| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9981298423724285, | |
| "eval_steps": 400, | |
| "global_step": 467, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0021373230029388193, | |
| "grad_norm": 42.099143078937416, | |
| "learning_rate": 1.0638297872340425e-08, | |
| "logits/chosen": 2.2472424507141113, | |
| "logits/rejected": 2.264739513397217, | |
| "logps/chosen": -0.8019136786460876, | |
| "logps/rejected": -0.7812027335166931, | |
| "loss": 1.7463, | |
| "rewards/accuracies": 0.4375, | |
| "rewards/chosen": -2.004784345626831, | |
| "rewards/margins": -0.05177761986851692, | |
| "rewards/rejected": -1.953006625175476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010686615014694095, | |
| "grad_norm": 43.49437439863032, | |
| "learning_rate": 5.3191489361702123e-08, | |
| "logits/chosen": 2.1162009239196777, | |
| "logits/rejected": 2.0480892658233643, | |
| "logps/chosen": -1.0361735820770264, | |
| "logps/rejected": -1.1913045644760132, | |
| "loss": 1.9184, | |
| "rewards/accuracies": 0.453125, | |
| "rewards/chosen": -2.5904340744018555, | |
| "rewards/margins": 0.38782745599746704, | |
| "rewards/rejected": -2.9782614707946777, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02137323002938819, | |
| "grad_norm": 73.58193785863429, | |
| "learning_rate": 1.0638297872340425e-07, | |
| "logits/chosen": 2.0012879371643066, | |
| "logits/rejected": 1.9172722101211548, | |
| "logps/chosen": -1.5639755725860596, | |
| "logps/rejected": -1.5803353786468506, | |
| "loss": 1.9077, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -3.9099388122558594, | |
| "rewards/margins": 0.04089919477701187, | |
| "rewards/rejected": -3.950838088989258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03205984504408229, | |
| "grad_norm": 18.887588182169267, | |
| "learning_rate": 1.5957446808510638e-07, | |
| "logits/chosen": 1.9121309518814087, | |
| "logits/rejected": 1.8687114715576172, | |
| "logps/chosen": -1.1899975538253784, | |
| "logps/rejected": -1.2847260236740112, | |
| "loss": 1.832, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.974993944168091, | |
| "rewards/margins": 0.2368215024471283, | |
| "rewards/rejected": -3.211815357208252, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04274646005877638, | |
| "grad_norm": 8.819209234657059, | |
| "learning_rate": 2.127659574468085e-07, | |
| "logits/chosen": 1.8210818767547607, | |
| "logits/rejected": 1.8469772338867188, | |
| "logps/chosen": -1.21903657913208, | |
| "logps/rejected": -1.7520463466644287, | |
| "loss": 1.7601, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -3.0475919246673584, | |
| "rewards/margins": 1.3325239419937134, | |
| "rewards/rejected": -4.380115509033203, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.053433075073470476, | |
| "grad_norm": 33.18790384628351, | |
| "learning_rate": 2.659574468085106e-07, | |
| "logits/chosen": 2.0562968254089355, | |
| "logits/rejected": 2.0691914558410645, | |
| "logps/chosen": -1.0988093614578247, | |
| "logps/rejected": -1.1313331127166748, | |
| "loss": 1.815, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.747023344039917, | |
| "rewards/margins": 0.08130944520235062, | |
| "rewards/rejected": -2.8283333778381348, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06411969008816458, | |
| "grad_norm": 35.16962019463958, | |
| "learning_rate": 3.1914893617021275e-07, | |
| "logits/chosen": 1.9061098098754883, | |
| "logits/rejected": 1.9218835830688477, | |
| "logps/chosen": -1.2370525598526, | |
| "logps/rejected": -1.4245789051055908, | |
| "loss": 1.6802, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -3.0926311016082764, | |
| "rewards/margins": 0.46881628036499023, | |
| "rewards/rejected": -3.5614471435546875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07480630510285867, | |
| "grad_norm": 44.11653715682163, | |
| "learning_rate": 3.7234042553191484e-07, | |
| "logits/chosen": 1.9321657419204712, | |
| "logits/rejected": 1.955640435218811, | |
| "logps/chosen": -1.344245433807373, | |
| "logps/rejected": -1.36150062084198, | |
| "loss": 1.8113, | |
| "rewards/accuracies": 0.42500001192092896, | |
| "rewards/chosen": -3.3606135845184326, | |
| "rewards/margins": 0.0431380569934845, | |
| "rewards/rejected": -3.4037513732910156, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08549292011755276, | |
| "grad_norm": 36.76549905569564, | |
| "learning_rate": 4.25531914893617e-07, | |
| "logits/chosen": 1.8915932178497314, | |
| "logits/rejected": 1.9206931591033936, | |
| "logps/chosen": -1.2968499660491943, | |
| "logps/rejected": -1.3007665872573853, | |
| "loss": 1.8425, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -3.2421250343322754, | |
| "rewards/margins": 0.009791326709091663, | |
| "rewards/rejected": -3.2519161701202393, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09617953513224686, | |
| "grad_norm": 17.026888436798433, | |
| "learning_rate": 4.787234042553192e-07, | |
| "logits/chosen": 1.8335082530975342, | |
| "logits/rejected": 1.803972601890564, | |
| "logps/chosen": -1.1560873985290527, | |
| "logps/rejected": -1.391876459121704, | |
| "loss": 1.748, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.8902182579040527, | |
| "rewards/margins": 0.5894726514816284, | |
| "rewards/rejected": -3.4796910285949707, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10686615014694095, | |
| "grad_norm": 12.410804374401861, | |
| "learning_rate": 4.999370587356267e-07, | |
| "logits/chosen": 1.864829659461975, | |
| "logits/rejected": 1.8258002996444702, | |
| "logps/chosen": -1.0499851703643799, | |
| "logps/rejected": -1.454998254776001, | |
| "loss": 1.5838, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.6249632835388184, | |
| "rewards/margins": 1.0125324726104736, | |
| "rewards/rejected": -3.637495517730713, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11755276516163506, | |
| "grad_norm": 16.97890172462393, | |
| "learning_rate": 4.995525324419337e-07, | |
| "logits/chosen": 1.8395353555679321, | |
| "logits/rejected": 1.8361022472381592, | |
| "logps/chosen": -0.9045565724372864, | |
| "logps/rejected": -1.1536071300506592, | |
| "loss": 1.6796, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.2613916397094727, | |
| "rewards/margins": 0.6226258873939514, | |
| "rewards/rejected": -2.8840174674987793, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12823938017632916, | |
| "grad_norm": 18.13814698710649, | |
| "learning_rate": 4.988189843662815e-07, | |
| "logits/chosen": 1.9378535747528076, | |
| "logits/rejected": 1.9659252166748047, | |
| "logps/chosen": -1.1384503841400146, | |
| "logps/rejected": -1.0124545097351074, | |
| "loss": 1.7608, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.846126079559326, | |
| "rewards/margins": -0.3149900436401367, | |
| "rewards/rejected": -2.5311360359191895, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13892599519102325, | |
| "grad_norm": 31.166552691677705, | |
| "learning_rate": 4.977374404419837e-07, | |
| "logits/chosen": 2.1393017768859863, | |
| "logits/rejected": 2.103208303451538, | |
| "logps/chosen": -0.8744574785232544, | |
| "logps/rejected": -0.9523324966430664, | |
| "loss": 1.6552, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -2.186143636703491, | |
| "rewards/margins": 0.19468756020069122, | |
| "rewards/rejected": -2.380831241607666, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.14961261020571734, | |
| "grad_norm": 52.728695245981314, | |
| "learning_rate": 4.963094133060148e-07, | |
| "logits/chosen": 2.0067527294158936, | |
| "logits/rejected": 1.9597012996673584, | |
| "logps/chosen": -0.9174124598503113, | |
| "logps/rejected": -1.1131672859191895, | |
| "loss": 1.7212, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.2935314178466797, | |
| "rewards/margins": 0.4893869459629059, | |
| "rewards/rejected": -2.7829184532165527, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.16029922522041143, | |
| "grad_norm": 46.624386507512185, | |
| "learning_rate": 4.945369001834514e-07, | |
| "logits/chosen": 1.8767681121826172, | |
| "logits/rejected": 1.8939720392227173, | |
| "logps/chosen": -0.9977117776870728, | |
| "logps/rejected": -1.1487284898757935, | |
| "loss": 1.6147, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -2.494279384613037, | |
| "rewards/margins": 0.3775419294834137, | |
| "rewards/rejected": -2.8718209266662598, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.17098584023510552, | |
| "grad_norm": 13.45137638802328, | |
| "learning_rate": 4.924223800941717e-07, | |
| "logits/chosen": 1.912676453590393, | |
| "logits/rejected": 1.8263626098632812, | |
| "logps/chosen": -0.9859241247177124, | |
| "logps/rejected": -1.0560874938964844, | |
| "loss": 1.651, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -2.464810609817505, | |
| "rewards/margins": 0.17540840804576874, | |
| "rewards/rejected": -2.640218734741211, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.18167245524979964, | |
| "grad_norm": 23.876540575284714, | |
| "learning_rate": 4.899688103857222e-07, | |
| "logits/chosen": 1.9252907037734985, | |
| "logits/rejected": 1.9396631717681885, | |
| "logps/chosen": -0.9312021136283875, | |
| "logps/rejected": -1.1102412939071655, | |
| "loss": 1.618, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.328005313873291, | |
| "rewards/margins": 0.44759804010391235, | |
| "rewards/rejected": -2.7756032943725586, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.19235907026449373, | |
| "grad_norm": 7.705041238913054, | |
| "learning_rate": 4.871796225971999e-07, | |
| "logits/chosen": 1.9238191843032837, | |
| "logits/rejected": 1.8918044567108154, | |
| "logps/chosen": -0.9711843729019165, | |
| "logps/rejected": -1.096145749092102, | |
| "loss": 1.6624, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.4279608726501465, | |
| "rewards/margins": 0.3124033510684967, | |
| "rewards/rejected": -2.7403643131256104, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.20304568527918782, | |
| "grad_norm": 16.98405162222745, | |
| "learning_rate": 4.840587176599343e-07, | |
| "logits/chosen": 2.0161519050598145, | |
| "logits/rejected": 2.037721872329712, | |
| "logps/chosen": -0.9618253707885742, | |
| "logps/rejected": -1.1678836345672607, | |
| "loss": 1.6553, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -2.4045631885528564, | |
| "rewards/margins": 0.5151457786560059, | |
| "rewards/rejected": -2.9197089672088623, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2137323002938819, | |
| "grad_norm": 26.59166513674174, | |
| "learning_rate": 4.806104604416823e-07, | |
| "logits/chosen": 1.9551931619644165, | |
| "logits/rejected": 1.9663063287734985, | |
| "logps/chosen": -0.9686329960823059, | |
| "logps/rejected": -0.964672863483429, | |
| "loss": 1.6952, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -2.4215824604034424, | |
| "rewards/margins": -0.009900185279548168, | |
| "rewards/rejected": -2.41168212890625, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.224418915308576, | |
| "grad_norm": 22.597015867331866, | |
| "learning_rate": 4.768396736419662e-07, | |
| "logits/chosen": 2.0987541675567627, | |
| "logits/rejected": 2.1704182624816895, | |
| "logps/chosen": -0.8102301359176636, | |
| "logps/rejected": -1.0246448516845703, | |
| "loss": 1.6353, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.0255753993988037, | |
| "rewards/margins": 0.5360367894172668, | |
| "rewards/rejected": -2.561612367630005, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2351055303232701, | |
| "grad_norm": 7.710202530561847, | |
| "learning_rate": 4.7275163104709194e-07, | |
| "logits/chosen": 1.8211323022842407, | |
| "logits/rejected": 1.8467600345611572, | |
| "logps/chosen": -0.8923318982124329, | |
| "logps/rejected": -0.9886472821235657, | |
| "loss": 1.6826, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -2.2308297157287598, | |
| "rewards/margins": 0.24078825116157532, | |
| "rewards/rejected": -2.4716179370880127, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2457921453379642, | |
| "grad_norm": 9.211974257959199, | |
| "learning_rate": 4.683520501542824e-07, | |
| "logits/chosen": 1.822178840637207, | |
| "logits/rejected": 1.8460540771484375, | |
| "logps/chosen": -0.937783420085907, | |
| "logps/rejected": -0.9862428903579712, | |
| "loss": 1.6087, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -2.34445858001709, | |
| "rewards/margins": 0.12114912271499634, | |
| "rewards/rejected": -2.4656076431274414, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2564787603526583, | |
| "grad_norm": 17.97332526477704, | |
| "learning_rate": 4.636470841752404e-07, | |
| "logits/chosen": 1.9925601482391357, | |
| "logits/rejected": 2.0132079124450684, | |
| "logps/chosen": -0.8938210606575012, | |
| "logps/rejected": -0.9105901718139648, | |
| "loss": 1.6647, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -2.2345528602600098, | |
| "rewards/margins": 0.04192250221967697, | |
| "rewards/rejected": -2.276475429534912, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2671653753673524, | |
| "grad_norm": 21.241131663632817, | |
| "learning_rate": 4.5864331343032565e-07, | |
| "logits/chosen": 1.821298360824585, | |
| "logits/rejected": 1.8526639938354492, | |
| "logps/chosen": -0.9126847386360168, | |
| "logps/rejected": -1.0501748323440552, | |
| "loss": 1.7558, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -2.281712055206299, | |
| "rewards/margins": 0.3437250852584839, | |
| "rewards/rejected": -2.6254372596740723, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2778519903820465, | |
| "grad_norm": 18.947973877308787, | |
| "learning_rate": 4.533477361453819e-07, | |
| "logits/chosen": 2.178891658782959, | |
| "logits/rejected": 2.143307685852051, | |
| "logps/chosen": -0.9617658853530884, | |
| "logps/rejected": -1.223284125328064, | |
| "loss": 1.6892, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.404414653778076, | |
| "rewards/margins": 0.6537958383560181, | |
| "rewards/rejected": -3.0582103729248047, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2885386053967406, | |
| "grad_norm": 13.76012227966358, | |
| "learning_rate": 4.4776775866408533e-07, | |
| "logits/chosen": 1.8531124591827393, | |
| "logits/rejected": 1.8338654041290283, | |
| "logps/chosen": -0.8667293787002563, | |
| "logps/rejected": -0.9339718818664551, | |
| "loss": 1.658, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.166823148727417, | |
| "rewards/margins": 0.16810639202594757, | |
| "rewards/rejected": -2.334929943084717, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2992252204114347, | |
| "grad_norm": 12.832812020829884, | |
| "learning_rate": 4.4191118508950277e-07, | |
| "logits/chosen": 1.8038040399551392, | |
| "logits/rejected": 1.7551212310791016, | |
| "logps/chosen": -0.8944159746170044, | |
| "logps/rejected": -1.0033025741577148, | |
| "loss": 1.6771, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": -2.236039638519287, | |
| "rewards/margins": 0.2722164988517761, | |
| "rewards/rejected": -2.508256435394287, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.30991183542612877, | |
| "grad_norm": 9.09964498419542, | |
| "learning_rate": 4.357862063693485e-07, | |
| "logits/chosen": 2.027944564819336, | |
| "logits/rejected": 2.005831718444824, | |
| "logps/chosen": -0.8879717588424683, | |
| "logps/rejected": -0.9542590975761414, | |
| "loss": 1.7133, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.2199294567108154, | |
| "rewards/margins": 0.16571831703186035, | |
| "rewards/rejected": -2.3856475353240967, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.32059845044082286, | |
| "grad_norm": 24.685014270210495, | |
| "learning_rate": 4.294013888402029e-07, | |
| "logits/chosen": 2.138366222381592, | |
| "logits/rejected": 2.2007527351379395, | |
| "logps/chosen": -0.8750768899917603, | |
| "logps/rejected": -1.0953787565231323, | |
| "loss": 1.6625, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.187692165374756, | |
| "rewards/margins": 0.5507549047470093, | |
| "rewards/rejected": -2.7384471893310547, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.33128506545551695, | |
| "grad_norm": 24.61662782262514, | |
| "learning_rate": 4.227656622467162e-07, | |
| "logits/chosen": 1.911320686340332, | |
| "logits/rejected": 1.9191503524780273, | |
| "logps/chosen": -0.8599516153335571, | |
| "logps/rejected": -1.1553843021392822, | |
| "loss": 1.6495, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.149878978729248, | |
| "rewards/margins": 0.7385817766189575, | |
| "rewards/rejected": -2.888460874557495, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.34197168047021104, | |
| "grad_norm": 9.846236022517108, | |
| "learning_rate": 4.158883072525528e-07, | |
| "logits/chosen": 2.061549425125122, | |
| "logits/rejected": 2.0822834968566895, | |
| "logps/chosen": -0.8990328907966614, | |
| "logps/rejected": -0.985998809337616, | |
| "loss": 1.6348, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -2.247582197189331, | |
| "rewards/margins": 0.21741452813148499, | |
| "rewards/rejected": -2.464996814727783, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3526582954849052, | |
| "grad_norm": 19.106656482086205, | |
| "learning_rate": 4.087789424605447e-07, | |
| "logits/chosen": 2.265204906463623, | |
| "logits/rejected": 2.245617151260376, | |
| "logps/chosen": -0.818160355091095, | |
| "logps/rejected": -0.9623705744743347, | |
| "loss": 1.618, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -2.045400857925415, | |
| "rewards/margins": 0.3605257570743561, | |
| "rewards/rejected": -2.405926465988159, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.36334491049959927, | |
| "grad_norm": 14.919110153191296, | |
| "learning_rate": 4.0144751096020497e-07, | |
| "logits/chosen": 1.9928451776504517, | |
| "logits/rejected": 1.9697974920272827, | |
| "logps/chosen": -1.013695478439331, | |
| "logps/rejected": -1.2301123142242432, | |
| "loss": 1.5848, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.534238815307617, | |
| "rewards/margins": 0.5410416722297668, | |
| "rewards/rejected": -3.0752806663513184, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.37403152551429336, | |
| "grad_norm": 11.830869809507767, | |
| "learning_rate": 3.939042664214184e-07, | |
| "logits/chosen": 2.031292676925659, | |
| "logits/rejected": 2.066436767578125, | |
| "logps/chosen": -0.97381991147995, | |
| "logps/rejected": -1.2112761735916138, | |
| "loss": 1.5954, | |
| "rewards/accuracies": 0.6000000238418579, | |
| "rewards/chosen": -2.4345498085021973, | |
| "rewards/margins": 0.5936408638954163, | |
| "rewards/rejected": -3.0281906127929688, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.38471814052898745, | |
| "grad_norm": 14.628170167780459, | |
| "learning_rate": 3.8615975875375676e-07, | |
| "logits/chosen": 2.258387804031372, | |
| "logits/rejected": 2.3218982219696045, | |
| "logps/chosen": -1.0137016773223877, | |
| "logps/rejected": -1.1529831886291504, | |
| "loss": 1.6695, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -2.534254312515259, | |
| "rewards/margins": 0.3482036888599396, | |
| "rewards/rejected": -2.882457971572876, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.39540475554368154, | |
| "grad_norm": 16.49947715615614, | |
| "learning_rate": 3.7822481935147655e-07, | |
| "logits/chosen": 2.0560050010681152, | |
| "logits/rejected": 2.1167311668395996, | |
| "logps/chosen": -0.9939271211624146, | |
| "logps/rejected": -1.1564804315567017, | |
| "loss": 1.6754, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.4848177433013916, | |
| "rewards/margins": 0.40638333559036255, | |
| "rewards/rejected": -2.8912010192871094, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.40609137055837563, | |
| "grad_norm": 13.5081717360946, | |
| "learning_rate": 3.7011054594483443e-07, | |
| "logits/chosen": 2.1290013790130615, | |
| "logits/rejected": 2.223310947418213, | |
| "logps/chosen": -0.9123891592025757, | |
| "logps/rejected": -1.1287665367126465, | |
| "loss": 1.5831, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -2.280972957611084, | |
| "rewards/margins": 0.5409437417984009, | |
| "rewards/rejected": -2.8219165802001953, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4167779855730697, | |
| "grad_norm": 17.61863203205812, | |
| "learning_rate": 3.618282870789081e-07, | |
| "logits/chosen": 2.1478934288024902, | |
| "logits/rejected": 2.1439719200134277, | |
| "logps/chosen": -0.974346935749054, | |
| "logps/rejected": -1.1090627908706665, | |
| "loss": 1.64, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.4358673095703125, | |
| "rewards/margins": 0.33678966760635376, | |
| "rewards/rejected": -2.7726569175720215, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.4274646005877638, | |
| "grad_norm": 12.457201720784246, | |
| "learning_rate": 3.5338962624163016e-07, | |
| "logits/chosen": 2.2304863929748535, | |
| "logits/rejected": 2.2417056560516357, | |
| "logps/chosen": -0.9161917567253113, | |
| "logps/rejected": -1.0349229574203491, | |
| "loss": 1.672, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": -2.2904791831970215, | |
| "rewards/margins": 0.29682818055152893, | |
| "rewards/rejected": -2.5873074531555176, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4381512156024579, | |
| "grad_norm": 25.419906192801392, | |
| "learning_rate": 3.448063656632321e-07, | |
| "logits/chosen": 2.2168259620666504, | |
| "logits/rejected": 2.2494800090789795, | |
| "logps/chosen": -0.9495501518249512, | |
| "logps/rejected": -1.0588171482086182, | |
| "loss": 1.6462, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.373875379562378, | |
| "rewards/margins": 0.2731671929359436, | |
| "rewards/rejected": -2.647042751312256, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.448837830617152, | |
| "grad_norm": 31.43495532901771, | |
| "learning_rate": 3.360905098097587e-07, | |
| "logits/chosen": 2.0355324745178223, | |
| "logits/rejected": 2.0058634281158447, | |
| "logps/chosen": -0.9030116200447083, | |
| "logps/rejected": -1.100672960281372, | |
| "loss": 1.7332, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.2575290203094482, | |
| "rewards/margins": 0.49415332078933716, | |
| "rewards/rejected": -2.751682758331299, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.45952444563184613, | |
| "grad_norm": 9.866165199153304, | |
| "learning_rate": 3.272542485937368e-07, | |
| "logits/chosen": 2.188046932220459, | |
| "logits/rejected": 2.209195375442505, | |
| "logps/chosen": -0.8452509045600891, | |
| "logps/rejected": -0.9856406450271606, | |
| "loss": 1.6173, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.1131272315979004, | |
| "rewards/margins": 0.3509744107723236, | |
| "rewards/rejected": -2.464101791381836, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.4702110606465402, | |
| "grad_norm": 11.268271977292386, | |
| "learning_rate": 3.1830994032548e-07, | |
| "logits/chosen": 2.2558753490448, | |
| "logits/rejected": 2.271909475326538, | |
| "logps/chosen": -0.9621235728263855, | |
| "logps/rejected": -1.0470136404037476, | |
| "loss": 1.6623, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -2.405308961868286, | |
| "rewards/margins": 0.21222510933876038, | |
| "rewards/rejected": -2.6175341606140137, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.4808976756612343, | |
| "grad_norm": 8.220154130520008, | |
| "learning_rate": 3.0927009442887437e-07, | |
| "logits/chosen": 2.033316135406494, | |
| "logits/rejected": 2.0451745986938477, | |
| "logps/chosen": -0.9348015785217285, | |
| "logps/rejected": -0.9307538866996765, | |
| "loss": 1.7025, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.3370039463043213, | |
| "rewards/margins": -0.010119226761162281, | |
| "rewards/rejected": -2.3268847465515137, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.4915842906759284, | |
| "grad_norm": 8.761484125412297, | |
| "learning_rate": 3.001473539458182e-07, | |
| "logits/chosen": 2.039243221282959, | |
| "logits/rejected": 2.0847630500793457, | |
| "logps/chosen": -0.9077224731445312, | |
| "logps/rejected": -0.9697052240371704, | |
| "loss": 1.6369, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -2.269306182861328, | |
| "rewards/margins": 0.15495693683624268, | |
| "rewards/rejected": -2.4242632389068604, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5022709056906225, | |
| "grad_norm": 21.069821104434805, | |
| "learning_rate": 2.909544778537844e-07, | |
| "logits/chosen": 2.1515793800354004, | |
| "logits/rejected": 2.0550239086151123, | |
| "logps/chosen": -0.9554904699325562, | |
| "logps/rejected": -1.0575495958328247, | |
| "loss": 1.6471, | |
| "rewards/accuracies": 0.4625000059604645, | |
| "rewards/chosen": -2.3887264728546143, | |
| "rewards/margins": 0.2551475167274475, | |
| "rewards/rejected": -2.643873691558838, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.5129575207053166, | |
| "grad_norm": 18.45689011337618, | |
| "learning_rate": 2.817043232212371e-07, | |
| "logits/chosen": 2.3277316093444824, | |
| "logits/rejected": 2.359060287475586, | |
| "logps/chosen": -0.9175651669502258, | |
| "logps/rejected": -1.075629472732544, | |
| "loss": 1.5723, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.2939131259918213, | |
| "rewards/margins": 0.39516064524650574, | |
| "rewards/rejected": -2.6890735626220703, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5236441357200107, | |
| "grad_norm": 5.945491870174955, | |
| "learning_rate": 2.7240982722585837e-07, | |
| "logits/chosen": 2.2272980213165283, | |
| "logits/rejected": 2.216254472732544, | |
| "logps/chosen": -0.887627124786377, | |
| "logps/rejected": -1.0360788106918335, | |
| "loss": 1.6259, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.2190678119659424, | |
| "rewards/margins": 0.3711293637752533, | |
| "rewards/rejected": -2.5901970863342285, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.5343307507347048, | |
| "grad_norm": 10.042684286997996, | |
| "learning_rate": 2.63083989060736e-07, | |
| "logits/chosen": 2.162696361541748, | |
| "logits/rejected": 2.178349494934082, | |
| "logps/chosen": -0.9883350133895874, | |
| "logps/rejected": -1.1994340419769287, | |
| "loss": 1.6589, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -2.4708378314971924, | |
| "rewards/margins": 0.5277475118637085, | |
| "rewards/rejected": -2.9985852241516113, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5450173657493989, | |
| "grad_norm": 10.520900876521566, | |
| "learning_rate": 2.537398517538159e-07, | |
| "logits/chosen": 2.2908027172088623, | |
| "logits/rejected": 2.235353708267212, | |
| "logps/chosen": -0.9431841969490051, | |
| "logps/rejected": -1.015700101852417, | |
| "loss": 1.6741, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.3579602241516113, | |
| "rewards/margins": 0.18129023909568787, | |
| "rewards/rejected": -2.539250612258911, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.555703980764093, | |
| "grad_norm": 9.313778052567603, | |
| "learning_rate": 2.4439048392604877e-07, | |
| "logits/chosen": 2.1532225608825684, | |
| "logits/rejected": 2.2637267112731934, | |
| "logps/chosen": -0.9131342768669128, | |
| "logps/rejected": -1.2010549306869507, | |
| "loss": 1.5779, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": -2.2828357219696045, | |
| "rewards/margins": 0.7198014259338379, | |
| "rewards/rejected": -3.0026373863220215, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.566390595778787, | |
| "grad_norm": 17.127300405069718, | |
| "learning_rate": 2.3504896151374144e-07, | |
| "logits/chosen": 2.2980525493621826, | |
| "logits/rejected": 2.2274222373962402, | |
| "logps/chosen": -0.9766885042190552, | |
| "logps/rejected": -1.0872061252593994, | |
| "loss": 1.6741, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.4417214393615723, | |
| "rewards/margins": 0.2762938141822815, | |
| "rewards/rejected": -2.718015193939209, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.5770772107934812, | |
| "grad_norm": 14.096322545468484, | |
| "learning_rate": 2.2572834948067795e-07, | |
| "logits/chosen": 2.13866925239563, | |
| "logits/rejected": 2.09075665473938, | |
| "logps/chosen": -0.866176962852478, | |
| "logps/rejected": -1.0079139471054077, | |
| "loss": 1.6445, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -2.165442705154419, | |
| "rewards/margins": 0.3543422520160675, | |
| "rewards/rejected": -2.519784688949585, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5877638258081752, | |
| "grad_norm": 11.519350142557252, | |
| "learning_rate": 2.164416835455862e-07, | |
| "logits/chosen": 1.9599807262420654, | |
| "logits/rejected": 1.9166367053985596, | |
| "logps/chosen": -0.9016801714897156, | |
| "logps/rejected": -1.060001015663147, | |
| "loss": 1.6308, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.2542004585266113, | |
| "rewards/margins": 0.39580219984054565, | |
| "rewards/rejected": -2.6500024795532227, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5984504408228694, | |
| "grad_norm": 9.94425188158257, | |
| "learning_rate": 2.072019519505062e-07, | |
| "logits/chosen": 2.006683349609375, | |
| "logits/rejected": 1.9877275228500366, | |
| "logps/chosen": -0.9040509462356567, | |
| "logps/rejected": -1.0043412446975708, | |
| "loss": 1.6201, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.260127305984497, | |
| "rewards/margins": 0.2507258355617523, | |
| "rewards/rejected": -2.5108530521392822, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6091370558375635, | |
| "grad_norm": 17.126362799060438, | |
| "learning_rate": 1.980220772955602e-07, | |
| "logits/chosen": 2.040419816970825, | |
| "logits/rejected": 1.9795433282852173, | |
| "logps/chosen": -1.0711162090301514, | |
| "logps/rejected": -1.1054927110671997, | |
| "loss": 1.6696, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -2.677790641784668, | |
| "rewards/margins": 0.08594076335430145, | |
| "rewards/rejected": -2.7637314796447754, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.6198236708522575, | |
| "grad_norm": 13.492215975630849, | |
| "learning_rate": 1.8891489846552644e-07, | |
| "logits/chosen": 2.3427670001983643, | |
| "logits/rejected": 2.3189902305603027, | |
| "logps/chosen": -0.9356976747512817, | |
| "logps/rejected": -1.0561234951019287, | |
| "loss": 1.6313, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.3392443656921387, | |
| "rewards/margins": 0.30106478929519653, | |
| "rewards/rejected": -2.6403088569641113, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6305102858669517, | |
| "grad_norm": 6.893975837082491, | |
| "learning_rate": 1.7989315267349933e-07, | |
| "logits/chosen": 2.3545644283294678, | |
| "logits/rejected": 2.3726115226745605, | |
| "logps/chosen": -0.9937087893486023, | |
| "logps/rejected": -1.0849647521972656, | |
| "loss": 1.6816, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.484271764755249, | |
| "rewards/margins": 0.22813992202281952, | |
| "rewards/rejected": -2.712411642074585, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.6411969008816457, | |
| "grad_norm": 6.6767839699246405, | |
| "learning_rate": 1.7096945764674398e-07, | |
| "logits/chosen": 2.0134410858154297, | |
| "logits/rejected": 1.9672603607177734, | |
| "logps/chosen": -1.038081169128418, | |
| "logps/rejected": -1.0271114110946655, | |
| "loss": 1.6598, | |
| "rewards/accuracies": 0.4375, | |
| "rewards/chosen": -2.595202922821045, | |
| "rewards/margins": -0.027424562722444534, | |
| "rewards/rejected": -2.5677783489227295, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6518835158963399, | |
| "grad_norm": 8.402566753074327, | |
| "learning_rate": 1.621562939796643e-07, | |
| "logits/chosen": 2.099931240081787, | |
| "logits/rejected": 2.131023406982422, | |
| "logps/chosen": -0.9801462888717651, | |
| "logps/rejected": -1.1142746210098267, | |
| "loss": 1.6239, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -2.4503657817840576, | |
| "rewards/margins": 0.33532071113586426, | |
| "rewards/rejected": -2.785686492919922, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.6625701309110339, | |
| "grad_norm": 13.484008579562406, | |
| "learning_rate": 1.5346598767856345e-07, | |
| "logits/chosen": 2.3738818168640137, | |
| "logits/rejected": 2.2915918827056885, | |
| "logps/chosen": -0.9194884300231934, | |
| "logps/rejected": -1.1123372316360474, | |
| "loss": 1.6509, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -2.2987208366394043, | |
| "rewards/margins": 0.4821222722530365, | |
| "rewards/rejected": -2.7808432579040527, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.673256745925728, | |
| "grad_norm": 11.276062854222866, | |
| "learning_rate": 1.4491069292260866e-07, | |
| "logits/chosen": 2.0688905715942383, | |
| "logits/rejected": 2.0706334114074707, | |
| "logps/chosen": -0.9416360855102539, | |
| "logps/rejected": -0.9889582395553589, | |
| "loss": 1.6263, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -2.354090452194214, | |
| "rewards/margins": 0.11830528825521469, | |
| "rewards/rejected": -2.472395658493042, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.6839433609404221, | |
| "grad_norm": 12.406779732367644, | |
| "learning_rate": 1.365023750651133e-07, | |
| "logits/chosen": 2.029076337814331, | |
| "logits/rejected": 2.07525634765625, | |
| "logps/chosen": -0.8669158220291138, | |
| "logps/rejected": -1.1443169116973877, | |
| "loss": 1.5861, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -2.1672892570495605, | |
| "rewards/margins": 0.6935025453567505, | |
| "rewards/rejected": -2.8607916831970215, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6946299759551162, | |
| "grad_norm": 9.410463016483124, | |
| "learning_rate": 1.2825279389890818e-07, | |
| "logits/chosen": 2.2680742740631104, | |
| "logits/rejected": 2.2626852989196777, | |
| "logps/chosen": -0.9127257466316223, | |
| "logps/rejected": -1.036811113357544, | |
| "loss": 1.5807, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.2818140983581543, | |
| "rewards/margins": 0.31021344661712646, | |
| "rewards/rejected": -2.5920276641845703, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.7053165909698104, | |
| "grad_norm": 13.015902838409264, | |
| "learning_rate": 1.201734872092077e-07, | |
| "logits/chosen": 2.0204429626464844, | |
| "logits/rejected": 1.9889049530029297, | |
| "logps/chosen": -0.9624814987182617, | |
| "logps/rejected": -1.4148118495941162, | |
| "loss": 1.6247, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.4062037467956543, | |
| "rewards/margins": 1.130826473236084, | |
| "rewards/rejected": -3.537029981613159, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7160032059845044, | |
| "grad_norm": 10.457412577224535, | |
| "learning_rate": 1.1227575463697439e-07, | |
| "logits/chosen": 2.1002488136291504, | |
| "logits/rejected": 2.1578989028930664, | |
| "logps/chosen": -0.9219167828559875, | |
| "logps/rejected": -1.0541021823883057, | |
| "loss": 1.6126, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.3047919273376465, | |
| "rewards/margins": 0.33046382665634155, | |
| "rewards/rejected": -2.635255813598633, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.7266898209991985, | |
| "grad_norm": 13.23573306912224, | |
| "learning_rate": 1.0457064187534861e-07, | |
| "logits/chosen": 2.2117228507995605, | |
| "logits/rejected": 2.291081666946411, | |
| "logps/chosen": -0.8333222270011902, | |
| "logps/rejected": -1.0662933588027954, | |
| "loss": 1.611, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.083305597305298, | |
| "rewards/margins": 0.5824280977249146, | |
| "rewards/rejected": -2.665733575820923, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7373764360138926, | |
| "grad_norm": 7.317920448430426, | |
| "learning_rate": 9.706892522124838e-08, | |
| "logits/chosen": 2.1216635704040527, | |
| "logits/rejected": 2.178093194961548, | |
| "logps/chosen": -1.0588462352752686, | |
| "logps/rejected": -1.0970056056976318, | |
| "loss": 1.5811, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.647115468978882, | |
| "rewards/margins": 0.09539877623319626, | |
| "rewards/rejected": -2.742514133453369, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.7480630510285867, | |
| "grad_norm": 14.193162676817792, | |
| "learning_rate": 8.978109650374396e-08, | |
| "logits/chosen": 2.2546029090881348, | |
| "logits/rejected": 2.294689893722534, | |
| "logps/chosen": -0.9023507833480835, | |
| "logps/rejected": -1.162570595741272, | |
| "loss": 1.6171, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -2.2558767795562744, | |
| "rewards/margins": 0.6505497694015503, | |
| "rewards/rejected": -2.9064266681671143, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7587496660432808, | |
| "grad_norm": 12.52863776377329, | |
| "learning_rate": 8.271734841028552e-08, | |
| "logits/chosen": 2.245272636413574, | |
| "logits/rejected": 2.2576751708984375, | |
| "logps/chosen": -1.005053997039795, | |
| "logps/rejected": -1.0007752180099487, | |
| "loss": 1.6536, | |
| "rewards/accuracies": 0.4749999940395355, | |
| "rewards/chosen": -2.512634754180908, | |
| "rewards/margins": -0.010696577839553356, | |
| "rewards/rejected": -2.5019383430480957, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.7694362810579749, | |
| "grad_norm": 10.369189534811127, | |
| "learning_rate": 7.588756023130833e-08, | |
| "logits/chosen": 2.318972587585449, | |
| "logits/rejected": 2.281419515609741, | |
| "logps/chosen": -1.0578750371932983, | |
| "logps/rejected": -1.3604905605316162, | |
| "loss": 1.6205, | |
| "rewards/accuracies": 0.625, | |
| "rewards/chosen": -2.6446874141693115, | |
| "rewards/margins": 0.7565388679504395, | |
| "rewards/rejected": -3.40122652053833, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7801228960726689, | |
| "grad_norm": 6.075365195709392, | |
| "learning_rate": 6.930128404315214e-08, | |
| "logits/chosen": 2.0289673805236816, | |
| "logits/rejected": 2.0680978298187256, | |
| "logps/chosen": -0.976359486579895, | |
| "logps/rejected": -1.0074145793914795, | |
| "loss": 1.6246, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.440898895263672, | |
| "rewards/margins": 0.07763750851154327, | |
| "rewards/rejected": -2.518536329269409, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.7908095110873631, | |
| "grad_norm": 16.214823251732284, | |
| "learning_rate": 6.296773134861824e-08, | |
| "logits/chosen": 2.2002553939819336, | |
| "logits/rejected": 2.2343714237213135, | |
| "logps/chosen": -0.9719416499137878, | |
| "logps/rejected": -1.023166537284851, | |
| "loss": 1.6894, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -2.429853916168213, | |
| "rewards/margins": 0.12806224822998047, | |
| "rewards/rejected": -2.5579161643981934, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8014961261020572, | |
| "grad_norm": 10.840080143128308, | |
| "learning_rate": 5.6895760193850145e-08, | |
| "logits/chosen": 2.1092734336853027, | |
| "logits/rejected": 2.168839693069458, | |
| "logps/chosen": -1.0623986721038818, | |
| "logps/rejected": -1.1893246173858643, | |
| "loss": 1.6248, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": -2.6559970378875732, | |
| "rewards/margins": 0.31731492280960083, | |
| "rewards/rejected": -2.9733119010925293, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.8121827411167513, | |
| "grad_norm": 14.986128731201607, | |
| "learning_rate": 5.109386277955477e-08, | |
| "logits/chosen": 2.400944232940674, | |
| "logits/rejected": 2.424126625061035, | |
| "logps/chosen": -1.0006974935531616, | |
| "logps/rejected": -1.0918558835983276, | |
| "loss": 1.6152, | |
| "rewards/accuracies": 0.48750001192092896, | |
| "rewards/chosen": -2.501743793487549, | |
| "rewards/margins": 0.22789612412452698, | |
| "rewards/rejected": -2.729639768600464, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8228693561314454, | |
| "grad_norm": 11.04509407630343, | |
| "learning_rate": 4.557015358389216e-08, | |
| "logits/chosen": 2.2161147594451904, | |
| "logits/rejected": 2.255049705505371, | |
| "logps/chosen": -0.9763911962509155, | |
| "logps/rejected": -1.2085295915603638, | |
| "loss": 1.6246, | |
| "rewards/accuracies": 0.5625, | |
| "rewards/chosen": -2.4409780502319336, | |
| "rewards/margins": 0.5803458094596863, | |
| "rewards/rejected": -3.0213241577148438, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.8335559711461394, | |
| "grad_norm": 17.08993723906078, | |
| "learning_rate": 4.0332358013644015e-08, | |
| "logits/chosen": 2.3219351768493652, | |
| "logits/rejected": 2.316385507583618, | |
| "logps/chosen": -0.8949235081672668, | |
| "logps/rejected": -1.2672293186187744, | |
| "loss": 1.6161, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -2.2373085021972656, | |
| "rewards/margins": 0.9307647943496704, | |
| "rewards/rejected": -3.1680736541748047, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8442425861608336, | |
| "grad_norm": 7.486937950213667, | |
| "learning_rate": 3.538780159953347e-08, | |
| "logits/chosen": 2.171618700027466, | |
| "logits/rejected": 2.133547067642212, | |
| "logps/chosen": -0.913979172706604, | |
| "logps/rejected": -1.011819839477539, | |
| "loss": 1.6306, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.284947633743286, | |
| "rewards/margins": 0.24460192024707794, | |
| "rewards/rejected": -2.5295493602752686, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.8549292011755276, | |
| "grad_norm": 12.731226626352624, | |
| "learning_rate": 3.074339975080836e-08, | |
| "logits/chosen": 2.207425594329834, | |
| "logits/rejected": 2.2549290657043457, | |
| "logps/chosen": -1.030874490737915, | |
| "logps/rejected": -1.2776422500610352, | |
| "loss": 1.6417, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -2.577186107635498, | |
| "rewards/margins": 0.6169193983078003, | |
| "rewards/rejected": -3.194105863571167, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8549292011755276, | |
| "eval_logits/chosen": 2.0145604610443115, | |
| "eval_logits/rejected": 2.0190441608428955, | |
| "eval_logps/chosen": -0.8955881595611572, | |
| "eval_logps/rejected": -1.058284044265747, | |
| "eval_loss": 1.6235809326171875, | |
| "eval_rewards/accuracies": 0.6209677457809448, | |
| "eval_rewards/chosen": -2.2389702796936035, | |
| "eval_rewards/margins": 0.40673962235450745, | |
| "eval_rewards/rejected": -2.645709753036499, | |
| "eval_runtime": 44.336, | |
| "eval_samples_per_second": 44.23, | |
| "eval_steps_per_second": 1.398, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8656158161902218, | |
| "grad_norm": 10.867554141726604, | |
| "learning_rate": 2.6405648083415833e-08, | |
| "logits/chosen": 2.151744842529297, | |
| "logits/rejected": 2.200650691986084, | |
| "logps/chosen": -0.980237603187561, | |
| "logps/rejected": -1.0543644428253174, | |
| "loss": 1.7482, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.450594186782837, | |
| "rewards/margins": 0.18531720340251923, | |
| "rewards/rejected": -2.635911226272583, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.8763024312049158, | |
| "grad_norm": 8.929503879536968, | |
| "learning_rate": 2.2380613335296033e-08, | |
| "logits/chosen": 2.186063289642334, | |
| "logits/rejected": 2.2187790870666504, | |
| "logps/chosen": -0.9089058041572571, | |
| "logps/rejected": -1.0911632776260376, | |
| "loss": 1.5847, | |
| "rewards/accuracies": 0.612500011920929, | |
| "rewards/chosen": -2.272264242172241, | |
| "rewards/margins": 0.45564380288124084, | |
| "rewards/rejected": -2.727908134460449, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.88698904621961, | |
| "grad_norm": 7.217288770833436, | |
| "learning_rate": 1.8673924881500823e-08, | |
| "logits/chosen": 2.505709409713745, | |
| "logits/rejected": 2.470183849334717, | |
| "logps/chosen": -0.8387972116470337, | |
| "logps/rejected": -1.0221149921417236, | |
| "loss": 1.6029, | |
| "rewards/accuracies": 0.5, | |
| "rewards/chosen": -2.0969929695129395, | |
| "rewards/margins": 0.45829471945762634, | |
| "rewards/rejected": -2.5552875995635986, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.897675661234304, | |
| "grad_norm": 8.941360081202905, | |
| "learning_rate": 1.5290766861003475e-08, | |
| "logits/chosen": 2.191061019897461, | |
| "logits/rejected": 2.173102378845215, | |
| "logps/chosen": -0.9252120852470398, | |
| "logps/rejected": -1.03108811378479, | |
| "loss": 1.6027, | |
| "rewards/accuracies": 0.550000011920929, | |
| "rewards/chosen": -2.31303071975708, | |
| "rewards/margins": 0.2646896243095398, | |
| "rewards/rejected": -2.5777201652526855, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9083622762489981, | |
| "grad_norm": 14.568857335011407, | |
| "learning_rate": 1.2235870926211616e-08, | |
| "logits/chosen": 2.0643928050994873, | |
| "logits/rejected": 2.0896859169006348, | |
| "logps/chosen": -0.9114057421684265, | |
| "logps/rejected": -1.0619531869888306, | |
| "loss": 1.6274, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -2.2785143852233887, | |
| "rewards/margins": 0.37636831402778625, | |
| "rewards/rejected": -2.6548826694488525, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.9190488912636923, | |
| "grad_norm": 12.761707033542287, | |
| "learning_rate": 9.513509625323518e-09, | |
| "logits/chosen": 2.1255576610565186, | |
| "logits/rejected": 2.181107759475708, | |
| "logps/chosen": -0.85987389087677, | |
| "logps/rejected": -1.0060930252075195, | |
| "loss": 1.5736, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": -2.149684429168701, | |
| "rewards/margins": 0.3655479848384857, | |
| "rewards/rejected": -2.515232563018799, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9297355062783863, | |
| "grad_norm": 16.68383920608418, | |
| "learning_rate": 7.127490426783123e-09, | |
| "logits/chosen": 2.2676453590393066, | |
| "logits/rejected": 2.224987506866455, | |
| "logps/chosen": -0.9531320333480835, | |
| "logps/rejected": -1.1150267124176025, | |
| "loss": 1.6026, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.3828301429748535, | |
| "rewards/margins": 0.4047369956970215, | |
| "rewards/rejected": -2.787567138671875, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.9404221212930804, | |
| "grad_norm": 11.429700658399854, | |
| "learning_rate": 5.08115039419113e-09, | |
| "logits/chosen": 2.2096710205078125, | |
| "logits/rejected": 2.2330925464630127, | |
| "logps/chosen": -0.8609305620193481, | |
| "logps/rejected": -0.9673101305961609, | |
| "loss": 1.5978, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": -2.1523263454437256, | |
| "rewards/margins": 0.265949010848999, | |
| "rewards/rejected": -2.4182753562927246, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9511087363077745, | |
| "grad_norm": 7.426544303240404, | |
| "learning_rate": 3.3773515191196646e-09, | |
| "logits/chosen": 2.20963716506958, | |
| "logits/rejected": 2.201622724533081, | |
| "logps/chosen": -0.8218202590942383, | |
| "logps/rejected": -0.8649258613586426, | |
| "loss": 1.6414, | |
| "rewards/accuracies": 0.512499988079071, | |
| "rewards/chosen": -2.0545506477355957, | |
| "rewards/margins": 0.10776408016681671, | |
| "rewards/rejected": -2.1623148918151855, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.9617953513224686, | |
| "grad_norm": 12.349821491663924, | |
| "learning_rate": 2.0184767183584474e-09, | |
| "logits/chosen": 2.325861930847168, | |
| "logits/rejected": 2.2664694786071777, | |
| "logps/chosen": -0.9952027201652527, | |
| "logps/rejected": -1.3025867938995361, | |
| "loss": 1.6015, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -2.488007068634033, | |
| "rewards/margins": 0.7684597969055176, | |
| "rewards/rejected": -3.2564666271209717, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9724819663371627, | |
| "grad_norm": 10.41544260252462, | |
| "learning_rate": 1.0064265011902328e-09, | |
| "logits/chosen": 2.0219030380249023, | |
| "logits/rejected": 1.9868360757827759, | |
| "logps/chosen": -1.0134050846099854, | |
| "logps/rejected": -1.0333858728408813, | |
| "loss": 1.6377, | |
| "rewards/accuracies": 0.4000000059604645, | |
| "rewards/chosen": -2.533512592315674, | |
| "rewards/margins": 0.049951858818531036, | |
| "rewards/rejected": -2.5834643840789795, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.9831685813518568, | |
| "grad_norm": 9.044209064035641, | |
| "learning_rate": 3.4261631135654167e-10, | |
| "logits/chosen": 2.2376327514648438, | |
| "logits/rejected": 2.1572484970092773, | |
| "logps/chosen": -1.0239425897598267, | |
| "logps/rejected": -1.3165332078933716, | |
| "loss": 1.5875, | |
| "rewards/accuracies": 0.5375000238418579, | |
| "rewards/chosen": -2.559856414794922, | |
| "rewards/margins": 0.7314767241477966, | |
| "rewards/rejected": -3.291332960128784, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9938551963665508, | |
| "grad_norm": 11.3294414057108, | |
| "learning_rate": 2.797454743164174e-11, | |
| "logits/chosen": 2.186420202255249, | |
| "logits/rejected": 2.1705265045166016, | |
| "logps/chosen": -0.875818133354187, | |
| "logps/rejected": -1.0201952457427979, | |
| "loss": 1.5967, | |
| "rewards/accuracies": 0.5249999761581421, | |
| "rewards/chosen": -2.1895456314086914, | |
| "rewards/margins": 0.36094242334365845, | |
| "rewards/rejected": -2.550488233566284, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.9981298423724285, | |
| "step": 467, | |
| "total_flos": 0.0, | |
| "train_loss": 1.6566840494470372, | |
| "train_runtime": 5417.7619, | |
| "train_samples_per_second": 11.052, | |
| "train_steps_per_second": 0.086 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 467, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000000, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |