| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9996020692399522, | |
| "eval_steps": 100, | |
| "global_step": 1256, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007958615200955034, | |
| "grad_norm": 4.841538053414044, | |
| "learning_rate": 3.968253968253968e-08, | |
| "logits/chosen": -2.470052719116211, | |
| "logits/rejected": -2.4655823707580566, | |
| "logps/chosen": -157.4224090576172, | |
| "logps/rejected": -164.1490936279297, | |
| "loss": 0.6932, | |
| "rewards/accuracies": 0.375, | |
| "rewards/chosen": -0.0001321556919720024, | |
| "rewards/margins": -0.0003976511361543089, | |
| "rewards/rejected": 0.00026549544418230653, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01591723040191007, | |
| "grad_norm": 5.024112543339822, | |
| "learning_rate": 7.936507936507936e-08, | |
| "logits/chosen": -2.4524307250976562, | |
| "logits/rejected": -2.4474711418151855, | |
| "logps/chosen": -142.13648986816406, | |
| "logps/rejected": -142.22164916992188, | |
| "loss": 0.6932, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -0.0001045634489855729, | |
| "rewards/margins": -0.0003915712586604059, | |
| "rewards/rejected": 0.0002870078315027058, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0238758456028651, | |
| "grad_norm": 4.743494095766565, | |
| "learning_rate": 1.1904761904761903e-07, | |
| "logits/chosen": -2.4943318367004395, | |
| "logits/rejected": -2.48530912399292, | |
| "logps/chosen": -154.43202209472656, | |
| "logps/rejected": -149.37612915039062, | |
| "loss": 0.6929, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": 0.0018067583441734314, | |
| "rewards/margins": 0.0005435317871160805, | |
| "rewards/rejected": 0.0012632266152650118, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03183446080382014, | |
| "grad_norm": 4.832210059469465, | |
| "learning_rate": 1.5873015873015872e-07, | |
| "logits/chosen": -2.5287983417510986, | |
| "logits/rejected": -2.510993242263794, | |
| "logps/chosen": -135.90139770507812, | |
| "logps/rejected": -132.0488739013672, | |
| "loss": 0.6927, | |
| "rewards/accuracies": 0.53125, | |
| "rewards/chosen": 0.004627659916877747, | |
| "rewards/margins": 0.000702070421539247, | |
| "rewards/rejected": 0.003925589844584465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03979307600477517, | |
| "grad_norm": 4.526944976438542, | |
| "learning_rate": 1.984126984126984e-07, | |
| "logits/chosen": -2.525243043899536, | |
| "logits/rejected": -2.4904685020446777, | |
| "logps/chosen": -157.05628967285156, | |
| "logps/rejected": -141.57211303710938, | |
| "loss": 0.6918, | |
| "rewards/accuracies": 0.606249988079071, | |
| "rewards/chosen": 0.013502730056643486, | |
| "rewards/margins": 0.005045468918979168, | |
| "rewards/rejected": 0.008457262068986893, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0477516912057302, | |
| "grad_norm": 4.47136990235777, | |
| "learning_rate": 2.3809523809523806e-07, | |
| "logits/chosen": -2.4738245010375977, | |
| "logits/rejected": -2.4801831245422363, | |
| "logps/chosen": -150.5889892578125, | |
| "logps/rejected": -159.7234344482422, | |
| "loss": 0.6903, | |
| "rewards/accuracies": 0.5562499761581421, | |
| "rewards/chosen": 0.01993567869067192, | |
| "rewards/margins": 0.004683250095695257, | |
| "rewards/rejected": 0.0152524309232831, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.055710306406685235, | |
| "grad_norm": 4.904005180990896, | |
| "learning_rate": 2.7777777777777776e-07, | |
| "logits/chosen": -2.5422394275665283, | |
| "logits/rejected": -2.529735565185547, | |
| "logps/chosen": -165.7467803955078, | |
| "logps/rejected": -162.11795043945312, | |
| "loss": 0.688, | |
| "rewards/accuracies": 0.5687500238418579, | |
| "rewards/chosen": 0.013221414759755135, | |
| "rewards/margins": 0.010048055090010166, | |
| "rewards/rejected": 0.003173359902575612, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06366892160764027, | |
| "grad_norm": 5.205118982895456, | |
| "learning_rate": 3.1746031746031743e-07, | |
| "logits/chosen": -2.5232584476470947, | |
| "logits/rejected": -2.5178704261779785, | |
| "logps/chosen": -147.32882690429688, | |
| "logps/rejected": -160.47280883789062, | |
| "loss": 0.6843, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -0.013839629478752613, | |
| "rewards/margins": 0.023469623178243637, | |
| "rewards/rejected": -0.037309251725673676, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07162753680859531, | |
| "grad_norm": 6.494638432518059, | |
| "learning_rate": 3.5714285714285716e-07, | |
| "logits/chosen": -2.510326385498047, | |
| "logits/rejected": -2.4887425899505615, | |
| "logps/chosen": -148.05128479003906, | |
| "logps/rejected": -149.84288024902344, | |
| "loss": 0.6798, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.1187344640493393, | |
| "rewards/margins": 0.04123911261558533, | |
| "rewards/rejected": -0.15997359156608582, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07958615200955034, | |
| "grad_norm": 5.5529916484322746, | |
| "learning_rate": 3.968253968253968e-07, | |
| "logits/chosen": -2.4746994972229004, | |
| "logits/rejected": -2.4473915100097656, | |
| "logps/chosen": -173.7371368408203, | |
| "logps/rejected": -159.02810668945312, | |
| "loss": 0.6755, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -0.13897764682769775, | |
| "rewards/margins": 0.035591237246990204, | |
| "rewards/rejected": -0.17456887662410736, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07958615200955034, | |
| "eval_logits/chosen": -2.4733359813690186, | |
| "eval_logits/rejected": -2.457453489303589, | |
| "eval_logps/chosen": -158.66261291503906, | |
| "eval_logps/rejected": -169.2390899658203, | |
| "eval_loss": 0.6757674217224121, | |
| "eval_rewards/accuracies": 0.58302241563797, | |
| "eval_rewards/chosen": -0.11758849024772644, | |
| "eval_rewards/margins": 0.044215064495801926, | |
| "eval_rewards/rejected": -0.16180357336997986, | |
| "eval_runtime": 347.737, | |
| "eval_samples_per_second": 24.593, | |
| "eval_steps_per_second": 0.385, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08754476721050537, | |
| "grad_norm": 6.715544747804576, | |
| "learning_rate": 4.365079365079365e-07, | |
| "logits/chosen": -2.4566893577575684, | |
| "logits/rejected": -2.416964530944824, | |
| "logps/chosen": -170.65357971191406, | |
| "logps/rejected": -163.5463104248047, | |
| "loss": 0.6704, | |
| "rewards/accuracies": 0.59375, | |
| "rewards/chosen": -0.16277848184108734, | |
| "rewards/margins": 0.05988674238324165, | |
| "rewards/rejected": -0.2226652204990387, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0955033824114604, | |
| "grad_norm": 9.596141007780728, | |
| "learning_rate": 4.761904761904761e-07, | |
| "logits/chosen": -2.4483439922332764, | |
| "logits/rejected": -2.454890012741089, | |
| "logps/chosen": -172.45748901367188, | |
| "logps/rejected": -192.52012634277344, | |
| "loss": 0.6658, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -0.3439694941043854, | |
| "rewards/margins": 0.06312272697687149, | |
| "rewards/rejected": -0.40709224343299866, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.10346199761241544, | |
| "grad_norm": 13.202078476460924, | |
| "learning_rate": 4.999845414634076e-07, | |
| "logits/chosen": -2.4176621437072754, | |
| "logits/rejected": -2.3901853561401367, | |
| "logps/chosen": -193.67239379882812, | |
| "logps/rejected": -195.47042846679688, | |
| "loss": 0.6499, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -0.41546326875686646, | |
| "rewards/margins": 0.09810779988765717, | |
| "rewards/rejected": -0.51357102394104, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11142061281337047, | |
| "grad_norm": 22.684431556876046, | |
| "learning_rate": 4.998106548810311e-07, | |
| "logits/chosen": -1.8343102931976318, | |
| "logits/rejected": -1.7827365398406982, | |
| "logps/chosen": -209.33108520507812, | |
| "logps/rejected": -233.1872100830078, | |
| "loss": 0.6356, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -0.6506957411766052, | |
| "rewards/margins": 0.23305030167102814, | |
| "rewards/rejected": -0.8837459683418274, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1193792280143255, | |
| "grad_norm": 21.199901451025738, | |
| "learning_rate": 4.994436933879359e-07, | |
| "logits/chosen": -1.7879050970077515, | |
| "logits/rejected": -1.6920697689056396, | |
| "logps/chosen": -249.83236694335938, | |
| "logps/rejected": -267.5176696777344, | |
| "loss": 0.6217, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -0.9289053678512573, | |
| "rewards/margins": 0.2332083284854889, | |
| "rewards/rejected": -1.162113904953003, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.12733784321528055, | |
| "grad_norm": 14.830944311799147, | |
| "learning_rate": 4.988839406031596e-07, | |
| "logits/chosen": -1.9281498193740845, | |
| "logits/rejected": -1.8930234909057617, | |
| "logps/chosen": -225.1186981201172, | |
| "logps/rejected": -262.7356262207031, | |
| "loss": 0.6212, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -0.8514399528503418, | |
| "rewards/margins": 0.2691754698753357, | |
| "rewards/rejected": -1.1206153631210327, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.13529645841623558, | |
| "grad_norm": 20.510239439728636, | |
| "learning_rate": 4.981318291512395e-07, | |
| "logits/chosen": -1.838880181312561, | |
| "logits/rejected": -1.7559387683868408, | |
| "logps/chosen": -188.37014770507812, | |
| "logps/rejected": -228.2301025390625, | |
| "loss": 0.6211, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -0.48021888732910156, | |
| "rewards/margins": 0.42019492387771606, | |
| "rewards/rejected": -0.9004138112068176, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.14325507361719061, | |
| "grad_norm": 25.59372376753845, | |
| "learning_rate": 4.971879403278432e-07, | |
| "logits/chosen": -1.7563384771347046, | |
| "logits/rejected": -1.6859989166259766, | |
| "logps/chosen": -209.96487426757812, | |
| "logps/rejected": -244.59176635742188, | |
| "loss": 0.6016, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -0.6993848085403442, | |
| "rewards/margins": 0.3423052430152893, | |
| "rewards/rejected": -1.0416901111602783, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.15121368881814565, | |
| "grad_norm": 19.61741462433235, | |
| "learning_rate": 4.960530036504941e-07, | |
| "logits/chosen": -1.0844591856002808, | |
| "logits/rejected": -0.939785361289978, | |
| "logps/chosen": -214.14883422851562, | |
| "logps/rejected": -269.7398376464844, | |
| "loss": 0.5844, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -0.7484572529792786, | |
| "rewards/margins": 0.5090824365615845, | |
| "rewards/rejected": -1.2575398683547974, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.15917230401910068, | |
| "grad_norm": 20.322889470392276, | |
| "learning_rate": 4.947278962947386e-07, | |
| "logits/chosen": -0.841314435005188, | |
| "logits/rejected": -0.6785773038864136, | |
| "logps/chosen": -217.5854949951172, | |
| "logps/rejected": -252.13394165039062, | |
| "loss": 0.5965, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -0.734225332736969, | |
| "rewards/margins": 0.3655502200126648, | |
| "rewards/rejected": -1.0997755527496338, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15917230401910068, | |
| "eval_logits/chosen": -0.5108200907707214, | |
| "eval_logits/rejected": -0.29105332493782043, | |
| "eval_logps/chosen": -253.34841918945312, | |
| "eval_logps/rejected": -302.3987731933594, | |
| "eval_loss": 0.5933550000190735, | |
| "eval_rewards/accuracies": 0.6772388219833374, | |
| "eval_rewards/chosen": -1.0644464492797852, | |
| "eval_rewards/margins": 0.42895349860191345, | |
| "eval_rewards/rejected": -1.4933998584747314, | |
| "eval_runtime": 347.7398, | |
| "eval_samples_per_second": 24.593, | |
| "eval_steps_per_second": 0.385, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1671309192200557, | |
| "grad_norm": 22.814312588520362, | |
| "learning_rate": 4.932136424161899e-07, | |
| "logits/chosen": -0.14724041521549225, | |
| "logits/rejected": 0.11416204273700714, | |
| "logps/chosen": -296.7062072753906, | |
| "logps/rejected": -309.0001525878906, | |
| "loss": 0.5991, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -1.3078434467315674, | |
| "rewards/margins": 0.296301931142807, | |
| "rewards/rejected": -1.6041454076766968, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.17508953442101075, | |
| "grad_norm": 21.458184320123785, | |
| "learning_rate": 4.915114123589732e-07, | |
| "logits/chosen": -0.4067531228065491, | |
| "logits/rejected": 0.039240967482328415, | |
| "logps/chosen": -275.824462890625, | |
| "logps/rejected": -349.72113037109375, | |
| "loss": 0.5687, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.1693265438079834, | |
| "rewards/margins": 0.5683996081352234, | |
| "rewards/rejected": -1.7377259731292725, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.18304814962196578, | |
| "grad_norm": 18.192679070915965, | |
| "learning_rate": 4.896225217511849e-07, | |
| "logits/chosen": -0.3498181998729706, | |
| "logits/rejected": -0.03378605097532272, | |
| "logps/chosen": -270.6407775878906, | |
| "logps/rejected": -321.39971923828125, | |
| "loss": 0.5735, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -1.18222177028656, | |
| "rewards/margins": 0.45714884996414185, | |
| "rewards/rejected": -1.6393705606460571, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1910067648229208, | |
| "grad_norm": 17.971534261191277, | |
| "learning_rate": 4.875484304880629e-07, | |
| "logits/chosen": -0.42381399869918823, | |
| "logits/rejected": -0.07996497303247452, | |
| "logps/chosen": -282.5169982910156, | |
| "logps/rejected": -310.2297668457031, | |
| "loss": 0.5686, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -1.2509108781814575, | |
| "rewards/margins": 0.36313191056251526, | |
| "rewards/rejected": -1.6140426397323608, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.19896538002387584, | |
| "grad_norm": 19.570671154398198, | |
| "learning_rate": 4.852907416036558e-07, | |
| "logits/chosen": -1.4505198001861572, | |
| "logits/rejected": -0.9843381643295288, | |
| "logps/chosen": -237.9661407470703, | |
| "logps/rejected": -284.70269775390625, | |
| "loss": 0.5926, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -0.8647058606147766, | |
| "rewards/margins": 0.535582423210144, | |
| "rewards/rejected": -1.4002882242202759, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.20692399522483088, | |
| "grad_norm": 16.95113035500878, | |
| "learning_rate": 4.828512000318616e-07, | |
| "logits/chosen": -0.7392469644546509, | |
| "logits/rejected": -0.28931230306625366, | |
| "logps/chosen": -262.4371643066406, | |
| "logps/rejected": -301.09613037109375, | |
| "loss": 0.5726, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -1.2168900966644287, | |
| "rewards/margins": 0.40174025297164917, | |
| "rewards/rejected": -1.6186301708221436, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2148826104257859, | |
| "grad_norm": 16.523246341979362, | |
| "learning_rate": 4.802316912577946e-07, | |
| "logits/chosen": -0.058869220316410065, | |
| "logits/rejected": 0.5011920928955078, | |
| "logps/chosen": -253.3494110107422, | |
| "logps/rejected": -311.0137939453125, | |
| "loss": 0.5791, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.2564125061035156, | |
| "rewards/margins": 0.604422926902771, | |
| "rewards/rejected": -1.8608356714248657, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 19.225450591324332, | |
| "learning_rate": 4.774342398605221e-07, | |
| "logits/chosen": 0.02062203921377659, | |
| "logits/rejected": 0.6116986274719238, | |
| "logps/chosen": -289.97467041015625, | |
| "logps/rejected": -309.21142578125, | |
| "loss": 0.5711, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -1.2227064371109009, | |
| "rewards/margins": 0.4611144959926605, | |
| "rewards/rejected": -1.6838209629058838, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.23079984082769597, | |
| "grad_norm": 18.086581218295944, | |
| "learning_rate": 4.744610079482978e-07, | |
| "logits/chosen": -0.2072794884443283, | |
| "logits/rejected": 0.367055743932724, | |
| "logps/chosen": -283.09442138671875, | |
| "logps/rejected": -332.0167541503906, | |
| "loss": 0.5907, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.336042046546936, | |
| "rewards/margins": 0.5237594246864319, | |
| "rewards/rejected": -1.8598015308380127, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.238758456028651, | |
| "grad_norm": 21.35763469044062, | |
| "learning_rate": 4.713142934875005e-07, | |
| "logits/chosen": -0.6442250609397888, | |
| "logits/rejected": -0.12395715713500977, | |
| "logps/chosen": -272.5120544433594, | |
| "logps/rejected": -335.85205078125, | |
| "loss": 0.5621, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -1.311974287033081, | |
| "rewards/margins": 0.5121132731437683, | |
| "rewards/rejected": -1.8240875005722046, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.238758456028651, | |
| "eval_logits/chosen": -0.1607174426317215, | |
| "eval_logits/rejected": 0.31636956334114075, | |
| "eval_logps/chosen": -280.8055114746094, | |
| "eval_logps/rejected": -342.06884765625, | |
| "eval_loss": 0.5711521506309509, | |
| "eval_rewards/accuracies": 0.6875, | |
| "eval_rewards/chosen": -1.3390170335769653, | |
| "eval_rewards/margins": 0.5510838627815247, | |
| "eval_rewards/rejected": -1.8901009559631348, | |
| "eval_runtime": 347.894, | |
| "eval_samples_per_second": 24.582, | |
| "eval_steps_per_second": 0.385, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.24671707122960604, | |
| "grad_norm": 18.925595409949292, | |
| "learning_rate": 4.679965285265706e-07, | |
| "logits/chosen": 0.1555846780538559, | |
| "logits/rejected": 0.7421888709068298, | |
| "logps/chosen": -270.05670166015625, | |
| "logps/rejected": -335.81304931640625, | |
| "loss": 0.5604, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -1.152674674987793, | |
| "rewards/margins": 0.6260913610458374, | |
| "rewards/rejected": -1.7787659168243408, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.2546756864305611, | |
| "grad_norm": 20.721991698227423, | |
| "learning_rate": 4.64510277316316e-07, | |
| "logits/chosen": 0.32529157400131226, | |
| "logits/rejected": 0.7045286893844604, | |
| "logps/chosen": -249.66665649414062, | |
| "logps/rejected": -322.38623046875, | |
| "loss": 0.5451, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -1.1683197021484375, | |
| "rewards/margins": 0.6144580841064453, | |
| "rewards/rejected": -1.7827777862548828, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.26263430163151613, | |
| "grad_norm": 14.642325287307886, | |
| "learning_rate": 4.6085823432804137e-07, | |
| "logits/chosen": 0.47873038053512573, | |
| "logits/rejected": 0.7926498055458069, | |
| "logps/chosen": -267.3265075683594, | |
| "logps/rejected": -309.6785888671875, | |
| "loss": 0.5785, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -1.2106026411056519, | |
| "rewards/margins": 0.4037841260433197, | |
| "rewards/rejected": -1.614386796951294, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.27059291683247116, | |
| "grad_norm": 21.85817503072542, | |
| "learning_rate": 4.570432221710314e-07, | |
| "logits/chosen": -0.6919598579406738, | |
| "logits/rejected": -0.20407061278820038, | |
| "logps/chosen": -269.3352355957031, | |
| "logps/rejected": -297.7936096191406, | |
| "loss": 0.566, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -1.2421492338180542, | |
| "rewards/margins": 0.45925775170326233, | |
| "rewards/rejected": -1.7014070749282837, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.2785515320334262, | |
| "grad_norm": 21.890637546837947, | |
| "learning_rate": 4.5306818941099866e-07, | |
| "logits/chosen": 0.06561018526554108, | |
| "logits/rejected": 0.5712476968765259, | |
| "logps/chosen": -322.6842041015625, | |
| "logps/rejected": -386.76849365234375, | |
| "loss": 0.5751, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.7097322940826416, | |
| "rewards/margins": 0.580051064491272, | |
| "rewards/rejected": -2.289783477783203, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28651014723438123, | |
| "grad_norm": 21.606918978741653, | |
| "learning_rate": 4.4893620829118124e-07, | |
| "logits/chosen": 0.25220245122909546, | |
| "logits/rejected": 0.6177417039871216, | |
| "logps/chosen": -311.06549072265625, | |
| "logps/rejected": -332.5730285644531, | |
| "loss": 0.5817, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -1.5046530961990356, | |
| "rewards/margins": 0.4226300120353699, | |
| "rewards/rejected": -1.9272829294204712, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.29446876243533626, | |
| "grad_norm": 18.712312384246502, | |
| "learning_rate": 4.4465047235785185e-07, | |
| "logits/chosen": -0.7520114183425903, | |
| "logits/rejected": -0.39875468611717224, | |
| "logps/chosen": -257.7146911621094, | |
| "logps/rejected": -293.6401062011719, | |
| "loss": 0.5653, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -1.1130893230438232, | |
| "rewards/margins": 0.4012773633003235, | |
| "rewards/rejected": -1.514366626739502, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3024273776362913, | |
| "grad_norm": 22.820775200718288, | |
| "learning_rate": 4.40214293992074e-07, | |
| "logits/chosen": -0.7524155378341675, | |
| "logits/rejected": -0.3933519721031189, | |
| "logps/chosen": -270.42950439453125, | |
| "logps/rejected": -315.5451354980469, | |
| "loss": 0.5603, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -1.2562357187271118, | |
| "rewards/margins": 0.46937066316604614, | |
| "rewards/rejected": -1.7256062030792236, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.3103859928372463, | |
| "grad_norm": 22.618138742949483, | |
| "learning_rate": 4.3563110184961234e-07, | |
| "logits/chosen": -0.30805596709251404, | |
| "logits/rejected": 0.08593909442424774, | |
| "logps/chosen": -304.3953552246094, | |
| "logps/rejected": -344.43048095703125, | |
| "loss": 0.5511, | |
| "rewards/accuracies": 0.65625, | |
| "rewards/chosen": -1.488152027130127, | |
| "rewards/margins": 0.6020984649658203, | |
| "rewards/rejected": -2.0902504920959473, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.31834460803820136, | |
| "grad_norm": 24.046968912259764, | |
| "learning_rate": 4.3090443821097566e-07, | |
| "logits/chosen": -0.4176566004753113, | |
| "logits/rejected": -0.04139077663421631, | |
| "logps/chosen": -271.0086669921875, | |
| "logps/rejected": -326.3518981933594, | |
| "loss": 0.551, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -1.2549865245819092, | |
| "rewards/margins": 0.5567766427993774, | |
| "rewards/rejected": -1.8117631673812866, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.31834460803820136, | |
| "eval_logits/chosen": -0.6012183427810669, | |
| "eval_logits/rejected": -0.20857903361320496, | |
| "eval_logps/chosen": -268.00634765625, | |
| "eval_logps/rejected": -335.35748291015625, | |
| "eval_loss": 0.5651077628135681, | |
| "eval_rewards/accuracies": 0.7192164063453674, | |
| "eval_rewards/chosen": -1.2110257148742676, | |
| "eval_rewards/margins": 0.6119614243507385, | |
| "eval_rewards/rejected": -1.8229870796203613, | |
| "eval_runtime": 348.003, | |
| "eval_samples_per_second": 24.574, | |
| "eval_steps_per_second": 0.385, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3263032232391564, | |
| "grad_norm": 22.684798823358562, | |
| "learning_rate": 4.2603795624364195e-07, | |
| "logits/chosen": -0.4925737977027893, | |
| "logits/rejected": -0.12107300758361816, | |
| "logps/chosen": -286.2200927734375, | |
| "logps/rejected": -347.74822998046875, | |
| "loss": 0.5528, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -1.3317722082138062, | |
| "rewards/margins": 0.5646699666976929, | |
| "rewards/rejected": -1.8964424133300781, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.3342618384401114, | |
| "grad_norm": 21.49498601600208, | |
| "learning_rate": 4.210354171785795e-07, | |
| "logits/chosen": -0.2925480008125305, | |
| "logits/rejected": 0.1620359718799591, | |
| "logps/chosen": -324.54119873046875, | |
| "logps/rejected": -375.17254638671875, | |
| "loss": 0.5617, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -1.7158241271972656, | |
| "rewards/margins": 0.5555315017700195, | |
| "rewards/rejected": -2.2713558673858643, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.34222045364106646, | |
| "grad_norm": 21.031716510195604, | |
| "learning_rate": 4.15900687403248e-07, | |
| "logits/chosen": -0.6163953542709351, | |
| "logits/rejected": -0.1466153860092163, | |
| "logps/chosen": -305.3257751464844, | |
| "logps/rejected": -376.08660888671875, | |
| "loss": 0.5559, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -1.4343578815460205, | |
| "rewards/margins": 0.6992334127426147, | |
| "rewards/rejected": -2.1335911750793457, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.3501790688420215, | |
| "grad_norm": 20.623388608927577, | |
| "learning_rate": 4.1063773547332584e-07, | |
| "logits/chosen": -0.6795397996902466, | |
| "logits/rejected": -0.08995871245861053, | |
| "logps/chosen": -294.76861572265625, | |
| "logps/rejected": -366.74078369140625, | |
| "loss": 0.5548, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -1.4508978128433228, | |
| "rewards/margins": 0.8005591630935669, | |
| "rewards/rejected": -2.2514569759368896, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3581376840429765, | |
| "grad_norm": 18.86752878832109, | |
| "learning_rate": 4.0525062904547276e-07, | |
| "logits/chosen": -1.0369296073913574, | |
| "logits/rejected": -0.7145065665245056, | |
| "logps/chosen": -260.9083557128906, | |
| "logps/rejected": -321.2560729980469, | |
| "loss": 0.5713, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -1.2059574127197266, | |
| "rewards/margins": 0.5262748003005981, | |
| "rewards/rejected": -1.7322320938110352, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36609629924393156, | |
| "grad_norm": 16.972689064266323, | |
| "learning_rate": 3.997435317334988e-07, | |
| "logits/chosen": -1.0485179424285889, | |
| "logits/rejected": -0.5938493609428406, | |
| "logps/chosen": -259.70257568359375, | |
| "logps/rejected": -303.14208984375, | |
| "loss": 0.5614, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -1.2105125188827515, | |
| "rewards/margins": 0.5468652248382568, | |
| "rewards/rejected": -1.7573776245117188, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.3740549144448866, | |
| "grad_norm": 20.430854113440475, | |
| "learning_rate": 3.941206998903701e-07, | |
| "logits/chosen": -0.8004724383354187, | |
| "logits/rejected": -0.3017769455909729, | |
| "logps/chosen": -305.0013122558594, | |
| "logps/rejected": -351.1456604003906, | |
| "loss": 0.5549, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -1.5550200939178467, | |
| "rewards/margins": 0.6512759327888489, | |
| "rewards/rejected": -2.206295967102051, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.3820135296458416, | |
| "grad_norm": 23.092485323541265, | |
| "learning_rate": 3.8838647931853684e-07, | |
| "logits/chosen": -0.3017476201057434, | |
| "logits/rejected": 0.17767734825611115, | |
| "logps/chosen": -338.9472961425781, | |
| "logps/rejected": -402.6326904296875, | |
| "loss": 0.5403, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.9183552265167236, | |
| "rewards/margins": 0.6131450533866882, | |
| "rewards/rejected": -2.5315003395080566, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.38997214484679665, | |
| "grad_norm": 18.08015650723665, | |
| "learning_rate": 3.825453019111281e-07, | |
| "logits/chosen": -0.07430411875247955, | |
| "logits/rejected": 0.602587878704071, | |
| "logps/chosen": -348.27655029296875, | |
| "logps/rejected": -385.1519775390625, | |
| "loss": 0.5459, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -1.762590765953064, | |
| "rewards/margins": 0.6176367402076721, | |
| "rewards/rejected": -2.3802273273468018, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.3979307600477517, | |
| "grad_norm": 20.002403877751092, | |
| "learning_rate": 3.7660168222660824e-07, | |
| "logits/chosen": 0.1473921835422516, | |
| "logits/rejected": 0.9172118902206421, | |
| "logps/chosen": -354.8985290527344, | |
| "logps/rejected": -379.05523681640625, | |
| "loss": 0.5696, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -1.8115737438201904, | |
| "rewards/margins": 0.544532060623169, | |
| "rewards/rejected": -2.3561058044433594, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3979307600477517, | |
| "eval_logits/chosen": 0.08715073019266129, | |
| "eval_logits/rejected": 0.5150542855262756, | |
| "eval_logps/chosen": -329.2126770019531, | |
| "eval_logps/rejected": -392.61614990234375, | |
| "eval_loss": 0.5572181344032288, | |
| "eval_rewards/accuracies": 0.7229477763175964, | |
| "eval_rewards/chosen": -1.8230891227722168, | |
| "eval_rewards/margins": 0.5724846124649048, | |
| "eval_rewards/rejected": -2.395573854446411, | |
| "eval_runtime": 348.5057, | |
| "eval_samples_per_second": 24.539, | |
| "eval_steps_per_second": 0.384, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4058893752487067, | |
| "grad_norm": 18.39580411753885, | |
| "learning_rate": 3.705602139995416e-07, | |
| "logits/chosen": 0.08027039468288422, | |
| "logits/rejected": 0.7471383810043335, | |
| "logps/chosen": -305.5868835449219, | |
| "logps/rejected": -390.7528076171875, | |
| "loss": 0.5476, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -1.5938637256622314, | |
| "rewards/margins": 0.8495914340019226, | |
| "rewards/rejected": -2.443455219268799, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.41384799044966175, | |
| "grad_norm": 21.538483001362934, | |
| "learning_rate": 3.6442556659016475e-07, | |
| "logits/chosen": 0.034043505787849426, | |
| "logits/rejected": 0.929337203502655, | |
| "logps/chosen": -279.78143310546875, | |
| "logps/rejected": -357.68695068359375, | |
| "loss": 0.554, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -1.2777533531188965, | |
| "rewards/margins": 0.8431286811828613, | |
| "rewards/rejected": -2.120882034301758, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.4218066056506168, | |
| "grad_norm": 17.59460512186992, | |
| "learning_rate": 3.582024813755076e-07, | |
| "logits/chosen": -0.20782026648521423, | |
| "logits/rejected": 0.35743075609207153, | |
| "logps/chosen": -288.68463134765625, | |
| "logps/rejected": -331.3399963378906, | |
| "loss": 0.5513, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -1.2878282070159912, | |
| "rewards/margins": 0.4769444465637207, | |
| "rewards/rejected": -1.7647724151611328, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.4297652208515718, | |
| "grad_norm": 20.90074242546295, | |
| "learning_rate": 3.5189576808485404e-07, | |
| "logits/chosen": -0.1114623099565506, | |
| "logits/rejected": 0.424373060464859, | |
| "logps/chosen": -293.0398864746094, | |
| "logps/rejected": -363.51739501953125, | |
| "loss": 0.5404, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -1.5382354259490967, | |
| "rewards/margins": 0.6857717633247375, | |
| "rewards/rejected": -2.2240071296691895, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.43772383605252685, | |
| "grad_norm": 23.171714324291212, | |
| "learning_rate": 3.4551030108237433e-07, | |
| "logits/chosen": 0.3947924077510834, | |
| "logits/rejected": 0.8871338963508606, | |
| "logps/chosen": -294.8044738769531, | |
| "logps/rejected": -357.0321350097656, | |
| "loss": 0.5583, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -1.5001775026321411, | |
| "rewards/margins": 0.5571330189704895, | |
| "rewards/rejected": -2.0573105812072754, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 16.844516375770297, | |
| "learning_rate": 3.390510155998023e-07, | |
| "logits/chosen": 0.7585184574127197, | |
| "logits/rejected": 1.5741997957229614, | |
| "logps/chosen": -327.8985595703125, | |
| "logps/rejected": -400.3335266113281, | |
| "loss": 0.5335, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -1.7798864841461182, | |
| "rewards/margins": 0.7171236872673035, | |
| "rewards/rejected": -2.4970102310180664, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.4536410664544369, | |
| "grad_norm": 19.847258394334578, | |
| "learning_rate": 3.325229039220684e-07, | |
| "logits/chosen": 0.8790721893310547, | |
| "logits/rejected": 1.7523505687713623, | |
| "logps/chosen": -359.2749938964844, | |
| "logps/rejected": -424.80499267578125, | |
| "loss": 0.5515, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -1.9252793788909912, | |
| "rewards/margins": 0.7141390442848206, | |
| "rewards/rejected": -2.639418363571167, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.46159968165539195, | |
| "grad_norm": 16.499266637052294, | |
| "learning_rate": 3.2593101152883795e-07, | |
| "logits/chosen": 0.8924285173416138, | |
| "logits/rejected": 1.5235947370529175, | |
| "logps/chosen": -365.3081970214844, | |
| "logps/rejected": -430.99444580078125, | |
| "loss": 0.5584, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.1520824432373047, | |
| "rewards/margins": 0.5842655897140503, | |
| "rewards/rejected": -2.7363476753234863, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.469558296856347, | |
| "grad_norm": 19.289158217917635, | |
| "learning_rate": 3.192804331949349e-07, | |
| "logits/chosen": 0.44026702642440796, | |
| "logits/rejected": 1.019954800605774, | |
| "logps/chosen": -345.7406005859375, | |
| "logps/rejected": -414.36175537109375, | |
| "loss": 0.5328, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.0610880851745605, | |
| "rewards/margins": 0.6739950180053711, | |
| "rewards/rejected": -2.7350831031799316, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.477516912057302, | |
| "grad_norm": 20.92118650846254, | |
| "learning_rate": 3.125763090526674e-07, | |
| "logits/chosen": 0.970676064491272, | |
| "logits/rejected": 2.074838399887085, | |
| "logps/chosen": -345.6512145996094, | |
| "logps/rejected": -411.70477294921875, | |
| "loss": 0.5504, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -1.9593521356582642, | |
| "rewards/margins": 0.8702648878097534, | |
| "rewards/rejected": -2.8296167850494385, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.477516912057302, | |
| "eval_logits/chosen": 0.4866677522659302, | |
| "eval_logits/rejected": 1.2370327711105347, | |
| "eval_logps/chosen": -339.2297668457031, | |
| "eval_logps/rejected": -423.96630859375, | |
| "eval_loss": 0.5507791638374329, | |
| "eval_rewards/accuracies": 0.7201492786407471, | |
| "eval_rewards/chosen": -1.9232597351074219, | |
| "eval_rewards/margins": 0.7858158946037292, | |
| "eval_rewards/rejected": -2.709075689315796, | |
| "eval_runtime": 349.0994, | |
| "eval_samples_per_second": 24.497, | |
| "eval_steps_per_second": 0.384, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.48547552725825704, | |
| "grad_norm": 18.912227877255763, | |
| "learning_rate": 3.0582382061909623e-07, | |
| "logits/chosen": 0.08690143376588821, | |
| "logits/rejected": 0.8724335432052612, | |
| "logps/chosen": -364.74578857421875, | |
| "logps/rejected": -458.05487060546875, | |
| "loss": 0.5407, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -1.894468903541565, | |
| "rewards/margins": 0.8513941764831543, | |
| "rewards/rejected": -2.745863437652588, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.4934341424592121, | |
| "grad_norm": 15.345100918286033, | |
| "learning_rate": 2.9902818679131775e-07, | |
| "logits/chosen": -0.0536082498729229, | |
| "logits/rejected": 1.048099398612976, | |
| "logps/chosen": -342.81097412109375, | |
| "logps/rejected": -402.736328125, | |
| "loss": 0.5478, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -1.7372751235961914, | |
| "rewards/margins": 0.8304754495620728, | |
| "rewards/rejected": -2.5677504539489746, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.5013927576601671, | |
| "grad_norm": 19.242517379429756, | |
| "learning_rate": 2.921946598128571e-07, | |
| "logits/chosen": -0.14560095965862274, | |
| "logits/rejected": 0.7982407808303833, | |
| "logps/chosen": -312.3756408691406, | |
| "logps/rejected": -383.5072021484375, | |
| "loss": 0.5432, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.5843050479888916, | |
| "rewards/margins": 0.8270316123962402, | |
| "rewards/rejected": -2.411336898803711, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.5093513728611222, | |
| "grad_norm": 19.263253541697434, | |
| "learning_rate": 2.8532852121428733e-07, | |
| "logits/chosen": 0.22138485312461853, | |
| "logits/rejected": 0.9763603210449219, | |
| "logps/chosen": -308.0843811035156, | |
| "logps/rejected": -368.4732971191406, | |
| "loss": 0.5352, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -1.6622591018676758, | |
| "rewards/margins": 0.7096768617630005, | |
| "rewards/rejected": -2.3719358444213867, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.5173099880620772, | |
| "grad_norm": 22.205857969775185, | |
| "learning_rate": 2.7843507773121414e-07, | |
| "logits/chosen": 0.6237181425094604, | |
| "logits/rejected": 1.5619014501571655, | |
| "logps/chosen": -342.9239807128906, | |
| "logps/rejected": -444.139892578125, | |
| "loss": 0.526, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -1.9262256622314453, | |
| "rewards/margins": 0.9577581286430359, | |
| "rewards/rejected": -2.883983850479126, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5252686032630323, | |
| "grad_norm": 18.128676048285264, | |
| "learning_rate": 2.715196572027789e-07, | |
| "logits/chosen": 0.98185795545578, | |
| "logits/rejected": 1.66350519657135, | |
| "logps/chosen": -382.2640075683594, | |
| "logps/rejected": -468.0584411621094, | |
| "loss": 0.5367, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -2.389634370803833, | |
| "rewards/margins": 0.7552004456520081, | |
| "rewards/rejected": -3.1448347568511963, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.5332272184639872, | |
| "grad_norm": 16.001394211106067, | |
| "learning_rate": 2.645876044538521e-07, | |
| "logits/chosen": 1.2729809284210205, | |
| "logits/rejected": 1.5976616144180298, | |
| "logps/chosen": -350.9837646484375, | |
| "logps/rejected": -434.87060546875, | |
| "loss": 0.5386, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -2.2160532474517822, | |
| "rewards/margins": 0.5502675771713257, | |
| "rewards/rejected": -2.7663207054138184, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.5411858336649423, | |
| "grad_norm": 18.674809360169434, | |
| "learning_rate": 2.5764427716409815e-07, | |
| "logits/chosen": 1.510772705078125, | |
| "logits/rejected": 2.1603095531463623, | |
| "logps/chosen": -406.2839660644531, | |
| "logps/rejected": -456.6971740722656, | |
| "loss": 0.5519, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -2.386213779449463, | |
| "rewards/margins": 0.6464362740516663, | |
| "rewards/rejected": -3.0326499938964844, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.5491444488658973, | |
| "grad_norm": 19.685756061152915, | |
| "learning_rate": 2.5069504172710494e-07, | |
| "logits/chosen": 1.9052760601043701, | |
| "logits/rejected": 2.854236364364624, | |
| "logps/chosen": -398.56829833984375, | |
| "logps/rejected": -475.7207946777344, | |
| "loss": 0.5318, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -2.607776165008545, | |
| "rewards/margins": 0.8156100511550903, | |
| "rewards/rejected": -3.423386335372925, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "grad_norm": 21.722190178307944, | |
| "learning_rate": 2.4374526910277886e-07, | |
| "logits/chosen": 1.4309998750686646, | |
| "logits/rejected": 2.0307841300964355, | |
| "logps/chosen": -382.191162109375, | |
| "logps/rejected": -473.32183837890625, | |
| "loss": 0.5387, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -2.5259125232696533, | |
| "rewards/margins": 0.7485069632530212, | |
| "rewards/rejected": -3.2744197845458984, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "eval_logits/chosen": 1.1806707382202148, | |
| "eval_logits/rejected": 1.9106937646865845, | |
| "eval_logps/chosen": -380.19281005859375, | |
| "eval_logps/rejected": -464.579833984375, | |
| "eval_loss": 0.5417102575302124, | |
| "eval_rewards/accuracies": 0.7210820913314819, | |
| "eval_rewards/chosen": -2.332890510559082, | |
| "eval_rewards/margins": 0.7823202013969421, | |
| "eval_rewards/rejected": -3.115210771560669, | |
| "eval_runtime": 349.0863, | |
| "eval_samples_per_second": 24.498, | |
| "eval_steps_per_second": 0.384, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5650616792678074, | |
| "grad_norm": 16.03437069863273, | |
| "learning_rate": 2.368003306662104e-07, | |
| "logits/chosen": 0.908370316028595, | |
| "logits/rejected": 1.6032642126083374, | |
| "logps/chosen": -369.47900390625, | |
| "logps/rejected": -431.5857849121094, | |
| "loss": 0.5607, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.1660048961639404, | |
| "rewards/margins": 0.6613842248916626, | |
| "rewards/rejected": -2.8273892402648926, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.5730202944687625, | |
| "grad_norm": 17.46281711779211, | |
| "learning_rate": 2.2986559405621886e-07, | |
| "logits/chosen": 0.8651970028877258, | |
| "logits/rejected": 1.6542387008666992, | |
| "logps/chosen": -364.164794921875, | |
| "logps/rejected": -433.8982849121094, | |
| "loss": 0.5354, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.096378803253174, | |
| "rewards/margins": 0.7120481133460999, | |
| "rewards/rejected": -2.808427095413208, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.5809789096697174, | |
| "grad_norm": 19.94099113488109, | |
| "learning_rate": 2.2294641902678443e-07, | |
| "logits/chosen": 0.88880854845047, | |
| "logits/rejected": 1.6225669384002686, | |
| "logps/chosen": -333.8936462402344, | |
| "logps/rejected": -411.53857421875, | |
| "loss": 0.5348, | |
| "rewards/accuracies": 0.643750011920929, | |
| "rewards/chosen": -1.8313400745391846, | |
| "rewards/margins": 0.8025676608085632, | |
| "rewards/rejected": -2.6339077949523926, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.5889375248706725, | |
| "grad_norm": 19.161711121288285, | |
| "learning_rate": 2.160481533045751e-07, | |
| "logits/chosen": 1.7531951665878296, | |
| "logits/rejected": 2.6644296646118164, | |
| "logps/chosen": -379.2308654785156, | |
| "logps/rejected": -482.81903076171875, | |
| "loss": 0.554, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -2.293461322784424, | |
| "rewards/margins": 1.045929193496704, | |
| "rewards/rejected": -3.339390516281128, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.5968961400716275, | |
| "grad_norm": 19.15869602934714, | |
| "learning_rate": 2.0917612845576882e-07, | |
| "logits/chosen": 1.944665551185608, | |
| "logits/rejected": 2.7940452098846436, | |
| "logps/chosen": -385.5401916503906, | |
| "logps/rejected": -463.55401611328125, | |
| "loss": 0.5252, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -2.5116262435913086, | |
| "rewards/margins": 0.8533546328544617, | |
| "rewards/rejected": -3.364980697631836, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.6048547552725826, | |
| "grad_norm": 21.49823487598931, | |
| "learning_rate": 2.0233565576536564e-07, | |
| "logits/chosen": 1.6610772609710693, | |
| "logits/rejected": 2.386462688446045, | |
| "logps/chosen": -380.05462646484375, | |
| "logps/rejected": -462.010498046875, | |
| "loss": 0.5255, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -2.2347652912139893, | |
| "rewards/margins": 0.7181671261787415, | |
| "rewards/rejected": -2.952932119369507, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.6128133704735376, | |
| "grad_norm": 20.93099391686062, | |
| "learning_rate": 1.9553202213217537e-07, | |
| "logits/chosen": 2.1078057289123535, | |
| "logits/rejected": 3.0261335372924805, | |
| "logps/chosen": -390.66082763671875, | |
| "logps/rejected": -465.5203552246094, | |
| "loss": 0.541, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -2.3615031242370605, | |
| "rewards/margins": 0.9020525217056274, | |
| "rewards/rejected": -3.2635560035705566, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.6207719856744927, | |
| "grad_norm": 16.749614654207814, | |
| "learning_rate": 1.887704859826528e-07, | |
| "logits/chosen": 2.5508079528808594, | |
| "logits/rejected": 3.456491470336914, | |
| "logps/chosen": -404.16729736328125, | |
| "logps/rejected": -483.2388610839844, | |
| "loss": 0.5457, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -2.6340322494506836, | |
| "rewards/margins": 0.8538228869438171, | |
| "rewards/rejected": -3.4878547191619873, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.6287306008754476, | |
| "grad_norm": 16.5271927987375, | |
| "learning_rate": 1.8205627320673836e-07, | |
| "logits/chosen": 2.747197389602661, | |
| "logits/rejected": 3.1584315299987793, | |
| "logps/chosen": -409.50946044921875, | |
| "logps/rejected": -479.3316345214844, | |
| "loss": 0.5402, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -2.6576485633850098, | |
| "rewards/margins": 0.5818369388580322, | |
| "rewards/rejected": -3.239485502243042, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.6366892160764027, | |
| "grad_norm": 20.529555438059905, | |
| "learning_rate": 1.7539457311884675e-07, | |
| "logits/chosen": 2.4543442726135254, | |
| "logits/rejected": 3.273699998855591, | |
| "logps/chosen": -408.31427001953125, | |
| "logps/rejected": -496.12091064453125, | |
| "loss": 0.5119, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.5986037254333496, | |
| "rewards/margins": 0.82551509141922, | |
| "rewards/rejected": -3.424118757247925, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6366892160764027, | |
| "eval_logits/chosen": 2.7208683490753174, | |
| "eval_logits/rejected": 3.444331645965576, | |
| "eval_logps/chosen": -414.11798095703125, | |
| "eval_logps/rejected": -503.328125, | |
| "eval_loss": 0.541582465171814, | |
| "eval_rewards/accuracies": 0.7276119589805603, | |
| "eval_rewards/chosen": -2.6721420288085938, | |
| "eval_rewards/margins": 0.83055180311203, | |
| "eval_rewards/rejected": -3.5026936531066895, | |
| "eval_runtime": 348.3456, | |
| "eval_samples_per_second": 24.55, | |
| "eval_steps_per_second": 0.385, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6446478312773577, | |
| "grad_norm": 19.46716360912331, | |
| "learning_rate": 1.687905344471226e-07, | |
| "logits/chosen": 2.899752616882324, | |
| "logits/rejected": 3.6358859539031982, | |
| "logps/chosen": -426.015380859375, | |
| "logps/rejected": -523.51708984375, | |
| "loss": 0.5394, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -2.757784605026245, | |
| "rewards/margins": 0.8762688636779785, | |
| "rewards/rejected": -3.6340534687042236, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.6526064464783128, | |
| "grad_norm": 20.097758366480125, | |
| "learning_rate": 1.6224926135406693e-07, | |
| "logits/chosen": 2.4270927906036377, | |
| "logits/rejected": 3.3316092491149902, | |
| "logps/chosen": -420.87542724609375, | |
| "logps/rejected": -481.60076904296875, | |
| "loss": 0.5303, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.7377285957336426, | |
| "rewards/margins": 0.7255538702011108, | |
| "rewards/rejected": -3.463282823562622, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.6605650616792678, | |
| "grad_norm": 17.290268929609024, | |
| "learning_rate": 1.557758094916053e-07, | |
| "logits/chosen": 2.7220635414123535, | |
| "logits/rejected": 3.3889517784118652, | |
| "logps/chosen": -438.2432556152344, | |
| "logps/rejected": -506.6184997558594, | |
| "loss": 0.5311, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -2.7044851779937744, | |
| "rewards/margins": 0.7628629803657532, | |
| "rewards/rejected": -3.467348575592041, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.6685236768802229, | |
| "grad_norm": 20.475546044973836, | |
| "learning_rate": 1.4937518209365108e-07, | |
| "logits/chosen": 2.531759738922119, | |
| "logits/rejected": 3.477173328399658, | |
| "logps/chosen": -438.1893615722656, | |
| "logps/rejected": -512.6656494140625, | |
| "loss": 0.5221, | |
| "rewards/accuracies": 0.6937500238418579, | |
| "rewards/chosen": -2.8120474815368652, | |
| "rewards/margins": 0.850610613822937, | |
| "rewards/rejected": -3.66265869140625, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.6764822920811778, | |
| "grad_norm": 19.71518623080275, | |
| "learning_rate": 1.4305232610918045e-07, | |
| "logits/chosen": 2.5035440921783447, | |
| "logits/rejected": 3.8153274059295654, | |
| "logps/chosen": -413.65533447265625, | |
| "logps/rejected": -504.1393127441406, | |
| "loss": 0.5189, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -2.5576460361480713, | |
| "rewards/margins": 1.1708472967147827, | |
| "rewards/rejected": -3.7284939289093018, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6844409072821329, | |
| "grad_norm": 17.595133264616365, | |
| "learning_rate": 1.3681212837880977e-07, | |
| "logits/chosen": 2.362572431564331, | |
| "logits/rejected": 3.3001837730407715, | |
| "logps/chosen": -384.64825439453125, | |
| "logps/rejected": -475.32489013671875, | |
| "loss": 0.5186, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -2.380725145339966, | |
| "rewards/margins": 0.9119716882705688, | |
| "rewards/rejected": -3.292696714401245, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.6923995224830879, | |
| "grad_norm": 18.53603009333697, | |
| "learning_rate": 1.3065941185782977e-07, | |
| "logits/chosen": 2.170623302459717, | |
| "logits/rejected": 2.6820473670959473, | |
| "logps/chosen": -410.9842224121094, | |
| "logps/rejected": -517.3212890625, | |
| "loss": 0.5136, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -2.604910135269165, | |
| "rewards/margins": 0.8896166682243347, | |
| "rewards/rejected": -3.4945271015167236, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.700358137684043, | |
| "grad_norm": 27.040507130579233, | |
| "learning_rate": 1.2459893188861613e-07, | |
| "logits/chosen": 2.036362648010254, | |
| "logits/rejected": 3.0169339179992676, | |
| "logps/chosen": -395.36248779296875, | |
| "logps/rejected": -469.5846252441406, | |
| "loss": 0.5127, | |
| "rewards/accuracies": 0.78125, | |
| "rewards/chosen": -2.4672751426696777, | |
| "rewards/margins": 0.9281255006790161, | |
| "rewards/rejected": -3.3954005241394043, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.708316752884998, | |
| "grad_norm": 19.58653971077579, | |
| "learning_rate": 1.1863537252529548e-07, | |
| "logits/chosen": 1.9658253192901611, | |
| "logits/rejected": 3.1701443195343018, | |
| "logps/chosen": -395.36279296875, | |
| "logps/rejected": -498.6559143066406, | |
| "loss": 0.5361, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": -2.475236177444458, | |
| "rewards/margins": 1.1605395078659058, | |
| "rewards/rejected": -3.635775327682495, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.716275368085953, | |
| "grad_norm": 16.08727968386679, | |
| "learning_rate": 1.1277334291351145e-07, | |
| "logits/chosen": 1.9292398691177368, | |
| "logits/rejected": 2.558868885040283, | |
| "logps/chosen": -445.3673400878906, | |
| "logps/rejected": -508.82794189453125, | |
| "loss": 0.564, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.6232690811157227, | |
| "rewards/margins": 0.7433099150657654, | |
| "rewards/rejected": -3.3665783405303955, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.716275368085953, | |
| "eval_logits/chosen": 1.9952205419540405, | |
| "eval_logits/rejected": 2.5529251098632812, | |
| "eval_logps/chosen": -410.51849365234375, | |
| "eval_logps/rejected": -489.1202087402344, | |
| "eval_loss": 0.5384515523910522, | |
| "eval_rewards/accuracies": 0.7182835936546326, | |
| "eval_rewards/chosen": -2.6361470222473145, | |
| "eval_rewards/margins": 0.7244672775268555, | |
| "eval_rewards/rejected": -3.36061429977417, | |
| "eval_runtime": 348.9854, | |
| "eval_samples_per_second": 24.505, | |
| "eval_steps_per_second": 0.384, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.724233983286908, | |
| "grad_norm": 19.608360282510876, | |
| "learning_rate": 1.0701737372808431e-07, | |
| "logits/chosen": 1.9433863162994385, | |
| "logits/rejected": 2.197230100631714, | |
| "logps/chosen": -402.63958740234375, | |
| "logps/rejected": -492.9768981933594, | |
| "loss": 0.5417, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.6037509441375732, | |
| "rewards/margins": 0.6724608540534973, | |
| "rewards/rejected": -3.2762115001678467, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.7321925984878631, | |
| "grad_norm": 21.302962778555738, | |
| "learning_rate": 1.0137191367132078e-07, | |
| "logits/chosen": 2.313117504119873, | |
| "logits/rejected": 2.6423773765563965, | |
| "logps/chosen": -418.1343688964844, | |
| "logps/rejected": -490.7264709472656, | |
| "loss": 0.542, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -2.770127534866333, | |
| "rewards/margins": 0.5889343619346619, | |
| "rewards/rejected": -3.3590621948242188, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.7401512136888182, | |
| "grad_norm": 20.543232804563647, | |
| "learning_rate": 9.584132603467827e-08, | |
| "logits/chosen": 2.2165169715881348, | |
| "logits/rejected": 2.9923043251037598, | |
| "logps/chosen": -415.32177734375, | |
| "logps/rejected": -475.14544677734375, | |
| "loss": 0.5193, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -2.3847451210021973, | |
| "rewards/margins": 0.7635815739631653, | |
| "rewards/rejected": -3.148326873779297, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.7481098288897732, | |
| "grad_norm": 16.82352536953462, | |
| "learning_rate": 9.042988532644249e-08, | |
| "logits/chosen": 2.554182529449463, | |
| "logits/rejected": 3.0109364986419678, | |
| "logps/chosen": -417.294921875, | |
| "logps/rejected": -497.1542053222656, | |
| "loss": 0.5421, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -2.6419878005981445, | |
| "rewards/margins": 0.7793722748756409, | |
| "rewards/rejected": -3.4213595390319824, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.7560684440907283, | |
| "grad_norm": 16.52509872707129, | |
| "learning_rate": 8.514177396802428e-08, | |
| "logits/chosen": 2.2360918521881104, | |
| "logits/rejected": 2.8688242435455322, | |
| "logps/chosen": -388.20880126953125, | |
| "logps/rejected": -494.08721923828125, | |
| "loss": 0.5432, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -2.520381450653076, | |
| "rewards/margins": 0.9274767637252808, | |
| "rewards/rejected": -3.4478580951690674, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7640270592916832, | |
| "grad_norm": 18.591898542275075, | |
| "learning_rate": 7.998107906142839e-08, | |
| "logits/chosen": 2.534701108932495, | |
| "logits/rejected": 3.3956542015075684, | |
| "logps/chosen": -409.61944580078125, | |
| "logps/rejected": -477.8722229003906, | |
| "loss": 0.5346, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": -2.4543957710266113, | |
| "rewards/margins": 0.8880963325500488, | |
| "rewards/rejected": -3.3424923419952393, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.7719856744926383, | |
| "grad_norm": 23.074813574206292, | |
| "learning_rate": 7.495178923039396e-08, | |
| "logits/chosen": 2.1817586421966553, | |
| "logits/rejected": 3.049762487411499, | |
| "logps/chosen": -394.3160705566406, | |
| "logps/rejected": -475.4697265625, | |
| "loss": 0.5496, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -2.4694297313690186, | |
| "rewards/margins": 0.882437527179718, | |
| "rewards/rejected": -3.35186767578125, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.7799442896935933, | |
| "grad_norm": 18.820352227282687, | |
| "learning_rate": 7.005779153764682e-08, | |
| "logits/chosen": 2.0304465293884277, | |
| "logits/rejected": 2.5523359775543213, | |
| "logps/chosen": -387.8653564453125, | |
| "logps/rejected": -465.1128845214844, | |
| "loss": 0.5422, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -2.4239563941955566, | |
| "rewards/margins": 0.675017237663269, | |
| "rewards/rejected": -3.098973512649536, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.7879029048945484, | |
| "grad_norm": 18.25070063670074, | |
| "learning_rate": 6.530286848064698e-08, | |
| "logits/chosen": 1.7723140716552734, | |
| "logits/rejected": 1.9407542943954468, | |
| "logps/chosen": -413.15692138671875, | |
| "logps/rejected": -463.80865478515625, | |
| "loss": 0.5479, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -2.591344118118286, | |
| "rewards/margins": 0.4910058379173279, | |
| "rewards/rejected": -3.082350254058838, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.7958615200955034, | |
| "grad_norm": 17.31216331182086, | |
| "learning_rate": 6.069069506815325e-08, | |
| "logits/chosen": 2.043708324432373, | |
| "logits/rejected": 2.6901423931121826, | |
| "logps/chosen": -399.66064453125, | |
| "logps/rejected": -487.8421936035156, | |
| "loss": 0.5201, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": -2.45231556892395, | |
| "rewards/margins": 0.9817484617233276, | |
| "rewards/rejected": -3.4340641498565674, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7958615200955034, | |
| "eval_logits/chosen": 1.8888087272644043, | |
| "eval_logits/rejected": 2.4305639266967773, | |
| "eval_logps/chosen": -397.115966796875, | |
| "eval_logps/rejected": -481.51214599609375, | |
| "eval_loss": 0.5347379446029663, | |
| "eval_rewards/accuracies": 0.7229477763175964, | |
| "eval_rewards/chosen": -2.502121925354004, | |
| "eval_rewards/margins": 0.7824118137359619, | |
| "eval_rewards/rejected": -3.2845335006713867, | |
| "eval_runtime": 350.501, | |
| "eval_samples_per_second": 24.399, | |
| "eval_steps_per_second": 0.382, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8038201352964585, | |
| "grad_norm": 17.72839329874758, | |
| "learning_rate": 5.6224835979863714e-08, | |
| "logits/chosen": 1.8582655191421509, | |
| "logits/rejected": 2.2548227310180664, | |
| "logps/chosen": -385.1344909667969, | |
| "logps/rejected": -468.8387145996094, | |
| "loss": 0.522, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.356790065765381, | |
| "rewards/margins": 0.7311912775039673, | |
| "rewards/rejected": -3.0879814624786377, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.8117787504974134, | |
| "grad_norm": 18.254082210124515, | |
| "learning_rate": 5.190874281132851e-08, | |
| "logits/chosen": 2.157611131668091, | |
| "logits/rejected": 2.920135974884033, | |
| "logps/chosen": -406.5130310058594, | |
| "logps/rejected": -482.342529296875, | |
| "loss": 0.5486, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -2.3830180168151855, | |
| "rewards/margins": 0.8080500364303589, | |
| "rewards/rejected": -3.191068172454834, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.8197373656983685, | |
| "grad_norm": 24.462207528511584, | |
| "learning_rate": 4.774575140626316e-08, | |
| "logits/chosen": 2.092142105102539, | |
| "logits/rejected": 2.9269495010375977, | |
| "logps/chosen": -421.19830322265625, | |
| "logps/rejected": -489.29571533203125, | |
| "loss": 0.5479, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": -2.6434485912323, | |
| "rewards/margins": 0.8873342275619507, | |
| "rewards/rejected": -3.530783176422119, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.8276959808993235, | |
| "grad_norm": 18.98119668610804, | |
| "learning_rate": 4.373907927832513e-08, | |
| "logits/chosen": 2.023267984390259, | |
| "logits/rejected": 2.8832485675811768, | |
| "logps/chosen": -404.16546630859375, | |
| "logps/rejected": -519.4654541015625, | |
| "loss": 0.5224, | |
| "rewards/accuracies": 0.78125, | |
| "rewards/chosen": -2.4847495555877686, | |
| "rewards/margins": 1.1609361171722412, | |
| "rewards/rejected": -3.6456856727600098, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.8356545961002786, | |
| "grad_norm": 17.461112275411644, | |
| "learning_rate": 3.9891823124345665e-08, | |
| "logits/chosen": 2.068453311920166, | |
| "logits/rejected": 2.5450072288513184, | |
| "logps/chosen": -420.19927978515625, | |
| "logps/rejected": -475.58404541015625, | |
| "loss": 0.5501, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -2.6072211265563965, | |
| "rewards/margins": 0.6359682083129883, | |
| "rewards/rejected": -3.2431893348693848, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.8436132113012336, | |
| "grad_norm": 16.543474663899303, | |
| "learning_rate": 3.620695643093924e-08, | |
| "logits/chosen": 1.6659740209579468, | |
| "logits/rejected": 2.1419837474823, | |
| "logps/chosen": -398.4236145019531, | |
| "logps/rejected": -484.2503967285156, | |
| "loss": 0.5452, | |
| "rewards/accuracies": 0.768750011920929, | |
| "rewards/chosen": -2.5702877044677734, | |
| "rewards/margins": 0.7829211950302124, | |
| "rewards/rejected": -3.353208541870117, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.8515718265021887, | |
| "grad_norm": 17.254761854068718, | |
| "learning_rate": 3.268732717634032e-08, | |
| "logits/chosen": 1.6836740970611572, | |
| "logits/rejected": 2.284329652786255, | |
| "logps/chosen": -411.85009765625, | |
| "logps/rejected": -475.13922119140625, | |
| "loss": 0.5274, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -2.4504170417785645, | |
| "rewards/margins": 0.7453802824020386, | |
| "rewards/rejected": -3.1957974433898926, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.8595304417031436, | |
| "grad_norm": 17.38092861982639, | |
| "learning_rate": 2.9335655629243645e-08, | |
| "logits/chosen": 1.6976267099380493, | |
| "logits/rejected": 2.579646110534668, | |
| "logps/chosen": -400.24896240234375, | |
| "logps/rejected": -494.01953125, | |
| "loss": 0.546, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -2.477663516998291, | |
| "rewards/margins": 0.8947075009346008, | |
| "rewards/rejected": -3.372371196746826, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.8674890569040987, | |
| "grad_norm": 19.735012113626887, | |
| "learning_rate": 2.6154532246349476e-08, | |
| "logits/chosen": 1.7606983184814453, | |
| "logits/rejected": 2.5042643547058105, | |
| "logps/chosen": -420.964599609375, | |
| "logps/rejected": -511.8990173339844, | |
| "loss": 0.5358, | |
| "rewards/accuracies": 0.7875000238418579, | |
| "rewards/chosen": -2.4465584754943848, | |
| "rewards/margins": 0.9180288314819336, | |
| "rewards/rejected": -3.3645873069763184, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.8754476721050537, | |
| "grad_norm": 20.59566154349169, | |
| "learning_rate": 2.31464156702382e-08, | |
| "logits/chosen": 1.714812994003296, | |
| "logits/rejected": 2.1487162113189697, | |
| "logps/chosen": -376.896728515625, | |
| "logps/rejected": -463.0181579589844, | |
| "loss": 0.5341, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -2.430546522140503, | |
| "rewards/margins": 0.7609037160873413, | |
| "rewards/rejected": -3.191450357437134, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8754476721050537, | |
| "eval_logits/chosen": 1.8146584033966064, | |
| "eval_logits/rejected": 2.3851335048675537, | |
| "eval_logps/chosen": -395.8829650878906, | |
| "eval_logps/rejected": -481.46636962890625, | |
| "eval_loss": 0.5346034169197083, | |
| "eval_rewards/accuracies": 0.72947758436203, | |
| "eval_rewards/chosen": -2.4897918701171875, | |
| "eval_rewards/margins": 0.7942842245101929, | |
| "eval_rewards/rejected": -3.2840757369995117, | |
| "eval_runtime": 349.0502, | |
| "eval_samples_per_second": 24.501, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8834062873060088, | |
| "grad_norm": 24.480879815940032, | |
| "learning_rate": 2.031363082912252e-08, | |
| "logits/chosen": 1.3329254388809204, | |
| "logits/rejected": 1.8607990741729736, | |
| "logps/chosen": -393.1271057128906, | |
| "logps/rejected": -474.62030029296875, | |
| "loss": 0.5303, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": -2.4428350925445557, | |
| "rewards/margins": 0.7839537858963013, | |
| "rewards/rejected": -3.2267889976501465, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.8913649025069638, | |
| "grad_norm": 22.23107791348212, | |
| "learning_rate": 1.7658367139945228e-08, | |
| "logits/chosen": 1.9081084728240967, | |
| "logits/rejected": 2.736818790435791, | |
| "logps/chosen": -383.86090087890625, | |
| "logps/rejected": -476.2447814941406, | |
| "loss": 0.5523, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.3657093048095703, | |
| "rewards/margins": 0.9522883296012878, | |
| "rewards/rejected": -3.317997455596924, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.8993235177079189, | |
| "grad_norm": 18.52217546312308, | |
| "learning_rate": 1.5182676816211632e-08, | |
| "logits/chosen": 1.5083836317062378, | |
| "logits/rejected": 2.2149221897125244, | |
| "logps/chosen": -386.4073791503906, | |
| "logps/rejected": -472.29425048828125, | |
| "loss": 0.5071, | |
| "rewards/accuracies": 0.75, | |
| "rewards/chosen": -2.3090853691101074, | |
| "rewards/margins": 0.8999401926994324, | |
| "rewards/rejected": -3.2090256214141846, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.9072821329088738, | |
| "grad_norm": 18.15234080791347, | |
| "learning_rate": 1.2888473281864597e-08, | |
| "logits/chosen": 2.142833709716797, | |
| "logits/rejected": 2.8091158866882324, | |
| "logps/chosen": -391.89910888671875, | |
| "logps/rejected": -496.69757080078125, | |
| "loss": 0.5088, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -2.436957836151123, | |
| "rewards/margins": 0.9512897729873657, | |
| "rewards/rejected": -3.3882477283477783, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.9152407481098289, | |
| "grad_norm": 40.801838672570874, | |
| "learning_rate": 1.0777529692427679e-08, | |
| "logits/chosen": 1.646925687789917, | |
| "logits/rejected": 2.3574109077453613, | |
| "logps/chosen": -405.37457275390625, | |
| "logps/rejected": -485.71990966796875, | |
| "loss": 0.5398, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -2.4802286624908447, | |
| "rewards/margins": 0.8511859774589539, | |
| "rewards/rejected": -3.3314144611358643, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.9231993633107839, | |
| "grad_norm": 18.707936215451618, | |
| "learning_rate": 8.851477564560061e-09, | |
| "logits/chosen": 1.6634693145751953, | |
| "logits/rejected": 2.3943982124328613, | |
| "logps/chosen": -370.2140197753906, | |
| "logps/rejected": -464.6942443847656, | |
| "loss": 0.5257, | |
| "rewards/accuracies": 0.7250000238418579, | |
| "rewards/chosen": -2.3133978843688965, | |
| "rewards/margins": 0.9280908703804016, | |
| "rewards/rejected": -3.241488218307495, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.931157978511739, | |
| "grad_norm": 20.648180333245318, | |
| "learning_rate": 7.111805515081531e-09, | |
| "logits/chosen": 2.0850751399993896, | |
| "logits/rejected": 2.890317440032959, | |
| "logps/chosen": -375.6150207519531, | |
| "logps/rejected": -469.1720275878906, | |
| "loss": 0.5335, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -2.287146806716919, | |
| "rewards/margins": 0.9208979606628418, | |
| "rewards/rejected": -3.2080445289611816, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.939116593712694, | |
| "grad_norm": 18.214755371193483, | |
| "learning_rate": 5.559858110443016e-09, | |
| "logits/chosen": 1.984487533569336, | |
| "logits/rejected": 2.5453860759735107, | |
| "logps/chosen": -384.75177001953125, | |
| "logps/rejected": -463.731689453125, | |
| "loss": 0.5315, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": -2.390475034713745, | |
| "rewards/margins": 0.7526242136955261, | |
| "rewards/rejected": -3.143099308013916, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.947075208913649, | |
| "grad_norm": 19.352322603158484, | |
| "learning_rate": 4.196834827531276e-09, | |
| "logits/chosen": 1.8608672618865967, | |
| "logits/rejected": 2.2748332023620605, | |
| "logps/chosen": -398.26397705078125, | |
| "logps/rejected": -469.12542724609375, | |
| "loss": 0.5555, | |
| "rewards/accuracies": 0.668749988079071, | |
| "rewards/chosen": -2.4501779079437256, | |
| "rewards/margins": 0.6367470026016235, | |
| "rewards/rejected": -3.0869250297546387, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.955033824114604, | |
| "grad_norm": 22.98572661304592, | |
| "learning_rate": 3.023789126611137e-09, | |
| "logits/chosen": 1.9012830257415771, | |
| "logits/rejected": 2.2817015647888184, | |
| "logps/chosen": -402.8839416503906, | |
| "logps/rejected": -466.7554626464844, | |
| "loss": 0.5394, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -2.605943202972412, | |
| "rewards/margins": 0.6437206864356995, | |
| "rewards/rejected": -3.249663829803467, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.955033824114604, | |
| "eval_logits/chosen": 1.891152024269104, | |
| "eval_logits/rejected": 2.4846954345703125, | |
| "eval_logps/chosen": -397.9764404296875, | |
| "eval_logps/rejected": -485.8160705566406, | |
| "eval_loss": 0.5341334342956543, | |
| "eval_rewards/accuracies": 0.72947758436203, | |
| "eval_rewards/chosen": -2.5107264518737793, | |
| "eval_rewards/margins": 0.8168463706970215, | |
| "eval_rewards/rejected": -3.327572822570801, | |
| "eval_runtime": 349.0972, | |
| "eval_samples_per_second": 24.497, | |
| "eval_steps_per_second": 0.384, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.9629924393155591, | |
| "grad_norm": 20.459199823597086, | |
| "learning_rate": 2.041627637121929e-09, | |
| "logits/chosen": 2.0498170852661133, | |
| "logits/rejected": 2.8115336894989014, | |
| "logps/chosen": -374.2912292480469, | |
| "logps/rejected": -481.9027404785156, | |
| "loss": 0.5073, | |
| "rewards/accuracies": 0.793749988079071, | |
| "rewards/chosen": -2.3598573207855225, | |
| "rewards/margins": 1.0655521154403687, | |
| "rewards/rejected": -3.4254093170166016, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.9709510545165141, | |
| "grad_norm": 27.51193921402863, | |
| "learning_rate": 1.2511094569571668e-09, | |
| "logits/chosen": 1.997765302658081, | |
| "logits/rejected": 2.4746177196502686, | |
| "logps/chosen": -394.349365234375, | |
| "logps/rejected": -496.71588134765625, | |
| "loss": 0.5213, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": -2.551574468612671, | |
| "rewards/margins": 0.9096673727035522, | |
| "rewards/rejected": -3.4612419605255127, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.9789096697174692, | |
| "grad_norm": 21.766618365029238, | |
| "learning_rate": 6.528455657691112e-10, | |
| "logits/chosen": 1.7345082759857178, | |
| "logits/rejected": 2.2918901443481445, | |
| "logps/chosen": -404.74481201171875, | |
| "logps/rejected": -502.8517150878906, | |
| "loss": 0.535, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": -2.441373825073242, | |
| "rewards/margins": 0.877045750617981, | |
| "rewards/rejected": -3.3184192180633545, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.9868682849184242, | |
| "grad_norm": 23.710802357522613, | |
| "learning_rate": 2.4729835275189016e-10, | |
| "logits/chosen": 1.854836106300354, | |
| "logits/rejected": 2.660703420639038, | |
| "logps/chosen": -402.3847961425781, | |
| "logps/rejected": -474.1854553222656, | |
| "loss": 0.5461, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": -2.477180004119873, | |
| "rewards/margins": 0.7909337282180786, | |
| "rewards/rejected": -3.268113613128662, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.9948269001193792, | |
| "grad_norm": 20.55632802983822, | |
| "learning_rate": 3.478125926756337e-11, | |
| "logits/chosen": 2.092129945755005, | |
| "logits/rejected": 2.7219738960266113, | |
| "logps/chosen": -392.1388854980469, | |
| "logps/rejected": -490.11273193359375, | |
| "loss": 0.5228, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": -2.4716639518737793, | |
| "rewards/margins": 0.9531086683273315, | |
| "rewards/rejected": -3.4247727394104004, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.9996020692399522, | |
| "step": 1256, | |
| "total_flos": 0.0, | |
| "train_loss": 0.5626794682566527, | |
| "train_runtime": 30362.0274, | |
| "train_samples_per_second": 5.296, | |
| "train_steps_per_second": 0.041 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1256, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |