| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9989528795811519, |
| "eval_steps": 200, |
| "global_step": 477, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0020942408376963353, |
| "grad_norm": 70.76434326171875, |
| "learning_rate": 0.0, |
| "logits/chosen": -0.5995081663131714, |
| "logits/rejected": -0.6144353747367859, |
| "logps/chosen": -267.5271911621094, |
| "logps/rejected": -204.23904418945312, |
| "loss": 19.467, |
| "nll_loss": 1.0874961614608765, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.675271511077881, |
| "rewards/margins": -0.6328814029693604, |
| "rewards/rejected": -2.0423905849456787, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.020942408376963352, |
| "grad_norm": 66.30955505371094, |
| "learning_rate": 9.375e-08, |
| "logits/chosen": -0.6324494481086731, |
| "logits/rejected": -0.6370331645011902, |
| "logps/chosen": -296.5570068359375, |
| "logps/rejected": -258.9596252441406, |
| "loss": 18.6053, |
| "nll_loss": 1.038037657737732, |
| "rewards/accuracies": 0.4826388955116272, |
| "rewards/chosen": -2.9655702114105225, |
| "rewards/margins": -0.37597405910491943, |
| "rewards/rejected": -2.5895962715148926, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.041884816753926704, |
| "grad_norm": 70.56298828125, |
| "learning_rate": 1.9791666666666664e-07, |
| "logits/chosen": -0.5974550247192383, |
| "logits/rejected": -0.6282276511192322, |
| "logps/chosen": -297.4111022949219, |
| "logps/rejected": -256.52508544921875, |
| "loss": 18.3633, |
| "nll_loss": 1.0587749481201172, |
| "rewards/accuracies": 0.45625001192092896, |
| "rewards/chosen": -2.9741110801696777, |
| "rewards/margins": -0.4088606834411621, |
| "rewards/rejected": -2.5652506351470947, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06282722513089005, |
| "grad_norm": 58.68699645996094, |
| "learning_rate": 3.020833333333333e-07, |
| "logits/chosen": -0.6186209321022034, |
| "logits/rejected": -0.6106249094009399, |
| "logps/chosen": -274.9568786621094, |
| "logps/rejected": -245.85302734375, |
| "loss": 18.1303, |
| "nll_loss": 1.0308423042297363, |
| "rewards/accuracies": 0.47187501192092896, |
| "rewards/chosen": -2.749568462371826, |
| "rewards/margins": -0.2910384237766266, |
| "rewards/rejected": -2.4585299491882324, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08376963350785341, |
| "grad_norm": 51.15740966796875, |
| "learning_rate": 4.0625e-07, |
| "logits/chosen": -0.6243024468421936, |
| "logits/rejected": -0.6493061780929565, |
| "logps/chosen": -273.6658630371094, |
| "logps/rejected": -256.23516845703125, |
| "loss": 18.0446, |
| "nll_loss": 0.984009861946106, |
| "rewards/accuracies": 0.4937500059604645, |
| "rewards/chosen": -2.7366585731506348, |
| "rewards/margins": -0.17430701851844788, |
| "rewards/rejected": -2.562351703643799, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.10471204188481675, |
| "grad_norm": 44.492061614990234, |
| "learning_rate": 4.999932966293553e-07, |
| "logits/chosen": -0.6370277404785156, |
| "logits/rejected": -0.677150547504425, |
| "logps/chosen": -267.9862976074219, |
| "logps/rejected": -263.2257385253906, |
| "loss": 17.4079, |
| "nll_loss": 0.9246982336044312, |
| "rewards/accuracies": 0.4375, |
| "rewards/chosen": -2.679863452911377, |
| "rewards/margins": -0.04760568588972092, |
| "rewards/rejected": -2.6322576999664307, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1256544502617801, |
| "grad_norm": 46.6144905090332, |
| "learning_rate": 4.991893270335525e-07, |
| "logits/chosen": -0.645717203617096, |
| "logits/rejected": -0.6591695547103882, |
| "logps/chosen": -267.19000244140625, |
| "logps/rejected": -248.19009399414062, |
| "loss": 17.5598, |
| "nll_loss": 0.9888619184494019, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.6719002723693848, |
| "rewards/margins": -0.18999925255775452, |
| "rewards/rejected": -2.481900930404663, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.14659685863874344, |
| "grad_norm": 47.23382568359375, |
| "learning_rate": 4.970496218214204e-07, |
| "logits/chosen": -0.6946207284927368, |
| "logits/rejected": -0.6999990344047546, |
| "logps/chosen": -272.85723876953125, |
| "logps/rejected": -265.056640625, |
| "loss": 17.1179, |
| "nll_loss": 1.0355949401855469, |
| "rewards/accuracies": 0.48124998807907104, |
| "rewards/chosen": -2.728572368621826, |
| "rewards/margins": -0.07800592482089996, |
| "rewards/rejected": -2.650566577911377, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.16753926701570682, |
| "grad_norm": 44.47047805786133, |
| "learning_rate": 4.935856505068998e-07, |
| "logits/chosen": -0.6580323576927185, |
| "logits/rejected": -0.6536714434623718, |
| "logps/chosen": -264.0460510253906, |
| "logps/rejected": -245.66616821289062, |
| "loss": 17.0495, |
| "nll_loss": 0.9749844670295715, |
| "rewards/accuracies": 0.4437499940395355, |
| "rewards/chosen": -2.64046049118042, |
| "rewards/margins": -0.18379904329776764, |
| "rewards/rejected": -2.4566617012023926, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.18848167539267016, |
| "grad_norm": 43.76174545288086, |
| "learning_rate": 4.8881598109976e-07, |
| "logits/chosen": -0.6580432057380676, |
| "logits/rejected": -0.6635259389877319, |
| "logps/chosen": -260.81396484375, |
| "logps/rejected": -237.932373046875, |
| "loss": 17.2031, |
| "nll_loss": 0.9465915560722351, |
| "rewards/accuracies": 0.48750001192092896, |
| "rewards/chosen": -2.608139753341675, |
| "rewards/margins": -0.22881582379341125, |
| "rewards/rejected": -2.379323959350586, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2094240837696335, |
| "grad_norm": 52.968414306640625, |
| "learning_rate": 4.827661805750437e-07, |
| "logits/chosen": -0.6285615563392639, |
| "logits/rejected": -0.6467532515525818, |
| "logps/chosen": -256.7583923339844, |
| "logps/rejected": -259.3887634277344, |
| "loss": 17.1236, |
| "nll_loss": 0.9392696619033813, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": -2.5675835609436035, |
| "rewards/margins": 0.026304006576538086, |
| "rewards/rejected": -2.5938878059387207, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.23036649214659685, |
| "grad_norm": 43.268592834472656, |
| "learning_rate": 4.75468677825789e-07, |
| "logits/chosen": -0.6423302888870239, |
| "logits/rejected": -0.6667316555976868, |
| "logps/chosen": -255.0517120361328, |
| "logps/rejected": -249.2233428955078, |
| "loss": 16.8436, |
| "nll_loss": 0.8955658078193665, |
| "rewards/accuracies": 0.484375, |
| "rewards/chosen": -2.5505168437957764, |
| "rewards/margins": -0.058283496648073196, |
| "rewards/rejected": -2.4922332763671875, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2513089005235602, |
| "grad_norm": 44.98443603515625, |
| "learning_rate": 4.669625898336438e-07, |
| "logits/chosen": -0.6440318822860718, |
| "logits/rejected": -0.6476173400878906, |
| "logps/chosen": -251.17318725585938, |
| "logps/rejected": -258.1605529785156, |
| "loss": 17.2149, |
| "nll_loss": 0.9454558491706848, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.5117321014404297, |
| "rewards/margins": 0.06987308710813522, |
| "rewards/rejected": -2.5816054344177246, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.27225130890052357, |
| "grad_norm": 45.67206573486328, |
| "learning_rate": 4.5729351198915705e-07, |
| "logits/chosen": -0.6568298935890198, |
| "logits/rejected": -0.6463169455528259, |
| "logps/chosen": -256.1776428222656, |
| "logps/rejected": -261.1674499511719, |
| "loss": 17.4786, |
| "nll_loss": 0.9527324438095093, |
| "rewards/accuracies": 0.53125, |
| "rewards/chosen": -2.5617761611938477, |
| "rewards/margins": 0.049898095428943634, |
| "rewards/rejected": -2.6116745471954346, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.2931937172774869, |
| "grad_norm": 46.12214279174805, |
| "learning_rate": 4.4651327368569684e-07, |
| "logits/chosen": -0.6722804307937622, |
| "logits/rejected": -0.6767354011535645, |
| "logps/chosen": -256.47052001953125, |
| "logps/rejected": -241.89675903320312, |
| "loss": 16.9861, |
| "nll_loss": 0.9813588857650757, |
| "rewards/accuracies": 0.512499988079071, |
| "rewards/chosen": -2.5647053718566895, |
| "rewards/margins": -0.14573803544044495, |
| "rewards/rejected": -2.4189672470092773, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.31413612565445026, |
| "grad_norm": 41.50273132324219, |
| "learning_rate": 4.346796604970912e-07, |
| "logits/chosen": -0.6918385624885559, |
| "logits/rejected": -0.6956163644790649, |
| "logps/chosen": -277.5316162109375, |
| "logps/rejected": -241.47592163085938, |
| "loss": 17.2163, |
| "nll_loss": 0.9886034727096558, |
| "rewards/accuracies": 0.40312498807907104, |
| "rewards/chosen": -2.7753162384033203, |
| "rewards/margins": -0.36055710911750793, |
| "rewards/rejected": -2.4147589206695557, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.33507853403141363, |
| "grad_norm": 43.583335876464844, |
| "learning_rate": 4.218561044282098e-07, |
| "logits/chosen": -0.6789825558662415, |
| "logits/rejected": -0.6846081614494324, |
| "logps/chosen": -260.73504638671875, |
| "logps/rejected": -242.71273803710938, |
| "loss": 17.1598, |
| "nll_loss": 0.9698236584663391, |
| "rewards/accuracies": 0.4906249940395355, |
| "rewards/chosen": -2.6073505878448486, |
| "rewards/margins": -0.1802230179309845, |
| "rewards/rejected": -2.4271275997161865, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.35602094240837695, |
| "grad_norm": 46.515716552734375, |
| "learning_rate": 4.081113438988443e-07, |
| "logits/chosen": -0.660742461681366, |
| "logits/rejected": -0.6625587940216064, |
| "logps/chosen": -270.3114013671875, |
| "logps/rejected": -229.07958984375, |
| "loss": 17.5632, |
| "nll_loss": 0.9593551754951477, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.7031142711639404, |
| "rewards/margins": -0.4123184084892273, |
| "rewards/rejected": -2.2907958030700684, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.3769633507853403, |
| "grad_norm": 44.22664260864258, |
| "learning_rate": 3.935190552834828e-07, |
| "logits/chosen": -0.6569573879241943, |
| "logits/rejected": -0.672781229019165, |
| "logps/chosen": -266.2065734863281, |
| "logps/rejected": -238.51296997070312, |
| "loss": 16.9221, |
| "nll_loss": 0.986883282661438, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.6620657444000244, |
| "rewards/margins": -0.27693620324134827, |
| "rewards/rejected": -2.385129451751709, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.39790575916230364, |
| "grad_norm": 43.466007232666016, |
| "learning_rate": 3.781574579820464e-07, |
| "logits/chosen": -0.6655328273773193, |
| "logits/rejected": -0.683971107006073, |
| "logps/chosen": -261.59442138671875, |
| "logps/rejected": -244.1781768798828, |
| "loss": 17.1813, |
| "nll_loss": 0.9573402404785156, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -2.6159441471099854, |
| "rewards/margins": -0.17416232824325562, |
| "rewards/rejected": -2.441781520843506, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.418848167539267, |
| "grad_norm": 46.04378128051758, |
| "learning_rate": 3.621088951385353e-07, |
| "logits/chosen": -0.6769067645072937, |
| "logits/rejected": -0.6942776441574097, |
| "logps/chosen": -235.3308563232422, |
| "logps/rejected": -231.94094848632812, |
| "loss": 17.0014, |
| "nll_loss": 0.9534599184989929, |
| "rewards/accuracies": 0.48750001192092896, |
| "rewards/chosen": -2.353308916091919, |
| "rewards/margins": -0.03389930725097656, |
| "rewards/rejected": -2.3194096088409424, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.418848167539267, |
| "eval_logits/chosen": -0.6766718626022339, |
| "eval_logits/rejected": -0.6742084622383118, |
| "eval_logps/chosen": -270.51043701171875, |
| "eval_logps/rejected": -255.9008331298828, |
| "eval_loss": 2.0830676555633545, |
| "eval_nll_loss": 0.9401236176490784, |
| "eval_rewards/accuracies": 0.5019999742507935, |
| "eval_rewards/chosen": -2.7051045894622803, |
| "eval_rewards/margins": -0.1460963785648346, |
| "eval_rewards/rejected": -2.5590081214904785, |
| "eval_runtime": 40.7467, |
| "eval_samples_per_second": 49.084, |
| "eval_steps_per_second": 3.068, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4397905759162304, |
| "grad_norm": 43.57101058959961, |
| "learning_rate": 3.454593922550693e-07, |
| "logits/chosen": -0.6506687998771667, |
| "logits/rejected": -0.6705228090286255, |
| "logps/chosen": -269.6361389160156, |
| "logps/rejected": -255.491943359375, |
| "loss": 17.0614, |
| "nll_loss": 0.9551501274108887, |
| "rewards/accuracies": 0.4593749940395355, |
| "rewards/chosen": -2.696361541748047, |
| "rewards/margins": -0.14144185185432434, |
| "rewards/rejected": -2.554919481277466, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.4607329842931937, |
| "grad_norm": 48.80193328857422, |
| "learning_rate": 3.2829819606729477e-07, |
| "logits/chosen": -0.6907462477684021, |
| "logits/rejected": -0.6869294047355652, |
| "logps/chosen": -264.3199157714844, |
| "logps/rejected": -263.21435546875, |
| "loss": 17.3722, |
| "nll_loss": 1.016068696975708, |
| "rewards/accuracies": 0.5093749761581421, |
| "rewards/chosen": -2.6431994438171387, |
| "rewards/margins": -0.01105602364987135, |
| "rewards/rejected": -2.632143020629883, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.4816753926701571, |
| "grad_norm": 49.72327423095703, |
| "learning_rate": 3.1071729615293424e-07, |
| "logits/chosen": -0.6712943315505981, |
| "logits/rejected": -0.6651626825332642, |
| "logps/chosen": -258.03948974609375, |
| "logps/rejected": -247.8812713623047, |
| "loss": 16.7045, |
| "nll_loss": 0.9863218069076538, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -2.5803945064544678, |
| "rewards/margins": -0.10158199071884155, |
| "rewards/rejected": -2.4788126945495605, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5026178010471204, |
| "grad_norm": 47.963985443115234, |
| "learning_rate": 2.9281093183781403e-07, |
| "logits/chosen": -0.6394098997116089, |
| "logits/rejected": -0.6638405323028564, |
| "logps/chosen": -253.6232452392578, |
| "logps/rejected": -248.09030151367188, |
| "loss": 17.0898, |
| "nll_loss": 0.9433158040046692, |
| "rewards/accuracies": 0.46562498807907104, |
| "rewards/chosen": -2.5362324714660645, |
| "rewards/margins": -0.05532960966229439, |
| "rewards/rejected": -2.480902910232544, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.5235602094240838, |
| "grad_norm": 47.86073303222656, |
| "learning_rate": 2.7467508704251135e-07, |
| "logits/chosen": -0.6551315784454346, |
| "logits/rejected": -0.6670433282852173, |
| "logps/chosen": -270.5923156738281, |
| "logps/rejected": -261.06988525390625, |
| "loss": 17.1281, |
| "nll_loss": 0.9717443585395813, |
| "rewards/accuracies": 0.48124998807907104, |
| "rewards/chosen": -2.705922842025757, |
| "rewards/margins": -0.09522420912981033, |
| "rewards/rejected": -2.610698938369751, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5445026178010471, |
| "grad_norm": 47.56459045410156, |
| "learning_rate": 2.5640697577740815e-07, |
| "logits/chosen": -0.6732845306396484, |
| "logits/rejected": -0.6699023842811584, |
| "logps/chosen": -270.72198486328125, |
| "logps/rejected": -260.89947509765625, |
| "loss": 17.1471, |
| "nll_loss": 0.9890007972717285, |
| "rewards/accuracies": 0.4781250059604645, |
| "rewards/chosen": -2.7072196006774902, |
| "rewards/margins": -0.09822509437799454, |
| "rewards/rejected": -2.608994245529175, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.5654450261780105, |
| "grad_norm": 48.21664810180664, |
| "learning_rate": 2.381045210440644e-07, |
| "logits/chosen": -0.6522115468978882, |
| "logits/rejected": -0.6585103273391724, |
| "logps/chosen": -263.1189880371094, |
| "logps/rejected": -262.07476806640625, |
| "loss": 16.5867, |
| "nll_loss": 0.9758440852165222, |
| "rewards/accuracies": 0.515625, |
| "rewards/chosen": -2.6311895847320557, |
| "rewards/margins": -0.010442105121910572, |
| "rewards/rejected": -2.6207478046417236, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.5863874345549738, |
| "grad_norm": 48.17446517944336, |
| "learning_rate": 2.1986582993616925e-07, |
| "logits/chosen": -0.6916307210922241, |
| "logits/rejected": -0.6949232816696167, |
| "logps/chosen": -283.92138671875, |
| "logps/rejected": -252.03695678710938, |
| "loss": 16.3066, |
| "nll_loss": 0.9775869250297546, |
| "rewards/accuracies": 0.4906249940395355, |
| "rewards/chosen": -2.8392136096954346, |
| "rewards/margins": -0.31884413957595825, |
| "rewards/rejected": -2.5203697681427, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.6073298429319371, |
| "grad_norm": 50.038490295410156, |
| "learning_rate": 2.0178866775369774e-07, |
| "logits/chosen": -0.6787586212158203, |
| "logits/rejected": -0.6551983952522278, |
| "logps/chosen": -288.01885986328125, |
| "logps/rejected": -289.47210693359375, |
| "loss": 17.0343, |
| "nll_loss": 0.9661861658096313, |
| "rewards/accuracies": 0.5062500238418579, |
| "rewards/chosen": -2.880188465118408, |
| "rewards/margins": 0.014532634988427162, |
| "rewards/rejected": -2.8947207927703857, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.6282722513089005, |
| "grad_norm": 51.18766784667969, |
| "learning_rate": 1.839699339491937e-07, |
| "logits/chosen": -0.6984601616859436, |
| "logits/rejected": -0.6806785464286804, |
| "logps/chosen": -260.677001953125, |
| "logps/rejected": -259.806640625, |
| "loss": 16.2516, |
| "nll_loss": 1.0030128955841064, |
| "rewards/accuracies": 0.5625, |
| "rewards/chosen": -2.6067698001861572, |
| "rewards/margins": -0.008703561499714851, |
| "rewards/rejected": -2.5980663299560547, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6492146596858639, |
| "grad_norm": 52.35702896118164, |
| "learning_rate": 1.6650514271527465e-07, |
| "logits/chosen": -0.6617860198020935, |
| "logits/rejected": -0.6756520867347717, |
| "logps/chosen": -277.81988525390625, |
| "logps/rejected": -275.82440185546875, |
| "loss": 16.6359, |
| "nll_loss": 0.9435958862304688, |
| "rewards/accuracies": 0.48124998807907104, |
| "rewards/chosen": -2.778198719024658, |
| "rewards/margins": -0.01995471678674221, |
| "rewards/rejected": -2.7582437992095947, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.6701570680628273, |
| "grad_norm": 54.676971435546875, |
| "learning_rate": 1.4948791099758052e-07, |
| "logits/chosen": -0.6700472235679626, |
| "logits/rejected": -0.6831429600715637, |
| "logps/chosen": -268.69464111328125, |
| "logps/rejected": -261.7899169921875, |
| "loss": 17.0965, |
| "nll_loss": 0.9783571362495422, |
| "rewards/accuracies": 0.534375011920929, |
| "rewards/chosen": -2.686946392059326, |
| "rewards/margins": -0.06904693692922592, |
| "rewards/rejected": -2.6178994178771973, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.6910994764397905, |
| "grad_norm": 53.3182487487793, |
| "learning_rate": 1.3300945667758012e-07, |
| "logits/chosen": -0.6883733868598938, |
| "logits/rejected": -0.6983016133308411, |
| "logps/chosen": -267.2320861816406, |
| "logps/rejected": -268.79241943359375, |
| "loss": 16.5789, |
| "nll_loss": 0.9990630149841309, |
| "rewards/accuracies": 0.543749988079071, |
| "rewards/chosen": -2.672320604324341, |
| "rewards/margins": 0.015603733249008656, |
| "rewards/rejected": -2.68792462348938, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.7120418848167539, |
| "grad_norm": 60.07493591308594, |
| "learning_rate": 1.1715810961514072e-07, |
| "logits/chosen": -0.6815968155860901, |
| "logits/rejected": -0.684557318687439, |
| "logps/chosen": -242.76406860351562, |
| "logps/rejected": -240.29312133789062, |
| "loss": 16.7382, |
| "nll_loss": 0.9848185777664185, |
| "rewards/accuracies": 0.4937500059604645, |
| "rewards/chosen": -2.427640676498413, |
| "rewards/margins": -0.024709587916731834, |
| "rewards/rejected": -2.402930736541748, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.7329842931937173, |
| "grad_norm": 65.03939056396484, |
| "learning_rate": 1.0201883817182949e-07, |
| "logits/chosen": -0.7134624719619751, |
| "logits/rejected": -0.7202504277229309, |
| "logps/chosen": -281.94329833984375, |
| "logps/rejected": -274.9791564941406, |
| "loss": 16.9451, |
| "nll_loss": 1.0326627492904663, |
| "rewards/accuracies": 0.46562498807907104, |
| "rewards/chosen": -2.8194327354431152, |
| "rewards/margins": -0.06964141130447388, |
| "rewards/rejected": -2.7497916221618652, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.7539267015706806, |
| "grad_norm": 61.326541900634766, |
| "learning_rate": 8.76727937529367e-08, |
| "logits/chosen": -0.6863014101982117, |
| "logits/rejected": -0.6968516111373901, |
| "logps/chosen": -264.82586669921875, |
| "logps/rejected": -264.02423095703125, |
| "loss": 16.3796, |
| "nll_loss": 0.9723429679870605, |
| "rewards/accuracies": 0.5218750238418579, |
| "rewards/chosen": -2.648258686065674, |
| "rewards/margins": -0.008016402833163738, |
| "rewards/rejected": -2.640242338180542, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.774869109947644, |
| "grad_norm": 63.97214889526367, |
| "learning_rate": 7.419687580962222e-08, |
| "logits/chosen": -0.7269243001937866, |
| "logits/rejected": -0.7250298261642456, |
| "logps/chosen": -285.830078125, |
| "logps/rejected": -268.97650146484375, |
| "loss": 16.7584, |
| "nll_loss": 1.045341968536377, |
| "rewards/accuracies": 0.5093749761581421, |
| "rewards/chosen": -2.858299970626831, |
| "rewards/margins": -0.16853561997413635, |
| "rewards/rejected": -2.6897647380828857, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.7958115183246073, |
| "grad_norm": 69.49169921875, |
| "learning_rate": 6.166331963291519e-08, |
| "logits/chosen": -0.6884605884552002, |
| "logits/rejected": -0.6921494603157043, |
| "logps/chosen": -285.6980895996094, |
| "logps/rejected": -267.3122863769531, |
| "loss": 17.1889, |
| "nll_loss": 0.9817717671394348, |
| "rewards/accuracies": 0.5375000238418579, |
| "rewards/chosen": -2.856981039047241, |
| "rewards/margins": -0.18385852873325348, |
| "rewards/rejected": -2.6731224060058594, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.8167539267015707, |
| "grad_norm": 51.80916213989258, |
| "learning_rate": 5.013930914912476e-08, |
| "logits/chosen": -0.7183871269226074, |
| "logits/rejected": -0.7136878967285156, |
| "logps/chosen": -279.07049560546875, |
| "logps/rejected": -281.7729797363281, |
| "loss": 15.9599, |
| "nll_loss": 0.9877471923828125, |
| "rewards/accuracies": 0.5062500238418579, |
| "rewards/chosen": -2.7907042503356934, |
| "rewards/margins": 0.027025192975997925, |
| "rewards/rejected": -2.8177294731140137, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.837696335078534, |
| "grad_norm": 51.51334762573242, |
| "learning_rate": 3.968661679220467e-08, |
| "logits/chosen": -0.6999576091766357, |
| "logits/rejected": -0.709846019744873, |
| "logps/chosen": -280.9571228027344, |
| "logps/rejected": -258.52105712890625, |
| "loss": 16.5359, |
| "nll_loss": 1.0165809392929077, |
| "rewards/accuracies": 0.46875, |
| "rewards/chosen": -2.8095710277557373, |
| "rewards/margins": -0.2243608683347702, |
| "rewards/rejected": -2.585210084915161, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.837696335078534, |
| "eval_logits/chosen": -0.7198893427848816, |
| "eval_logits/rejected": -0.717597246170044, |
| "eval_logps/chosen": -272.6577453613281, |
| "eval_logps/rejected": -266.8027038574219, |
| "eval_loss": 2.0329947471618652, |
| "eval_nll_loss": 0.9492927193641663, |
| "eval_rewards/accuracies": 0.515999972820282, |
| "eval_rewards/chosen": -2.7265775203704834, |
| "eval_rewards/margins": -0.05855049937963486, |
| "eval_rewards/rejected": -2.668027400970459, |
| "eval_runtime": 40.6786, |
| "eval_samples_per_second": 49.166, |
| "eval_steps_per_second": 3.073, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8586387434554974, |
| "grad_norm": 68.03474426269531, |
| "learning_rate": 3.036127238347164e-08, |
| "logits/chosen": -0.6865943670272827, |
| "logits/rejected": -0.6730343699455261, |
| "logps/chosen": -275.6883239746094, |
| "logps/rejected": -273.2828674316406, |
| "loss": 16.7848, |
| "nll_loss": 0.9662915468215942, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -2.756883144378662, |
| "rewards/margins": -0.024054694920778275, |
| "rewards/rejected": -2.7328288555145264, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.8795811518324608, |
| "grad_norm": 61.58699417114258, |
| "learning_rate": 2.2213262793589482e-08, |
| "logits/chosen": -0.6929936408996582, |
| "logits/rejected": -0.6882384419441223, |
| "logps/chosen": -292.38946533203125, |
| "logps/rejected": -280.07513427734375, |
| "loss": 16.3599, |
| "nll_loss": 0.9645106196403503, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -2.9238946437835693, |
| "rewards/margins": -0.12314357608556747, |
| "rewards/rejected": -2.800751209259033, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.900523560209424, |
| "grad_norm": 49.81018829345703, |
| "learning_rate": 1.5286263996730026e-08, |
| "logits/chosen": -0.689557671546936, |
| "logits/rejected": -0.7012760639190674, |
| "logps/chosen": -279.8668518066406, |
| "logps/rejected": -269.4853210449219, |
| "loss": 16.75, |
| "nll_loss": 0.9698156118392944, |
| "rewards/accuracies": 0.48124998807907104, |
| "rewards/chosen": -2.7986679077148438, |
| "rewards/margins": -0.10381509363651276, |
| "rewards/rejected": -2.6948530673980713, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.9214659685863874, |
| "grad_norm": 58.9363899230957, |
| "learning_rate": 9.617406953185136e-09, |
| "logits/chosen": -0.6873979568481445, |
| "logits/rejected": -0.7001478672027588, |
| "logps/chosen": -281.0133361816406, |
| "logps/rejected": -289.45672607421875, |
| "loss": 16.5338, |
| "nll_loss": 0.9704917073249817, |
| "rewards/accuracies": 0.543749988079071, |
| "rewards/chosen": -2.810133457183838, |
| "rewards/margins": 0.08443373441696167, |
| "rewards/rejected": -2.8945672512054443, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.9424083769633508, |
| "grad_norm": 54.53861999511719, |
| "learning_rate": 5.2370785753763356e-09, |
| "logits/chosen": -0.7115738987922668, |
| "logits/rejected": -0.7190148830413818, |
| "logps/chosen": -279.23431396484375, |
| "logps/rejected": -262.49847412109375, |
| "loss": 16.6766, |
| "nll_loss": 0.9821802377700806, |
| "rewards/accuracies": 0.515625, |
| "rewards/chosen": -2.7923433780670166, |
| "rewards/margins": -0.16735850274562836, |
| "rewards/rejected": -2.6249847412109375, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.9633507853403142, |
| "grad_norm": 63.032047271728516, |
| "learning_rate": 2.168758844148272e-09, |
| "logits/chosen": -0.7155815958976746, |
| "logits/rejected": -0.7291616797447205, |
| "logps/chosen": -297.2403869628906, |
| "logps/rejected": -281.8386535644531, |
| "loss": 16.78, |
| "nll_loss": 1.0376783609390259, |
| "rewards/accuracies": 0.49687498807907104, |
| "rewards/chosen": -2.9724037647247314, |
| "rewards/margins": -0.15401716530323029, |
| "rewards/rejected": -2.8183865547180176, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.9842931937172775, |
| "grad_norm": 56.330345153808594, |
| "learning_rate": 4.288949484559934e-10, |
| "logits/chosen": -0.6912795305252075, |
| "logits/rejected": -0.6842938661575317, |
| "logps/chosen": -260.95965576171875, |
| "logps/rejected": -258.5793762207031, |
| "loss": 17.0646, |
| "nll_loss": 0.9770845174789429, |
| "rewards/accuracies": 0.528124988079071, |
| "rewards/chosen": -2.6095967292785645, |
| "rewards/margins": -0.02380307950079441, |
| "rewards/rejected": -2.5857937335968018, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.9989528795811519, |
| "step": 477, |
| "total_flos": 0.0, |
| "train_loss": 17.025300079921507, |
| "train_runtime": 4689.5603, |
| "train_samples_per_second": 13.036, |
| "train_steps_per_second": 0.102 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 477, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
