| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 368, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1359.2177158077461, | |
| "learning_rate": 2.702702702702703e-10, | |
| "logits/chosen": -1.3332719802856445, | |
| "logits/rejected": -1.246394395828247, | |
| "logps/chosen": -286.9539794921875, | |
| "logps/rejected": -263.3782958984375, | |
| "loss": 0.7007, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 1659.9667867776882, | |
| "learning_rate": 2.702702702702703e-09, | |
| "logits/chosen": -1.6176425218582153, | |
| "logits/rejected": -1.3966516256332397, | |
| "logps/chosen": -342.49456787109375, | |
| "logps/rejected": -294.5242614746094, | |
| "loss": 0.7618, | |
| "rewards/accuracies": 0.4340277910232544, | |
| "rewards/chosen": 0.040204986929893494, | |
| "rewards/margins": 0.027825627475976944, | |
| "rewards/rejected": 0.012379361316561699, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1365.2835589869765, | |
| "learning_rate": 5.405405405405406e-09, | |
| "logits/chosen": -1.4892847537994385, | |
| "logits/rejected": -1.311715006828308, | |
| "logps/chosen": -314.7313537597656, | |
| "logps/rejected": -279.33746337890625, | |
| "loss": 0.7414, | |
| "rewards/accuracies": 0.5406249761581421, | |
| "rewards/chosen": 0.03467293456196785, | |
| "rewards/margins": 0.06634848564863205, | |
| "rewards/rejected": -0.0316755548119545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1495.215254347967, | |
| "learning_rate": 8.108108108108109e-09, | |
| "logits/chosen": -1.5478875637054443, | |
| "logits/rejected": -1.3803514242172241, | |
| "logps/chosen": -324.8534240722656, | |
| "logps/rejected": -286.27276611328125, | |
| "loss": 0.7533, | |
| "rewards/accuracies": 0.5218750238418579, | |
| "rewards/chosen": 0.05265723541378975, | |
| "rewards/margins": 0.04645369574427605, | |
| "rewards/rejected": 0.006203538738191128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 1385.2297985942057, | |
| "learning_rate": 9.997973265157192e-09, | |
| "logits/chosen": -1.5357484817504883, | |
| "logits/rejected": -1.3583762645721436, | |
| "logps/chosen": -325.4037780761719, | |
| "logps/rejected": -285.64508056640625, | |
| "loss": 0.7565, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": -0.010429712943732738, | |
| "rewards/margins": -0.014903778210282326, | |
| "rewards/rejected": 0.0044740648008883, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 1517.4779086138956, | |
| "learning_rate": 9.961988113473708e-09, | |
| "logits/chosen": -1.5413590669631958, | |
| "logits/rejected": -1.3948113918304443, | |
| "logps/chosen": -337.04327392578125, | |
| "logps/rejected": -297.2876892089844, | |
| "loss": 0.7454, | |
| "rewards/accuracies": 0.47187501192092896, | |
| "rewards/chosen": -0.022386690601706505, | |
| "rewards/margins": -0.045912474393844604, | |
| "rewards/rejected": 0.0235257837921381, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 1317.1513962511742, | |
| "learning_rate": 9.881337335184878e-09, | |
| "logits/chosen": -1.5795971155166626, | |
| "logits/rejected": -1.43094801902771, | |
| "logps/chosen": -319.79681396484375, | |
| "logps/rejected": -285.0555725097656, | |
| "loss": 0.6982, | |
| "rewards/accuracies": 0.606249988079071, | |
| "rewards/chosen": 0.046097733080387115, | |
| "rewards/margins": 0.21919748187065125, | |
| "rewards/rejected": -0.17309975624084473, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 1446.8726182465537, | |
| "learning_rate": 9.756746912994832e-09, | |
| "logits/chosen": -1.5057274103164673, | |
| "logits/rejected": -1.343697190284729, | |
| "logps/chosen": -312.12432861328125, | |
| "logps/rejected": -275.1330871582031, | |
| "loss": 0.6973, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.016833370551466942, | |
| "rewards/margins": 0.13973814249038696, | |
| "rewards/rejected": -0.15657152235507965, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 1216.5073312303066, | |
| "learning_rate": 9.589338354885628e-09, | |
| "logits/chosen": -1.5987694263458252, | |
| "logits/rejected": -1.4453301429748535, | |
| "logps/chosen": -323.3362731933594, | |
| "logps/rejected": -288.1485595703125, | |
| "loss": 0.6695, | |
| "rewards/accuracies": 0.565625011920929, | |
| "rewards/chosen": 0.04707593470811844, | |
| "rewards/margins": 0.22710590064525604, | |
| "rewards/rejected": -0.180029958486557, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 1161.721503342428, | |
| "learning_rate": 9.380618598797472e-09, | |
| "logits/chosen": -1.6032607555389404, | |
| "logits/rejected": -1.4058634042739868, | |
| "logps/chosen": -319.96173095703125, | |
| "logps/rejected": -281.8211364746094, | |
| "loss": 0.6501, | |
| "rewards/accuracies": 0.628125011920929, | |
| "rewards/chosen": 0.11853907257318497, | |
| "rewards/margins": 0.32674410939216614, | |
| "rewards/rejected": -0.20820502936840057, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1255.206435160775, | |
| "learning_rate": 9.132466447838596e-09, | |
| "logits/chosen": -1.5419257879257202, | |
| "logits/rejected": -1.3666443824768066, | |
| "logps/chosen": -321.9004821777344, | |
| "logps/rejected": -282.74346923828125, | |
| "loss": 0.6241, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": 0.21292057633399963, | |
| "rewards/margins": 0.4663107991218567, | |
| "rewards/rejected": -0.25339022278785706, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 1196.6092743226689, | |
| "learning_rate": 8.847115658129039e-09, | |
| "logits/chosen": -1.50592839717865, | |
| "logits/rejected": -1.3777477741241455, | |
| "logps/chosen": -318.1675720214844, | |
| "logps/rejected": -287.3236083984375, | |
| "loss": 0.6068, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": 0.17643409967422485, | |
| "rewards/margins": 0.4380553662776947, | |
| "rewards/rejected": -0.26162129640579224, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 1069.9581355208816, | |
| "learning_rate": 8.527134831514116e-09, | |
| "logits/chosen": -1.5797988176345825, | |
| "logits/rejected": -1.4248679876327515, | |
| "logps/chosen": -331.4310302734375, | |
| "logps/rejected": -297.9786682128906, | |
| "loss": 0.613, | |
| "rewards/accuracies": 0.6187499761581421, | |
| "rewards/chosen": 0.19524307548999786, | |
| "rewards/margins": 0.3385895788669586, | |
| "rewards/rejected": -0.14334650337696075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 1001.0236709718766, | |
| "learning_rate": 8.175404294144481e-09, | |
| "logits/chosen": -1.6208512783050537, | |
| "logits/rejected": -1.4344335794448853, | |
| "logps/chosen": -317.17388916015625, | |
| "logps/rejected": -271.62255859375, | |
| "loss": 0.5838, | |
| "rewards/accuracies": 0.6499999761581421, | |
| "rewards/chosen": 0.3348919153213501, | |
| "rewards/margins": 0.4819467067718506, | |
| "rewards/rejected": -0.14705480635166168, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 1056.0149896521477, | |
| "learning_rate": 7.79509016905158e-09, | |
| "logits/chosen": -1.566674828529358, | |
| "logits/rejected": -1.417965292930603, | |
| "logps/chosen": -331.0799255371094, | |
| "logps/rejected": -294.3246154785156, | |
| "loss": 0.5738, | |
| "rewards/accuracies": 0.7281249761581421, | |
| "rewards/chosen": 0.5121167898178101, | |
| "rewards/margins": 0.6085957288742065, | |
| "rewards/rejected": -0.09647894650697708, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 1085.2712824812697, | |
| "learning_rate": 7.389615876105773e-09, | |
| "logits/chosen": -1.5494105815887451, | |
| "logits/rejected": -1.4207683801651, | |
| "logps/chosen": -314.55694580078125, | |
| "logps/rejected": -291.8951110839844, | |
| "loss": 0.5814, | |
| "rewards/accuracies": 0.6656249761581421, | |
| "rewards/chosen": 0.5086601972579956, | |
| "rewards/margins": 0.5659324526786804, | |
| "rewards/rejected": -0.057272158563137054, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 1147.2094257934837, | |
| "learning_rate": 6.962631315901861e-09, | |
| "logits/chosen": -1.5222028493881226, | |
| "logits/rejected": -1.406696081161499, | |
| "logps/chosen": -317.96502685546875, | |
| "logps/rejected": -291.0884704589844, | |
| "loss": 0.5667, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": 0.5517348051071167, | |
| "rewards/margins": 0.5213624835014343, | |
| "rewards/rejected": 0.030372310429811478, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 1097.0692572479243, | |
| "learning_rate": 6.517980014965139e-09, | |
| "logits/chosen": -1.5993129014968872, | |
| "logits/rejected": -1.41109299659729, | |
| "logps/chosen": -331.37066650390625, | |
| "logps/rejected": -289.573486328125, | |
| "loss": 0.5518, | |
| "rewards/accuracies": 0.734375, | |
| "rewards/chosen": 0.6186414957046509, | |
| "rewards/margins": 0.6974190473556519, | |
| "rewards/rejected": -0.0787774994969368, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 1005.7280013223308, | |
| "learning_rate": 6.059664528022266e-09, | |
| "logits/chosen": -1.6032111644744873, | |
| "logits/rejected": -1.4532817602157593, | |
| "logps/chosen": -315.0304260253906, | |
| "logps/rejected": -276.7928771972656, | |
| "loss": 0.5485, | |
| "rewards/accuracies": 0.746874988079071, | |
| "rewards/chosen": 0.6357426047325134, | |
| "rewards/margins": 0.7282391786575317, | |
| "rewards/rejected": -0.09249657392501831, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 1081.11663192182, | |
| "learning_rate": 5.591810408770492e-09, | |
| "logits/chosen": -1.5532522201538086, | |
| "logits/rejected": -1.3794432878494263, | |
| "logps/chosen": -315.5338439941406, | |
| "logps/rejected": -278.7769470214844, | |
| "loss": 0.5324, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": 0.6404975056648254, | |
| "rewards/margins": 0.7475987076759338, | |
| "rewards/rejected": -0.10710116475820541, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 994.8740373609369, | |
| "learning_rate": 5.118629073464423e-09, | |
| "logits/chosen": -1.5689371824264526, | |
| "logits/rejected": -1.3581821918487549, | |
| "logps/chosen": -325.8009033203125, | |
| "logps/rejected": -282.7605895996094, | |
| "loss": 0.5279, | |
| "rewards/accuracies": 0.703125, | |
| "rewards/chosen": 0.8169169425964355, | |
| "rewards/margins": 0.8118550181388855, | |
| "rewards/rejected": 0.005061971955001354, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 1046.062764450064, | |
| "learning_rate": 4.644379891605983e-09, | |
| "logits/chosen": -1.6105190515518188, | |
| "logits/rejected": -1.4331891536712646, | |
| "logps/chosen": -324.65234375, | |
| "logps/rejected": -291.387451171875, | |
| "loss": 0.5257, | |
| "rewards/accuracies": 0.6875, | |
| "rewards/chosen": 0.7297837138175964, | |
| "rewards/margins": 0.761337399482727, | |
| "rewards/rejected": -0.03155365586280823, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 1062.5909355592705, | |
| "learning_rate": 4.173331844980362e-09, | |
| "logits/chosen": -1.542718529701233, | |
| "logits/rejected": -1.4185158014297485, | |
| "logps/chosen": -323.8753356933594, | |
| "logps/rejected": -293.48626708984375, | |
| "loss": 0.5141, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 0.7222188711166382, | |
| "rewards/margins": 0.7484906911849976, | |
| "rewards/rejected": -0.026271820068359375, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 1054.001314243816, | |
| "learning_rate": 3.7097251001664824e-09, | |
| "logits/chosen": -1.5353752374649048, | |
| "logits/rejected": -1.3762162923812866, | |
| "logps/chosen": -323.80047607421875, | |
| "logps/rejected": -287.00726318359375, | |
| "loss": 0.5117, | |
| "rewards/accuracies": 0.715624988079071, | |
| "rewards/chosen": 0.8148177266120911, | |
| "rewards/margins": 0.8335307240486145, | |
| "rewards/rejected": -0.018712949007749557, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 1057.7644150535455, | |
| "learning_rate": 3.2577328404292057e-09, | |
| "logits/chosen": -1.5480402708053589, | |
| "logits/rejected": -1.4182308912277222, | |
| "logps/chosen": -312.3599548339844, | |
| "logps/rejected": -285.9615478515625, | |
| "loss": 0.5004, | |
| "rewards/accuracies": 0.7437499761581421, | |
| "rewards/chosen": 0.8805425763130188, | |
| "rewards/margins": 0.8217647671699524, | |
| "rewards/rejected": 0.05877774953842163, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 1134.7078580204877, | |
| "learning_rate": 2.821423700565763e-09, | |
| "logits/chosen": -1.597772479057312, | |
| "logits/rejected": -1.4192153215408325, | |
| "logps/chosen": -350.49432373046875, | |
| "logps/rejected": -306.66290283203125, | |
| "loss": 0.497, | |
| "rewards/accuracies": 0.8031250238418579, | |
| "rewards/chosen": 1.035740613937378, | |
| "rewards/margins": 1.0768238306045532, | |
| "rewards/rejected": -0.04108327627182007, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 1065.7113049843235, | |
| "learning_rate": 2.4047251428513483e-09, | |
| "logits/chosen": -1.615321397781372, | |
| "logits/rejected": -1.4609696865081787, | |
| "logps/chosen": -325.0920104980469, | |
| "logps/rejected": -291.08197021484375, | |
| "loss": 0.513, | |
| "rewards/accuracies": 0.7406250238418579, | |
| "rewards/chosen": 0.9730992317199707, | |
| "rewards/margins": 0.9078540802001953, | |
| "rewards/rejected": 0.06524516642093658, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 864.6386915761193, | |
| "learning_rate": 2.011388103757442e-09, | |
| "logits/chosen": -1.5269956588745117, | |
| "logits/rejected": -1.3828452825546265, | |
| "logps/chosen": -316.21124267578125, | |
| "logps/rejected": -285.77667236328125, | |
| "loss": 0.4948, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": 0.9972602725028992, | |
| "rewards/margins": 0.9109752774238586, | |
| "rewards/rejected": 0.08628497272729874, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 990.2860964249656, | |
| "learning_rate": 1.644953229677474e-09, | |
| "logits/chosen": -1.601299524307251, | |
| "logits/rejected": -1.4185166358947754, | |
| "logps/chosen": -325.8226623535156, | |
| "logps/rejected": -284.75567626953125, | |
| "loss": 0.5046, | |
| "rewards/accuracies": 0.7906249761581421, | |
| "rewards/chosen": 1.0880569219589233, | |
| "rewards/margins": 1.0006572008132935, | |
| "rewards/rejected": 0.08739979565143585, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 1035.2441434858022, | |
| "learning_rate": 1.308719005590957e-09, | |
| "logits/chosen": -1.5150429010391235, | |
| "logits/rejected": -1.400657057762146, | |
| "logps/chosen": -318.3056640625, | |
| "logps/rejected": -282.54803466796875, | |
| "loss": 0.5012, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": 0.9477123022079468, | |
| "rewards/margins": 0.9480409622192383, | |
| "rewards/rejected": -0.00032869577989913523, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 952.917065524399, | |
| "learning_rate": 1.005712063557776e-09, | |
| "logits/chosen": -1.6322643756866455, | |
| "logits/rejected": -1.4532310962677002, | |
| "logps/chosen": -323.9804382324219, | |
| "logps/rejected": -290.63629150390625, | |
| "loss": 0.505, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 0.903466522693634, | |
| "rewards/margins": 0.8820658922195435, | |
| "rewards/rejected": 0.02140064910054207, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 946.6373160602382, | |
| "learning_rate": 7.386599383124321e-10, | |
| "logits/chosen": -1.5624831914901733, | |
| "logits/rejected": -1.3783166408538818, | |
| "logps/chosen": -321.67547607421875, | |
| "logps/rejected": -285.8205261230469, | |
| "loss": 0.5001, | |
| "rewards/accuracies": 0.7562500238418579, | |
| "rewards/chosen": 0.9382842779159546, | |
| "rewards/margins": 0.9216762781143188, | |
| "rewards/rejected": 0.01660792902112007, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 995.8621536271032, | |
| "learning_rate": 5.099665152003929e-10, | |
| "logits/chosen": -1.5874156951904297, | |
| "logits/rejected": -1.3745605945587158, | |
| "logps/chosen": -333.58453369140625, | |
| "logps/rejected": -289.9964294433594, | |
| "loss": 0.4994, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": 1.030099868774414, | |
| "rewards/margins": 1.0678800344467163, | |
| "rewards/rejected": -0.03778017312288284, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 920.3253000772652, | |
| "learning_rate": 3.216903914633745e-10, | |
| "logits/chosen": -1.5468734502792358, | |
| "logits/rejected": -1.4234826564788818, | |
| "logps/chosen": -325.117919921875, | |
| "logps/rejected": -296.07086181640625, | |
| "loss": 0.5015, | |
| "rewards/accuracies": 0.737500011920929, | |
| "rewards/chosen": 0.9095224142074585, | |
| "rewards/margins": 0.8073747754096985, | |
| "rewards/rejected": 0.1021476536989212, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 988.4564193799931, | |
| "learning_rate": 1.7552634565570324e-10, | |
| "logits/chosen": -1.5551540851593018, | |
| "logits/rejected": -1.3869084119796753, | |
| "logps/chosen": -329.73553466796875, | |
| "logps/rejected": -292.8804931640625, | |
| "loss": 0.4969, | |
| "rewards/accuracies": 0.7749999761581421, | |
| "rewards/chosen": 1.0978221893310547, | |
| "rewards/margins": 1.0354284048080444, | |
| "rewards/rejected": 0.0623936764895916, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 978.2289689829179, | |
| "learning_rate": 7.279008199590543e-11, | |
| "logits/chosen": -1.5398132801055908, | |
| "logits/rejected": -1.3765273094177246, | |
| "logps/chosen": -326.29425048828125, | |
| "logps/rejected": -292.0558166503906, | |
| "loss": 0.4951, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": 1.0201548337936401, | |
| "rewards/margins": 1.052316665649414, | |
| "rewards/rejected": -0.03216180205345154, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 921.2000894790062, | |
| "learning_rate": 1.4406386978128017e-11, | |
| "logits/chosen": -1.629494309425354, | |
| "logits/rejected": -1.434570074081421, | |
| "logps/chosen": -330.90911865234375, | |
| "logps/rejected": -291.73638916015625, | |
| "loss": 0.4873, | |
| "rewards/accuracies": 0.8125, | |
| "rewards/chosen": 1.1673272848129272, | |
| "rewards/margins": 1.1191251277923584, | |
| "rewards/rejected": 0.048202164471149445, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 368, | |
| "total_flos": 0.0, | |
| "train_loss": 0.577453197668428, | |
| "train_runtime": 9953.5163, | |
| "train_samples_per_second": 9.463, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 368, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |