134109497, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.027349811047315598, |
| "rewards/margins": 1.382154941558838, |
| "rewards/rejected": -1.3548052310943604, |
| "step": 128, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.12300724097857504, |
| "grad_norm": 2.575568199157715, |
| "learning_rate": 0.00019713472811393258, |
| "logits/chosen": -0.5765466094017029, |
| "logits/rejected": -0.5786842107772827, |
| "logps/chosen": -16.621131896972656, |
| "logps/rejected": -26.19173240661621, |
| "loss": 0.9337475895881653, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5804612636566162, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.37209561467170715, |
| "rewards/margins": 1.4012634754180908, |
| "rewards/rejected": -1.0291677713394165, |
| "step": 129, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.12396078548228492, |
| "grad_norm": 3.0303828716278076, |
| "learning_rate": 0.00019705920433570694, |
| "logits/chosen": -0.5693878531455994, |
| "logits/rejected": -0.5738221406936646, |
| "logps/chosen": -7.376468658447266, |
| "logps/rejected": -25.63204574584961, |
| "loss": 0.9063543081283569, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5075121521949768, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.23270781338214874, |
| "rewards/margins": 1.1151927709579468, |
| "rewards/rejected": -0.8824849128723145, |
| "step": 130, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.12491432998599482, |
| "grad_norm": 4.375239849090576, |
| "learning_rate": 0.0001969827129706482, |
| "logits/chosen": -0.5413441061973572, |
| "logits/rejected": -0.5445973873138428, |
| "logps/chosen": -9.677428245544434, |
| "logps/rejected": -23.95619010925293, |
| "loss": 0.982276439666748, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5150867104530334, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.23964405059814453, |
| "rewards/margins": 0.8764944076538086, |
| "rewards/rejected": -0.6368504762649536, |
| "step": 131, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.1258678744897047, |
| "grad_norm": 2.136566162109375, |
| "learning_rate": 0.0001969052547813016, |
| "logits/chosen": -0.5252913236618042, |
| "logits/rejected": -0.5288749933242798, |
| "logps/chosen": -8.76069450378418, |
| "logps/rejected": -24.643917083740234, |
| "loss": 0.6882707476615906, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3399735689163208, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.3247303366661072, |
| "rewards/margins": 1.320786952972412, |
| "rewards/rejected": -0.9960566759109497, |
| "step": 132, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.1268214189934146, |
| "grad_norm": 2.7579689025878906, |
| "learning_rate": 0.00019682683053985072, |
| "logits/chosen": -0.4897473454475403, |
| "logits/rejected": -0.49097952246665955, |
| "logps/chosen": -14.222724914550781, |
| "logps/rejected": -26.548240661621094, |
| "loss": 0.8395786881446838, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49962103366851807, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3120686113834381, |
| "rewards/margins": 1.3334513902664185, |
| "rewards/rejected": -1.0213829278945923, |
| "step": 133, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.12777496349712447, |
| "grad_norm": 4.233667850494385, |
| "learning_rate": 0.00019674744102810978, |
| "logits/chosen": -0.49640408158302307, |
| "logits/rejected": -0.49791407585144043, |
| "logps/chosen": -11.952919006347656, |
| "logps/rejected": -20.992504119873047, |
| "loss": 0.9811766147613525, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6130494475364685, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.26505932211875916, |
| "rewards/margins": 1.113063097000122, |
| "rewards/rejected": -0.8480038046836853, |
| "step": 134, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.12872850800083435, |
| "grad_norm": 4.032670974731445, |
| "learning_rate": 0.00019666708703751576, |
| "logits/chosen": -0.5555613040924072, |
| "logits/rejected": -0.5562028288841248, |
| "logps/chosen": -12.461511611938477, |
| "logps/rejected": -29.6381893157959, |
| "loss": 0.9406546354293823, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5542497634887695, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.14334315061569214, |
| "rewards/margins": 1.2391164302825928, |
| "rewards/rejected": -1.0957733392715454, |
| "step": 135, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.12968205250454423, |
| "grad_norm": 2.8314244747161865, |
| "learning_rate": 0.00019658576936912057, |
| "logits/chosen": -0.5166746973991394, |
| "logits/rejected": -0.5175175666809082, |
| "logps/chosen": -11.453944206237793, |
| "logps/rejected": -32.48845672607422, |
| "loss": 0.741032600402832, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.39420661330223083, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2297428399324417, |
| "rewards/margins": 1.5928231477737427, |
| "rewards/rejected": -1.3630802631378174, |
| "step": 136, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.1306355970082541, |
| "grad_norm": 3.786283016204834, |
| "learning_rate": 0.00019650348883358315, |
| "logits/chosen": -0.5285561084747314, |
| "logits/rejected": -0.529099702835083, |
| "logps/chosen": -14.34618091583252, |
| "logps/rejected": -24.930580139160156, |
| "loss": 1.0361278057098389, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.598253607749939, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2112821340560913, |
| "rewards/margins": 1.2288541793823242, |
| "rewards/rejected": -1.017572045326233, |
| "step": 137, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.131589141511964, |
| "grad_norm": 3.4468750953674316, |
| "learning_rate": 0.00019642024625116117, |
| "logits/chosen": -0.5355381369590759, |
| "logits/rejected": -0.5351199507713318, |
| "logps/chosen": -14.2181396484375, |
| "logps/rejected": -21.662395477294922, |
| "loss": 0.9722803831100464, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5212066769599915, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.12246156483888626, |
| "rewards/margins": 1.046801209449768, |
| "rewards/rejected": -0.9243396520614624, |
| "step": 138, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.1325426860156739, |
| "grad_norm": 4.629439830780029, |
| "learning_rate": 0.0001963360424517031, |
| "logits/chosen": -0.5707206726074219, |
| "logits/rejected": -0.5748513340950012, |
| "logps/chosen": -17.805238723754883, |
| "logps/rejected": -29.64284896850586, |
| "loss": 1.254711389541626, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.743948221206665, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.11810468882322311, |
| "rewards/margins": 0.9775583744049072, |
| "rewards/rejected": -0.8594536185264587, |
| "step": 139, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.13349623051938378, |
| "grad_norm": 4.580717086791992, |
| "learning_rate": 0.0001962508782746397, |
| "logits/chosen": -0.580274224281311, |
| "logits/rejected": -0.581068217754364, |
| "logps/chosen": -16.117170333862305, |
| "logps/rejected": -23.330665588378906, |
| "loss": 0.9780559539794922, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48741835355758667, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.07310809940099716, |
| "rewards/margins": 0.9340574741363525, |
| "rewards/rejected": -0.8609493374824524, |
| "step": 140, |
| "train_speed(iter/s)": 0.005514 |
| }, |
| { |
| "epoch": 0.13444977502309366, |
| "grad_norm": 3.511350631713867, |
| "learning_rate": 0.0001961647545689759, |
| "logits/chosen": -0.5712682604789734, |
| "logits/rejected": -0.5709258317947388, |
| "logps/chosen": -14.216093063354492, |
| "logps/rejected": -23.430875778198242, |
| "loss": 1.023219108581543, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5690780878067017, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.3575439751148224, |
| "rewards/margins": 0.9377648830413818, |
| "rewards/rejected": -0.5802209973335266, |
| "step": 141, |
| "train_speed(iter/s)": 0.005514 |
| }, |
| { |
| "epoch": 0.13540331952680354, |
| "grad_norm": 2.3146886825561523, |
| "learning_rate": 0.0001960776721932821, |
| "logits/chosen": -0.5722199082374573, |
| "logits/rejected": -0.5763861536979675, |
| "logps/chosen": -7.839071273803711, |
| "logps/rejected": -18.26845932006836, |
| "loss": 0.810951828956604, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3562580943107605, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.24190367758274078, |
| "rewards/margins": 0.711327850818634, |
| "rewards/rejected": -0.4694240987300873, |
| "step": 142, |
| "train_speed(iter/s)": 0.005514 |
| }, |
| { |
| "epoch": 0.13635686403051342, |
| "grad_norm": 3.1744766235351562, |
| "learning_rate": 0.00019598963201568573, |
| "logits/chosen": -0.5400611758232117, |
| "logits/rejected": -0.5411737561225891, |
| "logps/chosen": -13.320467948913574, |
| "logps/rejected": -24.537696838378906, |
| "loss": 1.0167641639709473, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47375380992889404, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.18297314643859863, |
| "rewards/margins": 0.6672495007514954, |
| "rewards/rejected": -0.48427632451057434, |
| "step": 143, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.1373104085342233, |
| "grad_norm": 2.385725259780884, |
| "learning_rate": 0.0001959006349138626, |
| "logits/chosen": -0.5638188123703003, |
| "logits/rejected": -0.5665206909179688, |
| "logps/chosen": -12.801736831665039, |
| "logps/rejected": -24.967641830444336, |
| "loss": 0.9001826047897339, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.45819178223609924, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.24550366401672363, |
| "rewards/margins": 0.9985946416854858, |
| "rewards/rejected": -0.7530909776687622, |
| "step": 144, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.13826395303793318, |
| "grad_norm": 4.4898362159729, |
| "learning_rate": 0.00019581068177502826, |
| "logits/chosen": -0.5841139554977417, |
| "logits/rejected": -0.5885876417160034, |
| "logps/chosen": -8.781448364257812, |
| "logps/rejected": -21.54075813293457, |
| "loss": 0.9311922192573547, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46065330505371094, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2900657057762146, |
| "rewards/margins": 0.7273497581481934, |
| "rewards/rejected": -0.43728405237197876, |
| "step": 145, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.1392174975416431, |
| "grad_norm": 2.794843912124634, |
| "learning_rate": 0.00019571977349592878, |
| "logits/chosen": -0.5932512879371643, |
| "logits/rejected": -0.5940472483634949, |
| "logps/chosen": -9.732755661010742, |
| "logps/rejected": -20.826379776000977, |
| "loss": 0.945945680141449, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47954535484313965, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2869046926498413, |
| "rewards/margins": 0.9880754947662354, |
| "rewards/rejected": -0.7011707425117493, |
| "step": 146, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.14017104204535297, |
| "grad_norm": 2.540703058242798, |
| "learning_rate": 0.00019562791098283225, |
| "logits/chosen": -0.6081781983375549, |
| "logits/rejected": -0.614071786403656, |
| "logps/chosen": -12.527294158935547, |
| "logps/rejected": -29.05521011352539, |
| "loss": 0.9200064539909363, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4640219807624817, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.25594115257263184, |
| "rewards/margins": 0.8903652429580688, |
| "rewards/rejected": -0.634424090385437, |
| "step": 147, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.14112458654906285, |
| "grad_norm": 2.9323384761810303, |
| "learning_rate": 0.0001955350951515195, |
| "logits/chosen": -0.6128370761871338, |
| "logits/rejected": -0.6138598322868347, |
| "logps/chosen": -12.749382019042969, |
| "logps/rejected": -25.719005584716797, |
| "loss": 0.9213395118713379, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.43978482484817505, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.32896676659584045, |
| "rewards/margins": 1.2176496982574463, |
| "rewards/rejected": -0.8886829018592834, |
| "step": 148, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.14207813105277273, |
| "grad_norm": 4.304955959320068, |
| "learning_rate": 0.00019544132692727497, |
| "logits/chosen": -0.6183297634124756, |
| "logits/rejected": -0.6181198358535767, |
| "logps/chosen": -13.527120590209961, |
| "logps/rejected": -16.62553596496582, |
| "loss": 1.1245884895324707, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5154122114181519, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": 0.12139306217432022, |
| "rewards/margins": 0.5662888884544373, |
| "rewards/rejected": -0.44489583373069763, |
| "step": 149, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.1430316755564826, |
| "grad_norm": 3.4540951251983643, |
| "learning_rate": 0.00019534660724487764, |
| "logits/chosen": -0.6565526127815247, |
| "logits/rejected": -0.6572035551071167, |
| "logps/chosen": -8.482949256896973, |
| "logps/rejected": -25.549943923950195, |
| "loss": 0.6943767070770264, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3159071207046509, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.13372917473316193, |
| "rewards/margins": 1.538865327835083, |
| "rewards/rejected": -1.4051361083984375, |
| "step": 150, |
| "train_speed(iter/s)": 0.005513 |
| }, |
| { |
| "epoch": 0.1439852200601925, |
| "grad_norm": 4.732980728149414, |
| "learning_rate": 0.00019525093704859156, |
| "logits/chosen": -0.6389154195785522, |
| "logits/rejected": -0.6404666304588318, |
| "logps/chosen": -9.446221351623535, |
| "logps/rejected": -21.919448852539062, |
| "loss": 0.9652438759803772, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.42131203413009644, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.06119174510240555, |
| "rewards/margins": 0.8354355096817017, |
| "rewards/rejected": -0.8966272473335266, |
| "step": 151, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.1449387645639024, |
| "grad_norm": 3.275040626525879, |
| "learning_rate": 0.00019515431729215642, |
| "logits/chosen": -0.6208993792533875, |
| "logits/rejected": -0.6198944449424744, |
| "logps/chosen": -14.077505111694336, |
| "logps/rejected": -20.674022674560547, |
| "loss": 0.9426023364067078, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4758264124393463, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.3683655261993408, |
| "rewards/margins": 0.8337981104850769, |
| "rewards/rejected": -0.4654325246810913, |
| "step": 152, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.14589230906761227, |
| "grad_norm": 3.4363420009613037, |
| "learning_rate": 0.0001950567489387783, |
| "logits/chosen": -0.6072810292243958, |
| "logits/rejected": -0.6104952692985535, |
| "logps/chosen": -11.343103408813477, |
| "logps/rejected": -27.840784072875977, |
| "loss": 0.8374794721603394, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47033166885375977, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.03130531311035156, |
| "rewards/margins": 1.3322855234146118, |
| "rewards/rejected": -1.3009803295135498, |
| "step": 153, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.14684585357132215, |
| "grad_norm": 4.580497741699219, |
| "learning_rate": 0.00019495823296111965, |
| "logits/chosen": -0.6362301111221313, |
| "logits/rejected": -0.6354808211326599, |
| "logps/chosen": -19.50163459777832, |
| "logps/rejected": -25.74669647216797, |
| "loss": 1.2240495681762695, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7012270092964172, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.006752293556928635, |
| "rewards/margins": 0.9509786367416382, |
| "rewards/rejected": -0.9442263245582581, |
| "step": 154, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.14779939807503203, |
| "grad_norm": 2.6184449195861816, |
| "learning_rate": 0.00019485877034128998, |
| "logits/chosen": -0.674143373966217, |
| "logits/rejected": -0.6776165962219238, |
| "logps/chosen": -7.580592155456543, |
| "logps/rejected": -31.08483123779297, |
| "loss": 0.6007921695709229, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3359020948410034, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.39511340856552124, |
| "rewards/margins": 1.9217884540557861, |
| "rewards/rejected": -1.5266749858856201, |
| "step": 155, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.14875294257874191, |
| "grad_norm": 10.089612007141113, |
| "learning_rate": 0.00019475836207083589, |
| "logits/chosen": -0.6476931571960449, |
| "logits/rejected": -0.6489571928977966, |
| "logps/chosen": -12.26353931427002, |
| "logps/rejected": -25.737834930419922, |
| "loss": 1.5494966506958008, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.9324380159378052, |
| "rewards/accuracies": 0.65625, |
| "rewards/chosen": -0.06559403240680695, |
| "rewards/margins": 0.7390923500061035, |
| "rewards/rejected": -0.8046863079071045, |
| "step": 156, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.1497064870824518, |
| "grad_norm": 3.3425323963165283, |
| "learning_rate": 0.0001946570091507311, |
| "logits/chosen": -0.6487354040145874, |
| "logits/rejected": -0.6536142826080322, |
| "logps/chosen": -10.630206108093262, |
| "logps/rejected": -30.927711486816406, |
| "loss": 0.9613731503486633, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6279934048652649, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.39098411798477173, |
| "rewards/margins": 1.6947877407073975, |
| "rewards/rejected": -1.3038034439086914, |
| "step": 157, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.15066003158616167, |
| "grad_norm": 7.0651702880859375, |
| "learning_rate": 0.0001945547125913667, |
| "logits/chosen": -0.6521321535110474, |
| "logits/rejected": -0.6505486369132996, |
| "logps/chosen": -15.865433692932129, |
| "logps/rejected": -35.44856262207031, |
| "loss": 0.792765736579895, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5261170864105225, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.2697344124317169, |
| "rewards/margins": 1.9019429683685303, |
| "rewards/rejected": -1.6322084665298462, |
| "step": 158, |
| "train_speed(iter/s)": 0.005512 |
| }, |
| { |
| "epoch": 0.15161357608987158, |
| "grad_norm": 5.0952863693237305, |
| "learning_rate": 0.00019445147341254094, |
| "logits/chosen": -0.6332048773765564, |
| "logits/rejected": -0.6331393122673035, |
| "logps/chosen": -10.345703125, |
| "logps/rejected": -25.010473251342773, |
| "loss": 0.9190976023674011, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4244757890701294, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.045503757894039154, |
| "rewards/margins": 1.3924332857131958, |
| "rewards/rejected": -1.346929669380188, |
| "step": 159, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.15256712059358146, |
| "grad_norm": 4.532683372497559, |
| "learning_rate": 0.00019434729264344898, |
| "logits/chosen": -0.6720902919769287, |
| "logits/rejected": -0.6760929226875305, |
| "logps/chosen": -12.491207122802734, |
| "logps/rejected": -29.585365295410156, |
| "loss": 0.9083388447761536, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48932063579559326, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.13267335295677185, |
| "rewards/margins": 1.416609287261963, |
| "rewards/rejected": -1.2839360237121582, |
| "step": 160, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.15352066509729134, |
| "grad_norm": 5.659564971923828, |
| "learning_rate": 0.0001942421713226729, |
| "logits/chosen": -0.636077880859375, |
| "logits/rejected": -0.6419317126274109, |
| "logps/chosen": -11.249347686767578, |
| "logps/rejected": -31.562650680541992, |
| "loss": 1.0359388589859009, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5222399234771729, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.1068134605884552, |
| "rewards/margins": 0.987252950668335, |
| "rewards/rejected": -0.8804395794868469, |
| "step": 161, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.15447420960100122, |
| "grad_norm": 2.4461114406585693, |
| "learning_rate": 0.00019413611049817097, |
| "logits/chosen": -0.6158936023712158, |
| "logits/rejected": -0.6181063652038574, |
| "logps/chosen": -12.928690910339355, |
| "logps/rejected": -33.6618766784668, |
| "loss": 0.8027182817459106, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4644929766654968, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.35731226205825806, |
| "rewards/margins": 1.6166467666625977, |
| "rewards/rejected": -1.2593344449996948, |
| "step": 162, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.1554277541047111, |
| "grad_norm": 2.674982786178589, |
| "learning_rate": 0.00019402911122726757, |
| "logits/chosen": -0.6532890200614929, |
| "logits/rejected": -0.6513383388519287, |
| "logps/chosen": -13.337392807006836, |
| "logps/rejected": -15.696168899536133, |
| "loss": 0.9040297269821167, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.430746465921402, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.368441641330719, |
| "rewards/margins": 0.7184236645698547, |
| "rewards/rejected": -0.34998205304145813, |
| "step": 163, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.15638129860842098, |
| "grad_norm": 2.6457912921905518, |
| "learning_rate": 0.0001939211745766424, |
| "logits/chosen": -0.6276657581329346, |
| "logits/rejected": -0.6290963292121887, |
| "logps/chosen": -11.891464233398438, |
| "logps/rejected": -23.75179100036621, |
| "loss": 0.7421783804893494, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.41357868909835815, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.3939753770828247, |
| "rewards/margins": 1.4096219539642334, |
| "rewards/rejected": -1.0156464576721191, |
| "step": 164, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.15733484311213086, |
| "grad_norm": 3.1174941062927246, |
| "learning_rate": 0.00019381230162231997, |
| "logits/chosen": -0.6429885029792786, |
| "logits/rejected": -0.6429612636566162, |
| "logps/chosen": -13.307516098022461, |
| "logps/rejected": -21.91159439086914, |
| "loss": 0.8932576775550842, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5357162952423096, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.40053704380989075, |
| "rewards/margins": 1.1449347734451294, |
| "rewards/rejected": -0.744397759437561, |
| "step": 165, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.15828838761584077, |
| "grad_norm": 3.907290458679199, |
| "learning_rate": 0.00019370249344965882, |
| "logits/chosen": -0.6336323618888855, |
| "logits/rejected": -0.6354680061340332, |
| "logps/chosen": -8.803092956542969, |
| "logps/rejected": -21.227846145629883, |
| "loss": 0.8063769936561584, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3984988331794739, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2638464570045471, |
| "rewards/margins": 1.1452890634536743, |
| "rewards/rejected": -0.8814425468444824, |
| "step": 166, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.15924193211955065, |
| "grad_norm": 3.197791814804077, |
| "learning_rate": 0.00019359175115334076, |
| "logits/chosen": -0.5956701636314392, |
| "logits/rejected": -0.5929427146911621, |
| "logps/chosen": -18.20105743408203, |
| "logps/rejected": -20.88482093811035, |
| "loss": 1.0089799165725708, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6080743670463562, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.26467055082321167, |
| "rewards/margins": 1.2077610492706299, |
| "rewards/rejected": -0.9430904388427734, |
| "step": 167, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.16019547662326053, |
| "grad_norm": 9.04864501953125, |
| "learning_rate": 0.00019348007583735983, |
| "logits/chosen": -0.5978728532791138, |
| "logits/rejected": -0.6020796895027161, |
| "logps/chosen": -11.225780487060547, |
| "logps/rejected": -26.560958862304688, |
| "loss": 0.803035318851471, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4957469701766968, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.25380873680114746, |
| "rewards/margins": 1.3392387628555298, |
| "rewards/rejected": -1.0854299068450928, |
| "step": 168, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.1611490211269704, |
| "grad_norm": 3.7316133975982666, |
| "learning_rate": 0.00019336746861501147, |
| "logits/chosen": -0.6536791920661926, |
| "logits/rejected": -0.6554186344146729, |
| "logps/chosen": -11.102974891662598, |
| "logps/rejected": -29.11667251586914, |
| "loss": 0.7718941569328308, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48562759160995483, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.23236791789531708, |
| "rewards/margins": 1.67207932472229, |
| "rewards/rejected": -1.439711570739746, |
| "step": 169, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.1621025656306803, |
| "grad_norm": 2.923807144165039, |
| "learning_rate": 0.00019325393060888124, |
| "logits/chosen": -0.6559415459632874, |
| "logits/rejected": -0.6620982885360718, |
| "logps/chosen": -11.615120887756348, |
| "logps/rejected": -43.504119873046875, |
| "loss": 0.7158108353614807, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.412832111120224, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.41992810368537903, |
| "rewards/margins": 1.7239785194396973, |
| "rewards/rejected": -1.3040504455566406, |
| "step": 170, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.16305611013439017, |
| "grad_norm": 9.927915573120117, |
| "learning_rate": 0.0001931394629508338, |
| "logits/chosen": -0.6775858402252197, |
| "logits/rejected": -0.6792483925819397, |
| "logps/chosen": -20.57831573486328, |
| "logps/rejected": -29.268760681152344, |
| "loss": 1.2057551145553589, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.8320274353027344, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.3444375693798065, |
| "rewards/margins": 1.6732782125473022, |
| "rewards/rejected": -1.3288406133651733, |
| "step": 171, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.16400965463810005, |
| "grad_norm": 4.74425745010376, |
| "learning_rate": 0.0001930240667820015, |
| "logits/chosen": -0.6995469927787781, |
| "logits/rejected": -0.7030329704284668, |
| "logps/chosen": -10.466329574584961, |
| "logps/rejected": -33.26238250732422, |
| "loss": 0.775245189666748, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5120316743850708, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3140904903411865, |
| "rewards/margins": 2.2553622722625732, |
| "rewards/rejected": -1.9412716627120972, |
| "step": 172, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.16496319914180996, |
| "grad_norm": 7.597793102264404, |
| "learning_rate": 0.00019290774325277305, |
| "logits/chosen": -0.6953250765800476, |
| "logits/rejected": -0.6955796480178833, |
| "logps/chosen": -13.002115249633789, |
| "logps/rejected": -20.02895164489746, |
| "loss": 0.9939925074577332, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5155970454216003, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2543705403804779, |
| "rewards/margins": 1.1046258211135864, |
| "rewards/rejected": -0.8502552509307861, |
| "step": 173, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.16591674364551984, |
| "grad_norm": 7.100286483764648, |
| "learning_rate": 0.00019279049352278208, |
| "logits/chosen": -0.683663547039032, |
| "logits/rejected": -0.6904964447021484, |
| "logps/chosen": -15.861849784851074, |
| "logps/rejected": -37.97547149658203, |
| "loss": 0.8642697334289551, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5443270802497864, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3070213496685028, |
| "rewards/margins": 2.0321590900421143, |
| "rewards/rejected": -1.725137710571289, |
| "step": 174, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.16687028814922972, |
| "grad_norm": 15.024664878845215, |
| "learning_rate": 0.0001926723187608955, |
| "logits/chosen": -0.6977289915084839, |
| "logits/rejected": -0.6982432007789612, |
| "logps/chosen": -15.910187721252441, |
| "logps/rejected": -33.083072662353516, |
| "loss": 1.3357112407684326, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7549878358840942, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.051902592182159424, |
| "rewards/margins": 1.6283537149429321, |
| "rewards/rejected": -1.6802561283111572, |
| "step": 175, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.1678238326529396, |
| "grad_norm": 4.188450336456299, |
| "learning_rate": 0.0001925532201452019, |
| "logits/chosen": -0.6970202326774597, |
| "logits/rejected": -0.7066731452941895, |
| "logps/chosen": -8.506889343261719, |
| "logps/rejected": -31.041738510131836, |
| "loss": 0.7935239672660828, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.43914929032325745, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.26104143261909485, |
| "rewards/margins": 1.6015070676803589, |
| "rewards/rejected": -1.3404656648635864, |
| "step": 176, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.16877737715664948, |
| "grad_norm": 2.6552200317382812, |
| "learning_rate": 0.0001924331988629999, |
| "logits/chosen": -0.6718675494194031, |
| "logits/rejected": -0.6740796566009521, |
| "logps/chosen": -13.090902328491211, |
| "logps/rejected": -39.854984283447266, |
| "loss": 0.8511579036712646, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4888760447502136, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.07794294506311417, |
| "rewards/margins": 1.9545315504074097, |
| "rewards/rejected": -1.8765883445739746, |
| "step": 177, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.16973092166035936, |
| "grad_norm": 4.044957160949707, |
| "learning_rate": 0.0001923122561107861, |
| "logits/chosen": -0.6866507530212402, |
| "logits/rejected": -0.6862455606460571, |
| "logps/chosen": -15.46005630493164, |
| "logps/rejected": -23.957612991333008, |
| "loss": 1.1913825273513794, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6236597299575806, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": -0.0235525481402874, |
| "rewards/margins": 0.8489581346511841, |
| "rewards/rejected": -0.8725106716156006, |
| "step": 178, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.17068446616406924, |
| "grad_norm": 3.096329927444458, |
| "learning_rate": 0.0001921903930942433, |
| "logits/chosen": -0.714995265007019, |
| "logits/rejected": -0.7174742817878723, |
| "logps/chosen": -8.619962692260742, |
| "logps/rejected": -24.74419403076172, |
| "loss": 0.7347225546836853, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3649461567401886, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.3418368399143219, |
| "rewards/margins": 1.3640844821929932, |
| "rewards/rejected": -1.0222476720809937, |
| "step": 179, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.17163801066777915, |
| "grad_norm": 4.56447696685791, |
| "learning_rate": 0.0001920676110282285, |
| "logits/chosen": -0.6581594347953796, |
| "logits/rejected": -0.6673140525817871, |
| "logps/chosen": -9.23294734954834, |
| "logps/rejected": -30.7730712890625, |
| "loss": 0.850014328956604, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4674980640411377, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.34507861733436584, |
| "rewards/margins": 1.5998858213424683, |
| "rewards/rejected": -1.2548071146011353, |
| "step": 180, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.17259155517148903, |
| "grad_norm": 5.760802268981934, |
| "learning_rate": 0.00019194391113676066, |
| "logits/chosen": -0.6523366570472717, |
| "logits/rejected": -0.6550288796424866, |
| "logps/chosen": -6.740331649780273, |
| "logps/rejected": -30.781539916992188, |
| "loss": 0.6302055716514587, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.36273908615112305, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.28853604197502136, |
| "rewards/margins": 1.6939523220062256, |
| "rewards/rejected": -1.405416488647461, |
| "step": 181, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.1735450996751989, |
| "grad_norm": 12.585807800292969, |
| "learning_rate": 0.00019181929465300867, |
| "logits/chosen": -0.6555710434913635, |
| "logits/rejected": -0.6563291549682617, |
| "logps/chosen": -8.818254470825195, |
| "logps/rejected": -26.118162155151367, |
| "loss": 1.006192684173584, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5286135077476501, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.1584509164094925, |
| "rewards/margins": 1.0672976970672607, |
| "rewards/rejected": -0.9088467359542847, |
| "step": 182, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.17449864417890878, |
| "grad_norm": 14.85263442993164, |
| "learning_rate": 0.00019169376281927888, |
| "logits/chosen": -0.6442791223526001, |
| "logits/rejected": -0.6450104713439941, |
| "logps/chosen": -14.86386489868164, |
| "logps/rejected": -26.05071449279785, |
| "loss": 0.9775609970092773, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5570365786552429, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.21638250350952148, |
| "rewards/margins": 1.2050378322601318, |
| "rewards/rejected": -0.9886554479598999, |
| "step": 183, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.17545218868261866, |
| "grad_norm": 3.230543375015259, |
| "learning_rate": 0.00019156731688700282, |
| "logits/chosen": -0.6210854649543762, |
| "logits/rejected": -0.6267048716545105, |
| "logps/chosen": -13.91865348815918, |
| "logps/rejected": -38.97736740112305, |
| "loss": 0.7915259599685669, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5186562538146973, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.2942727506160736, |
| "rewards/margins": 1.8289098739624023, |
| "rewards/rejected": -1.5346370935440063, |
| "step": 184, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.17640573318632854, |
| "grad_norm": 2.8868508338928223, |
| "learning_rate": 0.00019143995811672477, |
| "logits/chosen": -0.6486306190490723, |
| "logits/rejected": -0.652104914188385, |
| "logps/chosen": -5.568210124969482, |
| "logps/rejected": -27.751487731933594, |
| "loss": 0.6170085072517395, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3322750926017761, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4464855492115021, |
| "rewards/margins": 1.7891556024551392, |
| "rewards/rejected": -1.342670202255249, |
| "step": 185, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.17735927769003845, |
| "grad_norm": 3.9456188678741455, |
| "learning_rate": 0.00019131168777808898, |
| "logits/chosen": -0.6291971206665039, |
| "logits/rejected": -0.6297172904014587, |
| "logps/chosen": -12.321616172790527, |
| "logps/rejected": -24.30876922607422, |
| "loss": 0.8616849780082703, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5116665363311768, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.24905012547969818, |
| "rewards/margins": 1.5109024047851562, |
| "rewards/rejected": -1.2618522644042969, |
| "step": 186, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.17831282219374833, |
| "grad_norm": 2.702249526977539, |
| "learning_rate": 0.00019118250714982731, |
| "logits/chosen": -0.5929388403892517, |
| "logits/rejected": -0.5927412509918213, |
| "logps/chosen": -18.426685333251953, |
| "logps/rejected": -29.490093231201172, |
| "loss": 0.9447975158691406, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6027999520301819, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.44031450152397156, |
| "rewards/margins": 1.3791184425354004, |
| "rewards/rejected": -0.9388039112091064, |
| "step": 187, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.1792663666974582, |
| "grad_norm": 8.779913902282715, |
| "learning_rate": 0.00019105241751974622, |
| "logits/chosen": -0.6030086874961853, |
| "logits/rejected": -0.6059356331825256, |
| "logps/chosen": -14.68698501586914, |
| "logps/rejected": -27.80228042602539, |
| "loss": 1.691088318824768, |
| "memory(GiB)": 46.35, |
| "nll_loss": 1.0041778087615967, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.17856761813163757, |
| "rewards/margins": 0.7927877902984619, |
| "rewards/rejected": -0.9713554382324219, |
| "step": 188, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.1802199112011681, |
| "grad_norm": 10.069469451904297, |
| "learning_rate": 0.00019092142018471415, |
| "logits/chosen": -0.6078054904937744, |
| "logits/rejected": -0.6128656268119812, |
| "logps/chosen": -12.452406883239746, |
| "logps/rejected": -28.240211486816406, |
| "loss": 1.3273694515228271, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.7840241193771362, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.06432705372571945, |
| "rewards/margins": 1.2688968181610107, |
| "rewards/rejected": -1.2045698165893555, |
| "step": 189, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.18117345570487797, |
| "grad_norm": 6.079003810882568, |
| "learning_rate": 0.00019078951645064838, |
| "logits/chosen": -0.6641287803649902, |
| "logits/rejected": -0.6651386618614197, |
| "logps/chosen": -11.525806427001953, |
| "logps/rejected": -29.05199432373047, |
| "loss": 0.7967350482940674, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5132903456687927, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4669915437698364, |
| "rewards/margins": 1.8379321098327637, |
| "rewards/rejected": -1.3709404468536377, |
| "step": 190, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.18212700020858785, |
| "grad_norm": 5.648211479187012, |
| "learning_rate": 0.0001906567076325022, |
| "logits/chosen": -0.6226366758346558, |
| "logits/rejected": -0.6231462359428406, |
| "logps/chosen": -12.877320289611816, |
| "logps/rejected": -25.276016235351562, |
| "loss": 1.0205765962600708, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.566328227519989, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.09460840374231339, |
| "rewards/margins": 1.310714602470398, |
| "rewards/rejected": -1.2161061763763428, |
| "step": 191, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.18308054471229773, |
| "grad_norm": 4.385422229766846, |
| "learning_rate": 0.00019052299505425163, |
| "logits/chosen": -0.6341255307197571, |
| "logits/rejected": -0.6353927254676819, |
| "logps/chosen": -12.35586166381836, |
| "logps/rejected": -28.534515380859375, |
| "loss": 0.6882162094116211, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3644564747810364, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.15853504836559296, |
| "rewards/margins": 1.6378214359283447, |
| "rewards/rejected": -1.4792861938476562, |
| "step": 192, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.18403408921600764, |
| "grad_norm": 4.654733657836914, |
| "learning_rate": 0.0001903883800488824, |
| "logits/chosen": -0.6233382225036621, |
| "logits/rejected": -0.6291900873184204, |
| "logps/chosen": -13.017970085144043, |
| "logps/rejected": -22.020763397216797, |
| "loss": 1.1330442428588867, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6492688059806824, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.13320674002170563, |
| "rewards/margins": 1.1537429094314575, |
| "rewards/rejected": -1.0205360651016235, |
| "step": 193, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.18498763371971752, |
| "grad_norm": 3.4216256141662598, |
| "learning_rate": 0.00019025286395837646, |
| "logits/chosen": -0.5952166318893433, |
| "logits/rejected": -0.5963065028190613, |
| "logps/chosen": -9.860529899597168, |
| "logps/rejected": -29.890125274658203, |
| "loss": 0.8962761759757996, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3847019672393799, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.15466918051242828, |
| "rewards/margins": 1.2276791334152222, |
| "rewards/rejected": -1.073009967803955, |
| "step": 194, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.1859411782234274, |
| "grad_norm": 4.316707134246826, |
| "learning_rate": 0.00019011644813369884, |
| "logits/chosen": -0.6289695501327515, |
| "logits/rejected": -0.6302688717842102, |
| "logps/chosen": -12.226104736328125, |
| "logps/rejected": -22.700223922729492, |
| "loss": 0.9454081058502197, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47017475962638855, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.13702160120010376, |
| "rewards/margins": 0.9464937448501587, |
| "rewards/rejected": -0.8094722032546997, |
| "step": 195, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.18689472272713728, |
| "grad_norm": 3.7120862007141113, |
| "learning_rate": 0.000189979133934784, |
| "logits/chosen": -0.6207241415977478, |
| "logits/rejected": -0.6233164668083191, |
| "logps/chosen": -11.039968490600586, |
| "logps/rejected": -27.233854293823242, |
| "loss": 0.7881925106048584, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49256622791290283, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.3206450343132019, |
| "rewards/margins": 1.7870210409164429, |
| "rewards/rejected": -1.466375708580017, |
| "step": 196, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.18784826723084716, |
| "grad_norm": 3.466970205307007, |
| "learning_rate": 0.00018984092273052226, |
| "logits/chosen": -0.5741087198257446, |
| "logits/rejected": -0.577633261680603, |
| "logps/chosen": -10.544950485229492, |
| "logps/rejected": -29.634170532226562, |
| "loss": 0.7709000706672668, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.44952672719955444, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2968864142894745, |
| "rewards/margins": 1.5171458721160889, |
| "rewards/rejected": -1.220259428024292, |
| "step": 197, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.18880181173455704, |
| "grad_norm": 5.925663948059082, |
| "learning_rate": 0.00018970181589874637, |
| "logits/chosen": -0.6281675696372986, |
| "logits/rejected": -0.6267039179801941, |
| "logps/chosen": -12.503989219665527, |
| "logps/rejected": -26.55430793762207, |
| "loss": 0.8320461511611938, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47903525829315186, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2876884341239929, |
| "rewards/margins": 1.6249191761016846, |
| "rewards/rejected": -1.3372308015823364, |
| "step": 198, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.18975535623826692, |
| "grad_norm": 4.836788177490234, |
| "learning_rate": 0.00018956181482621744, |
| "logits/chosen": -0.574232816696167, |
| "logits/rejected": -0.5773795247077942, |
| "logps/chosen": -12.001895904541016, |
| "logps/rejected": -33.00093078613281, |
| "loss": 0.8863531947135925, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47763878107070923, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.1612134873867035, |
| "rewards/margins": 1.1156642436981201, |
| "rewards/rejected": -0.9544508457183838, |
| "step": 199, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.19070890074197683, |
| "grad_norm": 3.3081352710723877, |
| "learning_rate": 0.0001894209209086114, |
| "logits/chosen": -0.5428276658058167, |
| "logits/rejected": -0.5466271638870239, |
| "logps/chosen": -10.126989364624023, |
| "logps/rejected": -20.518905639648438, |
| "loss": 0.9665564894676208, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.500993013381958, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.16999551653862, |
| "rewards/margins": 0.959606945514679, |
| "rewards/rejected": -0.7896114587783813, |
| "step": 200, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.1916624452456867, |
| "grad_norm": 2.897505521774292, |
| "learning_rate": 0.00018927913555050503, |
| "logits/chosen": -0.5779305100440979, |
| "logits/rejected": -0.5747931003570557, |
| "logps/chosen": -17.58974266052246, |
| "logps/rejected": -26.268123626708984, |
| "loss": 0.850783109664917, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5274812579154968, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.19601039588451385, |
| "rewards/margins": 1.5968701839447021, |
| "rewards/rejected": -1.4008598327636719, |
| "step": 201, |
| "train_speed(iter/s)": 0.005504 |
| }, |
| { |
| "epoch": 0.1926159897493966, |
| "grad_norm": 3.8850836753845215, |
| "learning_rate": 0.00018913646016536183, |
| "logits/chosen": -0.561751127243042, |
| "logits/rejected": -0.5625342130661011, |
| "logps/chosen": -12.929374694824219, |
| "logps/rejected": -23.321739196777344, |
| "loss": 1.1121145486831665, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.623794674873352, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.10641875863075256, |
| "rewards/margins": 0.8297063112258911, |
| "rewards/rejected": -0.7232875823974609, |
| "step": 202, |
| "train_speed(iter/s)": 0.005504 |
| }, |
| { |
| "epoch": 0.19356953425310647, |
| "grad_norm": 2.982349395751953, |
| "learning_rate": 0.00018899289617551804, |
| "logits/chosen": -0.5594407916069031, |
| "logits/rejected": -0.5587038397789001, |
| "logps/chosen": -10.63068675994873, |
| "logps/rejected": -24.737886428833008, |
| "loss": 0.7669390439987183, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.36006784439086914, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.24530011415481567, |
| "rewards/margins": 1.256105899810791, |
| "rewards/rejected": -1.0108058452606201, |
| "step": 203, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.19452307875681635, |
| "grad_norm": 2.643491506576538, |
| "learning_rate": 0.00018884844501216845, |
| "logits/chosen": -0.5894973874092102, |
| "logits/rejected": -0.5914351940155029, |
| "logps/chosen": -9.97107982635498, |
| "logps/rejected": -31.940563201904297, |
| "loss": 0.8093665242195129, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4172818660736084, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.06614634394645691, |
| "rewards/margins": 1.376508355140686, |
| "rewards/rejected": -1.3103621006011963, |
| "step": 204, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.19547662326052623, |
| "grad_norm": 3.3693642616271973, |
| "learning_rate": 0.0001887031081153521, |
| "logits/chosen": -0.5615100860595703, |
| "logits/rejected": -0.5650114417076111, |
| "logps/chosen": -13.976004600524902, |
| "logps/rejected": -28.519262313842773, |
| "loss": 0.8744814991950989, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5032024383544922, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.49708789587020874, |
| "rewards/margins": 1.6095080375671387, |
| "rewards/rejected": -1.1124200820922852, |
| "step": 205, |
| "train_speed(iter/s)": 0.005504 |
| }, |
| { |
| "epoch": 0.1964301677642361, |
| "grad_norm": 2.4091129302978516, |
| "learning_rate": 0.0001885568869339379, |
| "logits/chosen": -0.5869651436805725, |
| "logits/rejected": -0.5854282379150391, |
| "logps/chosen": -7.35068941116333, |
| "logps/rejected": -19.50687026977539, |
| "loss": 0.7085932493209839, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.2943400740623474, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.3026721179485321, |
| "rewards/margins": 1.0890121459960938, |
| "rewards/rejected": -0.7863401770591736, |
| "step": 206, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.19738371226794602, |
| "grad_norm": 2.7922327518463135, |
| "learning_rate": 0.0001884097829256103, |
| "logits/chosen": -0.5632832646369934, |
| "logits/rejected": -0.5713223814964294, |
| "logps/chosen": -4.739266395568848, |
| "logps/rejected": -22.380210876464844, |
| "loss": 0.6652868986129761, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.21661195158958435, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.25414109230041504, |
| "rewards/margins": 0.9292444586753845, |
| "rewards/rejected": -0.6751034259796143, |
| "step": 207, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.1983372567716559, |
| "grad_norm": 2.159740686416626, |
| "learning_rate": 0.0001882617975568547, |
| "logits/chosen": -0.5546308159828186, |
| "logits/rejected": -0.5577950477600098, |
| "logps/chosen": -8.135893821716309, |
| "logps/rejected": -26.290237426757812, |
| "loss": 0.6441012620925903, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.29732757806777954, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.23926052451133728, |
| "rewards/margins": 1.2788770198822021, |
| "rewards/rejected": -1.0396164655685425, |
| "step": 208, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.19929080127536578, |
| "grad_norm": 2.662601947784424, |
| "learning_rate": 0.0001881129323029427, |
| "logits/chosen": -0.6166251301765442, |
| "logits/rejected": -0.6195808053016663, |
| "logps/chosen": -11.880038261413574, |
| "logps/rejected": -22.851146697998047, |
| "loss": 0.9232374429702759, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.497083842754364, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.09440437704324722, |
| "rewards/margins": 1.113836407661438, |
| "rewards/rejected": -1.0194319486618042, |
| "step": 209, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.20024434577907566, |
| "grad_norm": 4.21198844909668, |
| "learning_rate": 0.00018796318864791763, |
| "logits/chosen": -0.596250593662262, |
| "logits/rejected": -0.5932587385177612, |
| "logps/chosen": -13.722579002380371, |
| "logps/rejected": -21.17253303527832, |
| "loss": 1.0904855728149414, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6094613671302795, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.3684840798377991, |
| "rewards/margins": 1.24985671043396, |
| "rewards/rejected": -0.8813725709915161, |
| "step": 210, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.20119789028278554, |
| "grad_norm": 2.3908798694610596, |
| "learning_rate": 0.00018781256808457952, |
| "logits/chosen": -0.6418711543083191, |
| "logits/rejected": -0.6426020860671997, |
| "logps/chosen": -9.313520431518555, |
| "logps/rejected": -28.35675048828125, |
| "loss": 0.6457710266113281, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3344080448150635, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3117567300796509, |
| "rewards/margins": 1.7926514148712158, |
| "rewards/rejected": -1.480894684791565, |
| "step": 211, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.20215143478649542, |
| "grad_norm": 4.213446140289307, |
| "learning_rate": 0.00018766107211447045, |
| "logits/chosen": -0.6857687830924988, |
| "logits/rejected": -0.6889129281044006, |
| "logps/chosen": -10.991165161132812, |
| "logps/rejected": -23.983476638793945, |
| "loss": 0.8246095180511475, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4915233850479126, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.44742169976234436, |
| "rewards/margins": 1.489663004875183, |
| "rewards/rejected": -1.0422413349151611, |
| "step": 212, |
| "train_speed(iter/s)": 0.005506 |
| }, |
| { |
| "epoch": 0.20310497929020532, |
| "grad_norm": 4.581085205078125, |
| "learning_rate": 0.00018750870224785939, |
| "logits/chosen": -0.6475303769111633, |
| "logits/rejected": -0.6516612768173218, |
| "logps/chosen": -8.425968170166016, |
| "logps/rejected": -27.245319366455078, |
| "loss": 1.00775146484375, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4461940824985504, |
| "rewards/accuracies": 0.6875, |
| "rewards/chosen": 0.12290078401565552, |
| "rewards/margins": 0.6714733839035034, |
| "rewards/rejected": -0.5485725998878479, |
| "step": 213, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.2040585237939152, |
| "grad_norm": 3.48254656791687, |
| "learning_rate": 0.0001873554600037272, |
| "logits/chosen": -0.7248468399047852, |
| "logits/rejected": -0.7298704981803894, |
| "logps/chosen": -16.679975509643555, |
| "logps/rejected": -29.29020881652832, |
| "loss": 0.9019865989685059, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5029369592666626, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.13473248481750488, |
| "rewards/margins": 1.3710637092590332, |
| "rewards/rejected": -1.2363313436508179, |
| "step": 214, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.20501206829762508, |
| "grad_norm": 3.339827299118042, |
| "learning_rate": 0.00018720134690975156, |
| "logits/chosen": -0.7348078489303589, |
| "logits/rejected": -0.736198902130127, |
| "logps/chosen": -14.8811674118042, |
| "logps/rejected": -29.43851661682129, |
| "loss": 0.8389151096343994, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4872620701789856, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.15459799766540527, |
| "rewards/margins": 1.7159806489944458, |
| "rewards/rejected": -1.5613826513290405, |
| "step": 215, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.20596561280133496, |
| "grad_norm": 3.656510591506958, |
| "learning_rate": 0.00018704636450229164, |
| "logits/chosen": -0.7041287422180176, |
| "logits/rejected": -0.7084454894065857, |
| "logps/chosen": -10.886726379394531, |
| "logps/rejected": -29.213560104370117, |
| "loss": 0.8103856444358826, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4273455739021301, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2712215781211853, |
| "rewards/margins": 1.8050236701965332, |
| "rewards/rejected": -1.5338020324707031, |
| "step": 216, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.20691915730504484, |
| "grad_norm": 3.91626238822937, |
| "learning_rate": 0.00018689051432637288, |
| "logits/chosen": -0.7283743023872375, |
| "logits/rejected": -0.7281219959259033, |
| "logps/chosen": -16.561418533325195, |
| "logps/rejected": -30.87485122680664, |
| "loss": 1.0018713474273682, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5711511969566345, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.08021259307861328, |
| "rewards/margins": 1.341779112815857, |
| "rewards/rejected": -1.4219918251037598, |
| "step": 217, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.20787270180875472, |
| "grad_norm": 6.127014636993408, |
| "learning_rate": 0.00018673379793567146, |
| "logits/chosen": -0.7484632730484009, |
| "logits/rejected": -0.7483644485473633, |
| "logps/chosen": -19.947607040405273, |
| "logps/rejected": -23.960468292236328, |
| "loss": 1.3958569765090942, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.8203793168067932, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": -0.06441813707351685, |
| "rewards/margins": 1.2137415409088135, |
| "rewards/rejected": -1.278159737586975, |
| "step": 218, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2088262463124646, |
| "grad_norm": 2.407982110977173, |
| "learning_rate": 0.000186576216892499, |
| "logits/chosen": -0.713143527507782, |
| "logits/rejected": -0.7156349420547485, |
| "logps/chosen": -5.429649829864502, |
| "logps/rejected": -26.790985107421875, |
| "loss": 0.587304413318634, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.27817654609680176, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.2246459275484085, |
| "rewards/margins": 1.6527907848358154, |
| "rewards/rejected": -1.4281446933746338, |
| "step": 219, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2097797908161745, |
| "grad_norm": 3.1036179065704346, |
| "learning_rate": 0.00018641777276778675, |
| "logits/chosen": -0.7326256632804871, |
| "logits/rejected": -0.7366985082626343, |
| "logps/chosen": -7.209220886230469, |
| "logps/rejected": -23.032699584960938, |
| "loss": 0.6927957534790039, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.33381518721580505, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.23173078894615173, |
| "rewards/margins": 1.3084405660629272, |
| "rewards/rejected": -1.0767097473144531, |
| "step": 220, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2107333353198844, |
| "grad_norm": 4.346834659576416, |
| "learning_rate": 0.00018625846714107012, |
| "logits/chosen": -0.7308673858642578, |
| "logits/rejected": -0.7319015860557556, |
| "logps/chosen": -12.318450927734375, |
| "logps/rejected": -18.871131896972656, |
| "loss": 0.8981698155403137, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5642520189285278, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.37170618772506714, |
| "rewards/margins": 1.4312975406646729, |
| "rewards/rejected": -1.059591293334961, |
| "step": 221, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.21168687982359427, |
| "grad_norm": 3.1750354766845703, |
| "learning_rate": 0.00018609830160047283, |
| "logits/chosen": -0.732227623462677, |
| "logits/rejected": -0.7383145689964294, |
| "logps/chosen": -7.505064964294434, |
| "logps/rejected": -38.76034927368164, |
| "loss": 0.5535200238227844, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.31380799412727356, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.3952406048774719, |
| "rewards/margins": 2.437666177749634, |
| "rewards/rejected": -2.0424253940582275, |
| "step": 222, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.21264042432730415, |
| "grad_norm": 7.859541416168213, |
| "learning_rate": 0.0001859372777426912, |
| "logits/chosen": -0.7466616630554199, |
| "logits/rejected": -0.7482908964157104, |
| "logps/chosen": -9.282036781311035, |
| "logps/rejected": -30.16108512878418, |
| "loss": 0.8680660724639893, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4826428294181824, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.1986997276544571, |
| "rewards/margins": 1.6596953868865967, |
| "rewards/rejected": -1.4609956741333008, |
| "step": 223, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.21359396883101403, |
| "grad_norm": 2.6235239505767822, |
| "learning_rate": 0.00018577539717297805, |
| "logits/chosen": -0.7357512712478638, |
| "logits/rejected": -0.7410033345222473, |
| "logps/chosen": -10.861976623535156, |
| "logps/rejected": -30.35597801208496, |
| "loss": 0.6867908239364624, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3553740084171295, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.31846415996551514, |
| "rewards/margins": 1.6189709901809692, |
| "rewards/rejected": -1.300506830215454, |
| "step": 224, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2145475133347239, |
| "grad_norm": 3.2945122718811035, |
| "learning_rate": 0.00018561266150512678, |
| "logits/chosen": -0.7396930456161499, |
| "logits/rejected": -0.7390568852424622, |
| "logps/chosen": -12.923048973083496, |
| "logps/rejected": -21.989673614501953, |
| "loss": 0.838452935218811, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46684154868125916, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3469083309173584, |
| "rewards/margins": 1.2420110702514648, |
| "rewards/rejected": -0.8951027989387512, |
| "step": 225, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.2155010578384338, |
| "grad_norm": 3.055189847946167, |
| "learning_rate": 0.00018544907236145542, |
| "logits/chosen": -0.7155624628067017, |
| "logits/rejected": -0.7295074462890625, |
| "logps/chosen": -8.0274658203125, |
| "logps/rejected": -33.05402374267578, |
| "loss": 0.6335862874984741, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.344045490026474, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.3197329342365265, |
| "rewards/margins": 1.8844159841537476, |
| "rewards/rejected": -1.564683198928833, |
| "step": 226, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2164546023421437, |
| "grad_norm": 3.998671770095825, |
| "learning_rate": 0.0001852846313727902, |
| "logits/chosen": -0.6813937425613403, |
| "logits/rejected": -0.6915090084075928, |
| "logps/chosen": -6.720040798187256, |
| "logps/rejected": -43.87916946411133, |
| "loss": 0.6070285439491272, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.34713295102119446, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3825485110282898, |
| "rewards/margins": 2.301313638687134, |
| "rewards/rejected": -1.9187651872634888, |
| "step": 227, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.21740814684585358, |
| "grad_norm": 6.1825127601623535, |
| "learning_rate": 0.00018511934017844948, |
| "logits/chosen": -0.7040500044822693, |
| "logits/rejected": -0.7090526223182678, |
| "logps/chosen": -9.686261177062988, |
| "logps/rejected": -29.63890266418457, |
| "loss": 0.7050997614860535, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.35831475257873535, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.2377694845199585, |
| "rewards/margins": 1.341123104095459, |
| "rewards/rejected": -1.103353500366211, |
| "step": 228, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.21836169134956346, |
| "grad_norm": 4.670922756195068, |
| "learning_rate": 0.00018495320042622736, |
| "logits/chosen": -0.7201105356216431, |
| "logits/rejected": -0.7206759452819824, |
| "logps/chosen": -11.61659049987793, |
| "logps/rejected": -22.681640625, |
| "loss": 0.880729615688324, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.44429099559783936, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2176312655210495, |
| "rewards/margins": 1.068014144897461, |
| "rewards/rejected": -0.8503826856613159, |
| "step": 229, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.21931523585327334, |
| "grad_norm": 2.941002368927002, |
| "learning_rate": 0.00018478621377237723, |
| "logits/chosen": -0.6653846502304077, |
| "logits/rejected": -0.6721563339233398, |
| "logps/chosen": -14.994268417358398, |
| "logps/rejected": -29.876937866210938, |
| "loss": 0.8451282382011414, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.535717248916626, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3403316140174866, |
| "rewards/margins": 1.5797615051269531, |
| "rewards/rejected": -1.2394298315048218, |
| "step": 230, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.22026878035698322, |
| "grad_norm": 4.083463191986084, |
| "learning_rate": 0.0001846183818815953, |
| "logits/chosen": -0.6833573579788208, |
| "logits/rejected": -0.6866470575332642, |
| "logps/chosen": -10.162806510925293, |
| "logps/rejected": -34.938297271728516, |
| "loss": 0.7267250418663025, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4074958264827728, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.1340690404176712, |
| "rewards/margins": 2.0150246620178223, |
| "rewards/rejected": -1.880955457687378, |
| "step": 231, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.2212223248606931, |
| "grad_norm": 7.379131317138672, |
| "learning_rate": 0.00018444970642700394, |
| "logits/chosen": -0.7077473998069763, |
| "logits/rejected": -0.7064493894577026, |
| "logps/chosen": -13.589353561401367, |
| "logps/rejected": -24.41387367248535, |
| "loss": 0.822698712348938, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.49851056933403015, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.29606232047080994, |
| "rewards/margins": 1.5206847190856934, |
| "rewards/rejected": -1.224622368812561, |
| "step": 232, |
| "train_speed(iter/s)": 0.005511 |
| }, |
| { |
| "epoch": 0.22217586936440298, |
| "grad_norm": 4.595974445343018, |
| "learning_rate": 0.00018428018909013506, |
| "logits/chosen": -0.71678227186203, |
| "logits/rejected": -0.7216454744338989, |
| "logps/chosen": -9.980438232421875, |
| "logps/rejected": -31.119977951049805, |
| "loss": 0.7918986082077026, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4974285066127777, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3226126432418823, |
| "rewards/margins": 1.9629307985305786, |
| "rewards/rejected": -1.6403182744979858, |
| "step": 233, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22312941386811289, |
| "grad_norm": 3.167337417602539, |
| "learning_rate": 0.00018410983156091332, |
| "logits/chosen": -0.7408382892608643, |
| "logits/rejected": -0.7445415258407593, |
| "logps/chosen": -8.515607833862305, |
| "logps/rejected": -33.531742095947266, |
| "loss": 0.6914982795715332, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4140031933784485, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.14548537135124207, |
| "rewards/margins": 1.8300060033798218, |
| "rewards/rejected": -1.6845208406448364, |
| "step": 234, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22408295837182277, |
| "grad_norm": 4.283833980560303, |
| "learning_rate": 0.0001839386355376393, |
| "logits/chosen": -0.6502076387405396, |
| "logits/rejected": -0.6558265089988708, |
| "logps/chosen": -19.92167091369629, |
| "logps/rejected": -47.21318435668945, |
| "loss": 1.0018163919448853, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6611323952674866, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.24247033894062042, |
| "rewards/margins": 2.237638473510742, |
| "rewards/rejected": -1.9951682090759277, |
| "step": 235, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22503650287553265, |
| "grad_norm": 7.356630325317383, |
| "learning_rate": 0.00018376660272697258, |
| "logits/chosen": -0.6707280278205872, |
| "logits/rejected": -0.6801574230194092, |
| "logps/chosen": -11.042348861694336, |
| "logps/rejected": -36.64607620239258, |
| "loss": 0.8370423316955566, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5653667449951172, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3662443459033966, |
| "rewards/margins": 1.9162840843200684, |
| "rewards/rejected": -1.5500398874282837, |
| "step": 236, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22599004737924253, |
| "grad_norm": 3.826658248901367, |
| "learning_rate": 0.00018359373484391458, |
| "logits/chosen": -0.6781504154205322, |
| "logits/rejected": -0.6821658611297607, |
| "logps/chosen": -15.55282211303711, |
| "logps/rejected": -37.502342224121094, |
| "loss": 0.8460524082183838, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5774834156036377, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3428380489349365, |
| "rewards/margins": 2.1569623947143555, |
| "rewards/rejected": -1.814124345779419, |
| "step": 237, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2269435918829524, |
| "grad_norm": 5.468197345733643, |
| "learning_rate": 0.00018342003361179176, |
| "logits/chosen": -0.6881271004676819, |
| "logits/rejected": -0.6934744119644165, |
| "logps/chosen": -14.643028259277344, |
| "logps/rejected": -32.62885665893555, |
| "loss": 0.9197757244110107, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5242944955825806, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.2500344216823578, |
| "rewards/margins": 1.471402645111084, |
| "rewards/rejected": -1.2213680744171143, |
| "step": 238, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22789713638666229, |
| "grad_norm": 3.4654653072357178, |
| "learning_rate": 0.0001832455007622382, |
| "logits/chosen": -0.6743485331535339, |
| "logits/rejected": -0.6775904893875122, |
| "logps/chosen": -10.395502090454102, |
| "logps/rejected": -30.561494827270508, |
| "loss": 0.8043732047080994, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47161921858787537, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.23796124756336212, |
| "rewards/margins": 1.657893180847168, |
| "rewards/rejected": -1.4199317693710327, |
| "step": 239, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.2288506808903722, |
| "grad_norm": 4.4645795822143555, |
| "learning_rate": 0.00018307013803517833, |
| "logits/chosen": -0.6564476490020752, |
| "logits/rejected": -0.6579591631889343, |
| "logps/chosen": -12.889369010925293, |
| "logps/rejected": -32.557186126708984, |
| "loss": 0.8514084219932556, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4758950173854828, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.1352337747812271, |
| "rewards/margins": 1.8795024156570435, |
| "rewards/rejected": -1.7442686557769775, |
| "step": 240, |
| "train_speed(iter/s)": 0.00551 |
| }, |
| { |
| "epoch": 0.22980422539408207, |
| "grad_norm": 2.232264757156372, |
| "learning_rate": 0.00018289394717880978, |
| "logits/chosen": -0.6453461647033691, |
| "logits/rejected": -0.6491398215293884, |
| "logps/chosen": -8.795199394226074, |
| "logps/rejected": -38.933860778808594, |
| "loss": 0.6577202081680298, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3493972718715668, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.2543625235557556, |
| "rewards/margins": 2.0953903198242188, |
| "rewards/rejected": -1.8410277366638184, |
| "step": 241, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.23075776989779195, |
| "grad_norm": 5.591300964355469, |
| "learning_rate": 0.00018271692994958577, |
| "logits/chosen": -0.6542764902114868, |
| "logits/rejected": -0.6555202007293701, |
| "logps/chosen": -13.642044067382812, |
| "logps/rejected": -25.366504669189453, |
| "loss": 1.0224049091339111, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5888019800186157, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.1471404731273651, |
| "rewards/margins": 1.296483039855957, |
| "rewards/rejected": -1.1493425369262695, |
| "step": 242, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.23171131440150183, |
| "grad_norm": 5.829916954040527, |
| "learning_rate": 0.00018253908811219764, |
| "logits/chosen": -0.6718738079071045, |
| "logits/rejected": -0.6782557964324951, |
| "logps/chosen": -8.563289642333984, |
| "logps/rejected": -33.8372688293457, |
| "loss": 0.6616629958152771, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.376559317111969, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.29688870906829834, |
| "rewards/margins": 1.8743014335632324, |
| "rewards/rejected": -1.577412724494934, |
| "step": 243, |
| "train_speed(iter/s)": 0.005509 |
| }, |
| { |
| "epoch": 0.2326648589052117, |
| "grad_norm": 2.7467596530914307, |
| "learning_rate": 0.00018236042343955733, |
| "logits/chosen": -0.6551127433776855, |
| "logits/rejected": -0.6554043889045715, |
| "logps/chosen": -18.136734008789062, |
| "logps/rejected": -26.344886779785156, |
| "loss": 0.9255790710449219, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5931095480918884, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4077427387237549, |
| "rewards/margins": 1.4671001434326172, |
| "rewards/rejected": -1.0593574047088623, |
| "step": 244, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.2336184034089216, |
| "grad_norm": 2.295992612838745, |
| "learning_rate": 0.00018218093771277965, |
| "logits/chosen": -0.6690840125083923, |
| "logits/rejected": -0.673971951007843, |
| "logps/chosen": -10.6835355758667, |
| "logps/rejected": -28.246593475341797, |
| "loss": 0.671001136302948, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.37796077132225037, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.35371649265289307, |
| "rewards/margins": 1.5933194160461426, |
| "rewards/rejected": -1.2396029233932495, |
| "step": 245, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.23457194791263147, |
| "grad_norm": 2.4248974323272705, |
| "learning_rate": 0.0001820006327211645, |
| "logits/chosen": -0.697637140750885, |
| "logits/rejected": -0.7033761143684387, |
| "logps/chosen": -17.12112045288086, |
| "logps/rejected": -37.0136604309082, |
| "loss": 0.8772357106208801, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5765882134437561, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.09836695343255997, |
| "rewards/margins": 1.795198917388916, |
| "rewards/rejected": -1.6968318223953247, |
| "step": 246, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.23552549241634138, |
| "grad_norm": 2.954430103302002, |
| "learning_rate": 0.00018181951026217908, |
| "logits/chosen": -0.6803640127182007, |
| "logits/rejected": -0.6828312873840332, |
| "logps/chosen": -11.082855224609375, |
| "logps/rejected": -31.45410919189453, |
| "loss": 0.8763056993484497, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5489755272865295, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.1993655562400818, |
| "rewards/margins": 1.7591843605041504, |
| "rewards/rejected": -1.5598187446594238, |
| "step": 247, |
| "train_speed(iter/s)": 0.005508 |
| }, |
| { |
| "epoch": 0.23647903692005126, |
| "grad_norm": 3.6945090293884277, |
| "learning_rate": 0.00018163757214143992, |
| "logits/chosen": -0.7247760891914368, |
| "logits/rejected": -0.7265908122062683, |
| "logps/chosen": -8.492441177368164, |
| "logps/rejected": -24.54302978515625, |
| "loss": 0.7595934271812439, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.36660653352737427, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.23363766074180603, |
| "rewards/margins": 1.2679532766342163, |
| "rewards/rejected": -1.0343154668807983, |
| "step": 248, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.23743258142376114, |
| "grad_norm": 5.059366703033447, |
| "learning_rate": 0.00018145482017269498, |
| "logits/chosen": -0.7539775967597961, |
| "logits/rejected": -0.7569143176078796, |
| "logps/chosen": -14.154876708984375, |
| "logps/rejected": -34.48857879638672, |
| "loss": 1.0243213176727295, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6785087585449219, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.313811331987381, |
| "rewards/margins": 1.7598588466644287, |
| "rewards/rejected": -1.4460474252700806, |
| "step": 249, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.23838612592747102, |
| "grad_norm": 4.5284881591796875, |
| "learning_rate": 0.00018127125617780542, |
| "logits/chosen": -0.7603623867034912, |
| "logits/rejected": -0.7655926942825317, |
| "logps/chosen": -15.725591659545898, |
| "logps/rejected": -36.53950881958008, |
| "loss": 0.797869861125946, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4995449483394623, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.34647393226623535, |
| "rewards/margins": 1.9886072874069214, |
| "rewards/rejected": -1.642133355140686, |
| "step": 250, |
| "train_speed(iter/s)": 0.005507 |
| }, |
| { |
| "epoch": 0.2393396704311809, |
| "grad_norm": 3.5723788738250732, |
| "learning_rate": 0.00018108688198672766, |
| "logits/chosen": -0.7488352060317993, |
| "logits/rejected": -0.7484657764434814, |
| "logps/chosen": -13.811964988708496, |
| "logps/rejected": -29.093414306640625, |
| "loss": 0.824102520942688, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46683502197265625, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.24177491664886475, |
| "rewards/margins": 1.4699395895004272, |
| "rewards/rejected": -1.2281646728515625, |
| "step": 251, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.24029321493489078, |
| "grad_norm": 3.6928255558013916, |
| "learning_rate": 0.00018090169943749476, |
| "logits/chosen": -0.8220372796058655, |
| "logits/rejected": -0.8342781066894531, |
| "logps/chosen": -16.097322463989258, |
| "logps/rejected": -46.93342590332031, |
| "loss": 0.7694358229637146, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5316731929779053, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.20401325821876526, |
| "rewards/margins": 2.321596145629883, |
| "rewards/rejected": -2.1175830364227295, |
| "step": 252, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.24124675943860066, |
| "grad_norm": 4.793475151062012, |
| "learning_rate": 0.00018071571037619853, |
| "logits/chosen": -0.8255568742752075, |
| "logits/rejected": -0.832805871963501, |
| "logps/chosen": -14.022353172302246, |
| "logps/rejected": -39.7362174987793, |
| "loss": 0.9730318784713745, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5591216087341309, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": -0.038475535809993744, |
| "rewards/margins": 2.198916435241699, |
| "rewards/rejected": -2.2373921871185303, |
| "step": 253, |
| "train_speed(iter/s)": 0.005505 |
| }, |
| { |
| "epoch": 0.24220030394231057, |
| "grad_norm": 5.3987250328063965, |
| "learning_rate": 0.0001805289166569709, |
| "logits/chosen": -0.8706380724906921, |
| "logits/rejected": -0.8680281639099121, |
| "logps/chosen": -19.27591323852539, |
| "logps/rejected": -24.156095504760742, |
| "loss": 0.9442822337150574, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5581637024879456, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.22315068542957306, |
| "rewards/margins": 1.5777620077133179, |
| "rewards/rejected": -1.3546112775802612, |
| "step": 254, |
| "train_speed(iter/s)": 0.005504 |
| }, |
| { |
| "epoch": 0.24315384844602045, |
| "grad_norm": 3.675352096557617, |
| "learning_rate": 0.00018034132014196541, |
| "logits/chosen": -0.8502498865127563, |
| "logits/rejected": -0.8500807881355286, |
| "logps/chosen": -15.931413650512695, |
| "logps/rejected": -34.360782623291016, |
| "loss": 0.9934901595115662, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46458542346954346, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": -0.05971866846084595, |
| "rewards/margins": 1.5547869205474854, |
| "rewards/rejected": -1.6145055294036865, |
| "step": 255, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.24410739294973033, |
| "grad_norm": 2.504709482192993, |
| "learning_rate": 0.00018015292270133872, |
| "logits/chosen": -0.8568322658538818, |
| "logits/rejected": -0.862451434135437, |
| "logps/chosen": -11.659085273742676, |
| "logps/rejected": -39.16455078125, |
| "loss": 0.6887809634208679, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4371872842311859, |
| "rewards/accuracies": 0.96875, |
| "rewards/chosen": 0.3427257239818573, |
| "rewards/margins": 2.4889614582061768, |
| "rewards/rejected": -2.146235466003418, |
| "step": 256, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.2450609374534402, |
| "grad_norm": 2.5033137798309326, |
| "learning_rate": 0.0001799637262132319, |
| "logits/chosen": -0.8038372993469238, |
| "logits/rejected": -0.8058630228042603, |
| "logps/chosen": -15.10529613494873, |
| "logps/rejected": -30.41006851196289, |
| "loss": 0.8026267886161804, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5051940679550171, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4036296010017395, |
| "rewards/margins": 2.0970892906188965, |
| "rewards/rejected": -1.6934596300125122, |
| "step": 257, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.2460144819571501, |
| "grad_norm": 6.446276664733887, |
| "learning_rate": 0.00017977373256375194, |
| "logits/chosen": -0.7744889855384827, |
| "logits/rejected": -0.7749512791633606, |
| "logps/chosen": -10.56025218963623, |
| "logps/rejected": -23.576618194580078, |
| "loss": 0.9698085188865662, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5578731894493103, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.360497385263443, |
| "rewards/margins": 1.4745229482650757, |
| "rewards/rejected": -1.1140254735946655, |
| "step": 258, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.24696802646085997, |
| "grad_norm": 5.751850605010986, |
| "learning_rate": 0.0001795829436469525, |
| "logits/chosen": -0.7688460350036621, |
| "logits/rejected": -0.7771020531654358, |
| "logps/chosen": -7.432956218719482, |
| "logps/rejected": -33.72074508666992, |
| "loss": 0.7200008034706116, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.37630078196525574, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.447079062461853, |
| "rewards/margins": 1.622812032699585, |
| "rewards/rejected": -1.1757328510284424, |
| "step": 259, |
| "train_speed(iter/s)": 0.005504 |
| }, |
| { |
| "epoch": 0.24792157096456985, |
| "grad_norm": 2.761026382446289, |
| "learning_rate": 0.0001793913613648155, |
| "logits/chosen": -0.7341782450675964, |
| "logits/rejected": -0.7375565767288208, |
| "logps/chosen": -13.347549438476562, |
| "logps/rejected": -36.34661865234375, |
| "loss": 0.730623185634613, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4697628319263458, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.4078211188316345, |
| "rewards/margins": 1.8925766944885254, |
| "rewards/rejected": -1.4847557544708252, |
| "step": 260, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.24887511546827976, |
| "grad_norm": 3.450498104095459, |
| "learning_rate": 0.0001791989876272318, |
| "logits/chosen": -0.7157857418060303, |
| "logits/rejected": -0.7172526717185974, |
| "logps/chosen": -13.749683380126953, |
| "logps/rejected": -26.766677856445312, |
| "loss": 0.9530576467514038, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6287062764167786, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2914014756679535, |
| "rewards/margins": 1.3994582891464233, |
| "rewards/rejected": -1.108056902885437, |
| "step": 261, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.24982865997198964, |
| "grad_norm": 9.672338485717773, |
| "learning_rate": 0.0001790058243519824, |
| "logits/chosen": -0.7441627979278564, |
| "logits/rejected": -0.7462865710258484, |
| "logps/chosen": -16.243741989135742, |
| "logps/rejected": -26.704174041748047, |
| "loss": 1.039839744567871, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.6975647211074829, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4236500561237335, |
| "rewards/margins": 1.4664613008499146, |
| "rewards/rejected": -1.0428110361099243, |
| "step": 262, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2507822044756995, |
| "grad_norm": 4.290750026702881, |
| "learning_rate": 0.00017881187346471925, |
| "logits/chosen": -0.6632997989654541, |
| "logits/rejected": -0.666835367679596, |
| "logps/chosen": -9.480688095092773, |
| "logps/rejected": -26.351364135742188, |
| "loss": 0.8655059337615967, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46523410081863403, |
| "rewards/accuracies": 0.75, |
| "rewards/chosen": 0.19613634049892426, |
| "rewards/margins": 1.3419668674468994, |
| "rewards/rejected": -1.145830512046814, |
| "step": 263, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2517357489794094, |
| "grad_norm": 2.3689281940460205, |
| "learning_rate": 0.00017861713689894593, |
| "logits/chosen": -0.6977696418762207, |
| "logits/rejected": -0.6972867250442505, |
| "logps/chosen": -15.168523788452148, |
| "logps/rejected": -26.164867401123047, |
| "loss": 0.8803794980049133, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5127299427986145, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.33054158091545105, |
| "rewards/margins": 1.4892292022705078, |
| "rewards/rejected": -1.1586875915527344, |
| "step": 264, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2526892934831193, |
| "grad_norm": 2.7021660804748535, |
| "learning_rate": 0.00017842161659599858, |
| "logits/chosen": -0.6796221733093262, |
| "logits/rejected": -0.6836917400360107, |
| "logps/chosen": -14.941936492919922, |
| "logps/rejected": -27.9511775970459, |
| "loss": 0.8421461582183838, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4779818058013916, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.43745580315589905, |
| "rewards/margins": 1.4425956010818481, |
| "rewards/rejected": -1.0051398277282715, |
| "step": 265, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2536428379868292, |
| "grad_norm": 3.343235492706299, |
| "learning_rate": 0.00017822531450502633, |
| "logits/chosen": -0.733414351940155, |
| "logits/rejected": -0.7376254796981812, |
| "logps/chosen": -13.379249572753906, |
| "logps/rejected": -28.608491897583008, |
| "loss": 0.8496363162994385, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.47925660014152527, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.33804893493652344, |
| "rewards/margins": 1.5891144275665283, |
| "rewards/rejected": -1.2510654926300049, |
| "step": 266, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.25459638249053906, |
| "grad_norm": 2.7692151069641113, |
| "learning_rate": 0.0001780282325829721, |
| "logits/chosen": -0.7533795237541199, |
| "logits/rejected": -0.7605142593383789, |
| "logps/chosen": -8.79134750366211, |
| "logps/rejected": -34.76374816894531, |
| "loss": 0.637890636920929, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3121227025985718, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3103838860988617, |
| "rewards/margins": 1.773932695388794, |
| "rewards/rejected": -1.4635487794876099, |
| "step": 267, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.25554992699424894, |
| "grad_norm": 3.4116291999816895, |
| "learning_rate": 0.00017783037279455298, |
| "logits/chosen": -0.7418196201324463, |
| "logits/rejected": -0.7402464747428894, |
| "logps/chosen": -11.315349578857422, |
| "logps/rejected": -21.74294090270996, |
| "loss": 0.8379570841789246, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4140942096710205, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.25896090269088745, |
| "rewards/margins": 1.0902950763702393, |
| "rewards/rejected": -0.831334114074707, |
| "step": 268, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.2565034714979588, |
| "grad_norm": 6.1076765060424805, |
| "learning_rate": 0.00017763173711224058, |
| "logits/chosen": -0.790728747844696, |
| "logits/rejected": -0.7954204082489014, |
| "logps/chosen": -9.064315795898438, |
| "logps/rejected": -32.547019958496094, |
| "loss": 0.6000303030014038, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.32860445976257324, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.5540530681610107, |
| "rewards/margins": 1.9924101829528809, |
| "rewards/rejected": -1.4383569955825806, |
| "step": 269, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.2574570160016687, |
| "grad_norm": 9.593379020690918, |
| "learning_rate": 0.00017743232751624136, |
| "logits/chosen": -0.8328629732131958, |
| "logits/rejected": -0.8391848206520081, |
| "logps/chosen": -12.624238967895508, |
| "logps/rejected": -34.67926788330078, |
| "loss": 0.8230252265930176, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4716958999633789, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.25691932439804077, |
| "rewards/margins": 2.0827646255493164, |
| "rewards/rejected": -1.8258453607559204, |
| "step": 270, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2584105605053786, |
| "grad_norm": 9.825614929199219, |
| "learning_rate": 0.0001772321459944771, |
| "logits/chosen": -0.8258954286575317, |
| "logits/rejected": -0.8328973650932312, |
| "logps/chosen": -9.406560897827148, |
| "logps/rejected": -34.54033660888672, |
| "loss": 0.8422060608863831, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4756934344768524, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.1846769154071808, |
| "rewards/margins": 1.7777724266052246, |
| "rewards/rejected": -1.5930955410003662, |
| "step": 271, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.25936410500908846, |
| "grad_norm": 3.833090305328369, |
| "learning_rate": 0.00017703119454256483, |
| "logits/chosen": -0.8049967885017395, |
| "logits/rejected": -0.809727668762207, |
| "logps/chosen": -15.965205192565918, |
| "logps/rejected": -32.25198745727539, |
| "loss": 0.9207373261451721, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5331530570983887, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.31756967306137085, |
| "rewards/margins": 1.7631841897964478, |
| "rewards/rejected": -1.4456146955490112, |
| "step": 272, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.26031764951279834, |
| "grad_norm": 3.5092363357543945, |
| "learning_rate": 0.00017682947516379707, |
| "logits/chosen": -0.7785454392433167, |
| "logits/rejected": -0.7849420309066772, |
| "logps/chosen": -9.509476661682129, |
| "logps/rejected": -41.2681884765625, |
| "loss": 0.7832239270210266, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5032631158828735, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3947156071662903, |
| "rewards/margins": 2.444946765899658, |
| "rewards/rejected": -2.0502312183380127, |
| "step": 273, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2612711940165082, |
| "grad_norm": 9.79853630065918, |
| "learning_rate": 0.0001766269898691219, |
| "logits/chosen": -0.7902746200561523, |
| "logits/rejected": -0.7958580255508423, |
| "logps/chosen": -14.500446319580078, |
| "logps/rejected": -40.677024841308594, |
| "loss": 0.818083643913269, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.544266939163208, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.20477710664272308, |
| "rewards/margins": 1.9639387130737305, |
| "rewards/rejected": -1.7591617107391357, |
| "step": 274, |
| "train_speed(iter/s)": 0.005501 |
| }, |
| { |
| "epoch": 0.2622247385202181, |
| "grad_norm": 2.8043007850646973, |
| "learning_rate": 0.00017642374067712276, |
| "logits/chosen": -0.8145909905433655, |
| "logits/rejected": -0.8201400637626648, |
| "logps/chosen": -6.1433939933776855, |
| "logps/rejected": -36.33699417114258, |
| "loss": 0.5093598365783691, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.250609815120697, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3683687448501587, |
| "rewards/margins": 2.32155704498291, |
| "rewards/rejected": -1.9531885385513306, |
| "step": 275, |
| "train_speed(iter/s)": 0.005501 |
| }, |
| { |
| "epoch": 0.263178283023928, |
| "grad_norm": 1.9743738174438477, |
| "learning_rate": 0.00017621972961399837, |
| "logits/chosen": -0.8289905190467834, |
| "logits/rejected": -0.8362520933151245, |
| "logps/chosen": -8.193869590759277, |
| "logps/rejected": -42.47102355957031, |
| "loss": 0.5758640170097351, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.35025331377983093, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.3571298122406006, |
| "rewards/margins": 2.474154472351074, |
| "rewards/rejected": -2.1170244216918945, |
| "step": 276, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2641318275276379, |
| "grad_norm": 3.2046637535095215, |
| "learning_rate": 0.00017601495871354272, |
| "logits/chosen": -0.8333855271339417, |
| "logits/rejected": -0.8423407077789307, |
| "logps/chosen": -12.388718605041504, |
| "logps/rejected": -37.287269592285156, |
| "loss": 0.8772380352020264, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5521318316459656, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.5665677785873413, |
| "rewards/margins": 2.0919201374053955, |
| "rewards/rejected": -1.5253523588180542, |
| "step": 277, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2650853720313478, |
| "grad_norm": 4.138637542724609, |
| "learning_rate": 0.00017580943001712455, |
| "logits/chosen": -0.8312089443206787, |
| "logits/rejected": -0.8350686430931091, |
| "logps/chosen": -10.27858829498291, |
| "logps/rejected": -23.721372604370117, |
| "loss": 0.8035193681716919, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.46928372979164124, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.2487541139125824, |
| "rewards/margins": 1.3405177593231201, |
| "rewards/rejected": -1.0917637348175049, |
| "step": 278, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2660389165350577, |
| "grad_norm": 10.411059379577637, |
| "learning_rate": 0.0001756031455736671, |
| "logits/chosen": -0.872393012046814, |
| "logits/rejected": -0.8761737942695618, |
| "logps/chosen": -10.651511192321777, |
| "logps/rejected": -34.54182815551758, |
| "loss": 0.7786023020744324, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.586529552936554, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.4380852282047272, |
| "rewards/margins": 2.2919764518737793, |
| "rewards/rejected": -1.853891134262085, |
| "step": 279, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.26699246103876756, |
| "grad_norm": 6.553945541381836, |
| "learning_rate": 0.0001753961074396277, |
| "logits/chosen": -0.8722527027130127, |
| "logits/rejected": -0.8801246285438538, |
| "logps/chosen": -14.362058639526367, |
| "logps/rejected": -38.951133728027344, |
| "loss": 0.7487638592720032, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48627233505249023, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.4535054564476013, |
| "rewards/margins": 2.5370492935180664, |
| "rewards/rejected": -2.0835437774658203, |
| "step": 280, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.26794600554247744, |
| "grad_norm": 3.1951112747192383, |
| "learning_rate": 0.0001751883176789772, |
| "logits/chosen": -0.8838074207305908, |
| "logits/rejected": -0.8843420147895813, |
| "logps/chosen": -14.274608612060547, |
| "logps/rejected": -31.143085479736328, |
| "loss": 0.7876904010772705, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.521136999130249, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.3397310972213745, |
| "rewards/margins": 2.2122066020965576, |
| "rewards/rejected": -1.8724756240844727, |
| "step": 281, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2688995500461873, |
| "grad_norm": 6.768604755401611, |
| "learning_rate": 0.00017497977836317957, |
| "logits/chosen": -0.8815992474555969, |
| "logits/rejected": -0.8873377442359924, |
| "logps/chosen": -10.060140609741211, |
| "logps/rejected": -37.913673400878906, |
| "loss": 0.7644662857055664, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4115667939186096, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.0558885782957077, |
| "rewards/margins": 2.0682661533355713, |
| "rewards/rejected": -2.0123775005340576, |
| "step": 282, |
| "train_speed(iter/s)": 0.005503 |
| }, |
| { |
| "epoch": 0.2698530945498972, |
| "grad_norm": 6.333160877227783, |
| "learning_rate": 0.00017477049157117093, |
| "logits/chosen": -0.8667274713516235, |
| "logits/rejected": -0.8733513951301575, |
| "logps/chosen": -7.258718013763428, |
| "logps/rejected": -35.21955490112305, |
| "loss": 0.5827018022537231, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3244476616382599, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.300222247838974, |
| "rewards/margins": 2.3158271312713623, |
| "rewards/rejected": -2.0156044960021973, |
| "step": 283, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2708066390536071, |
| "grad_norm": 8.849654197692871, |
| "learning_rate": 0.00017456045938933921, |
| "logits/chosen": -0.8408533334732056, |
| "logits/rejected": -0.8415780067443848, |
| "logps/chosen": -11.036890029907227, |
| "logps/rejected": -23.754640579223633, |
| "loss": 0.9040743708610535, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4470711350440979, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.1645175814628601, |
| "rewards/margins": 1.5826839208602905, |
| "rewards/rejected": -1.418166160583496, |
| "step": 284, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.27176018355731696, |
| "grad_norm": 9.435028076171875, |
| "learning_rate": 0.00017434968391150303, |
| "logits/chosen": -0.8585033416748047, |
| "logits/rejected": -0.8601518869400024, |
| "logps/chosen": -12.836453437805176, |
| "logps/rejected": -25.519573211669922, |
| "loss": 0.9164736270904541, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5822616219520569, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.12173706293106079, |
| "rewards/margins": 1.6899513006210327, |
| "rewards/rejected": -1.5682142972946167, |
| "step": 285, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.27271372806102684, |
| "grad_norm": 4.865884304046631, |
| "learning_rate": 0.000174138167238891, |
| "logits/chosen": -0.8257076144218445, |
| "logits/rejected": -0.8312942385673523, |
| "logps/chosen": -10.948116302490234, |
| "logps/rejected": -30.266220092773438, |
| "loss": 0.6918385624885559, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.40581583976745605, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4191591441631317, |
| "rewards/margins": 1.9850006103515625, |
| "rewards/rejected": -1.5658413171768188, |
| "step": 286, |
| "train_speed(iter/s)": 0.005502 |
| }, |
| { |
| "epoch": 0.2736672725647367, |
| "grad_norm": 6.899093151092529, |
| "learning_rate": 0.00017392591148012078, |
| "logits/chosen": -0.8300909996032715, |
| "logits/rejected": -0.8292056918144226, |
| "logps/chosen": -13.566852569580078, |
| "logps/rejected": -25.136863708496094, |
| "loss": 0.8579204678535461, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5340129733085632, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.28360167145729065, |
| "rewards/margins": 1.547747254371643, |
| "rewards/rejected": -1.2641456127166748, |
| "step": 287, |
| "train_speed(iter/s)": 0.005501 |
| }, |
| { |
| "epoch": 0.2746208170684466, |
| "grad_norm": 3.2125444412231445, |
| "learning_rate": 0.0001737129187511779, |
| "logits/chosen": -0.7984634637832642, |
| "logits/rejected": -0.7962420582771301, |
| "logps/chosen": -12.646373748779297, |
| "logps/rejected": -23.826274871826172, |
| "loss": 0.8648015260696411, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5307040810585022, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.354749858379364, |
| "rewards/margins": 1.804355502128601, |
| "rewards/rejected": -1.4496057033538818, |
| "step": 288, |
| "train_speed(iter/s)": 0.005501 |
| }, |
| { |
| "epoch": 0.2755743615721565, |
| "grad_norm": 4.156564712524414, |
| "learning_rate": 0.00017349919117539488, |
| "logits/chosen": -0.8059985041618347, |
| "logits/rejected": -0.8075786828994751, |
| "logps/chosen": -10.38840389251709, |
| "logps/rejected": -35.189395904541016, |
| "loss": 0.7971677780151367, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4960591793060303, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.19452165067195892, |
| "rewards/margins": 2.2108750343322754, |
| "rewards/rejected": -2.0163533687591553, |
| "step": 289, |
| "train_speed(iter/s)": 0.005501 |
| }, |
| { |
| "epoch": 0.27652790607586636, |
| "grad_norm": 3.699566125869751, |
| "learning_rate": 0.00017328473088342987, |
| "logits/chosen": -0.7830536365509033, |
| "logits/rejected": -0.7884054780006409, |
| "logps/chosen": -9.001375198364258, |
| "logps/rejected": -24.977922439575195, |
| "loss": 0.7682836651802063, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.45012813806533813, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.31072452664375305, |
| "rewards/margins": 1.495220422744751, |
| "rewards/rejected": -1.1844959259033203, |
| "step": 290, |
| "train_speed(iter/s)": 0.0055 |
| }, |
| { |
| "epoch": 0.2774814505795763, |
| "grad_norm": 3.4391629695892334, |
| "learning_rate": 0.00017306954001324552, |
| "logits/chosen": -0.793381929397583, |
| "logits/rejected": -0.7974541187286377, |
| "logps/chosen": -9.428447723388672, |
| "logps/rejected": -30.583572387695312, |
| "loss": 0.6941128373146057, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.36475610733032227, |
| "rewards/accuracies": 0.875, |
| "rewards/chosen": 0.2897493541240692, |
| "rewards/margins": 1.644429087638855, |
| "rewards/rejected": -1.354679822921753, |
| "step": 291, |
| "train_speed(iter/s)": 0.0055 |
| }, |
| { |
| "epoch": 0.2784349950832862, |
| "grad_norm": 2.091162919998169, |
| "learning_rate": 0.00017285362071008768, |
| "logits/chosen": -0.7802900075912476, |
| "logits/rejected": -0.7882706522941589, |
| "logps/chosen": -7.435225486755371, |
| "logps/rejected": -30.591846466064453, |
| "loss": 0.5618146657943726, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.30165815353393555, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.4134962558746338, |
| "rewards/margins": 1.8643654584884644, |
| "rewards/rejected": -1.4508693218231201, |
| "step": 292, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.27938853958699605, |
| "grad_norm": 3.063162088394165, |
| "learning_rate": 0.00017263697512646394, |
| "logits/chosen": -0.821967363357544, |
| "logits/rejected": -0.8264334201812744, |
| "logps/chosen": -8.026369094848633, |
| "logps/rejected": -25.152278900146484, |
| "loss": 0.8412648439407349, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.3368728756904602, |
| "rewards/accuracies": 0.71875, |
| "rewards/chosen": 0.38843220472335815, |
| "rewards/margins": 1.1777088642120361, |
| "rewards/rejected": -0.789276659488678, |
| "step": 293, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.28034208409070593, |
| "grad_norm": 2.3966128826141357, |
| "learning_rate": 0.00017241960542212223, |
| "logits/chosen": -0.8297107219696045, |
| "logits/rejected": -0.8338165283203125, |
| "logps/chosen": -8.615389823913574, |
| "logps/rejected": -32.974342346191406, |
| "loss": 0.5042250156402588, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.2696914076805115, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.4293951988220215, |
| "rewards/margins": 1.9121533632278442, |
| "rewards/rejected": -1.4827582836151123, |
| "step": 294, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.2812956285944158, |
| "grad_norm": 3.1407666206359863, |
| "learning_rate": 0.00017220151376402923, |
| "logits/chosen": -0.8734156489372253, |
| "logits/rejected": -0.8751937747001648, |
| "logps/chosen": -10.877248764038086, |
| "logps/rejected": -23.823291778564453, |
| "loss": 0.7644665837287903, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.48325201869010925, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.36976158618927, |
| "rewards/margins": 1.7261672019958496, |
| "rewards/rejected": -1.3564057350158691, |
| "step": 295, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.2822491730981257, |
| "grad_norm": 5.954962253570557, |
| "learning_rate": 0.00017198270232634882, |
| "logits/chosen": -0.8571165800094604, |
| "logits/rejected": -0.8631231784820557, |
| "logps/chosen": -12.14771842956543, |
| "logps/rejected": -25.558012008666992, |
| "loss": 0.9797024130821228, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5402089357376099, |
| "rewards/accuracies": 0.78125, |
| "rewards/chosen": 0.23559921979904175, |
| "rewards/margins": 1.5777668952941895, |
| "rewards/rejected": -1.3421677350997925, |
| "step": 296, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.2832027176018356, |
| "grad_norm": 3.2417871952056885, |
| "learning_rate": 0.00017176317329042039, |
| "logits/chosen": -0.8923822045326233, |
| "logits/rejected": -0.8942370414733887, |
| "logps/chosen": -12.435152053833008, |
| "logps/rejected": -43.53513717651367, |
| "loss": 0.6605998873710632, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4150802791118622, |
| "rewards/accuracies": 0.9375, |
| "rewards/chosen": 0.2827378511428833, |
| "rewards/margins": 2.347248077392578, |
| "rewards/rejected": -2.0645101070404053, |
| "step": 297, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.28415626210554545, |
| "grad_norm": 3.007387399673462, |
| "learning_rate": 0.00017154292884473713, |
| "logits/chosen": -0.9107887148857117, |
| "logits/rejected": -0.9185442328453064, |
| "logps/chosen": -10.763036727905273, |
| "logps/rejected": -29.044370651245117, |
| "loss": 0.7759221196174622, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4099638760089874, |
| "rewards/accuracies": 0.84375, |
| "rewards/chosen": 0.4205581545829773, |
| "rewards/margins": 1.5706223249435425, |
| "rewards/rejected": -1.15006422996521, |
| "step": 298, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.28510980660925533, |
| "grad_norm": 9.711405754089355, |
| "learning_rate": 0.00017132197118492414, |
| "logits/chosen": -0.9608332514762878, |
| "logits/rejected": -0.9669287800788879, |
| "logps/chosen": -13.537405967712402, |
| "logps/rejected": -35.40542984008789, |
| "loss": 0.8132117390632629, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.4869121313095093, |
| "rewards/accuracies": 0.8125, |
| "rewards/chosen": 0.27392715215682983, |
| "rewards/margins": 2.3943862915039062, |
| "rewards/rejected": -2.1204590797424316, |
| "step": 299, |
| "train_speed(iter/s)": 0.005499 |
| }, |
| { |
| "epoch": 0.2860633511129652, |
| "grad_norm": 3.53682804107666, |
| "learning_rate": 0.00017110030251371656, |
| "logits/chosen": -0.9520952701568604, |
| "logits/rejected": -0.9550566673278809, |
| "logps/chosen": -16.060148239135742, |
| "logps/rejected": -38.28667068481445, |
| "loss": 0.7298264503479004, |
| "memory(GiB)": 46.35, |
| "nll_loss": 0.5163760185241699, |
| "rewards/accuracies": 0.90625, |
| "rewards/chosen": 0.17441169917583466, |
| "rewards/margins": 2.245462417602539, |
| "rewards/rejected": -2.0710508823394775, |
| "step": 300, |
| "train_speed(iter/s)": 0.0055 |
| }, |
| { |
| "epoch": 0.2860633511129652, |
| "eval_logits/chosen": -0.9646651744842529, |
| "eval_logits/rejected": -0.9698951244354248, |
| "eval_logps/chosen": -10.691489219665527, |
| "eval_logps/rejected": -34.90596008300781, |
| "eval_loss": 0.7083612680435181, |
| "eval_nll_loss": 0.43937814235687256, |
| "eval_rewards/accuracies": 0.8846153616905212, |
| "eval_rewards/chosen": 0.3399006426334381, |
| "eval_rewards/margins": 2.248044490814209, |
| "eval_rewards/rejected": -1.9081437587738037, |
| "eval_runtime": 790.801, |
| "eval_samples_per_second": 0.427, |
| "eval_steps_per_second": 0.427, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1048, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 2.170744812918014e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
