| { | |
| "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": 2733.5875966596914, | |
| "learning_rate": 2.702702702702703e-10, | |
| "logits/chosen": -1.3332719802856445, | |
| "logits/rejected": -1.246394395828247, | |
| "logps/chosen": -286.9539794921875, | |
| "logps/rejected": -263.3782958984375, | |
| "loss": 0.7283, | |
| "rewards/accuracies": 0.0, | |
| "rewards/chosen": 0.0, | |
| "rewards/margins": 0.0, | |
| "rewards/rejected": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3426.28374639058, | |
| "learning_rate": 2.702702702702703e-09, | |
| "logits/chosen": -1.617490530014038, | |
| "logits/rejected": -1.3964743614196777, | |
| "logps/chosen": -342.53607177734375, | |
| "logps/rejected": -294.5452575683594, | |
| "loss": 0.9019, | |
| "rewards/accuracies": 0.4375, | |
| "rewards/chosen": -0.0025859144516289234, | |
| "rewards/margins": 0.014665775932371616, | |
| "rewards/rejected": -0.017251690849661827, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 3068.517544136213, | |
| "learning_rate": 5.405405405405406e-09, | |
| "logits/chosen": -1.4905732870101929, | |
| "logits/rejected": -1.3132953643798828, | |
| "logps/chosen": -314.7499084472656, | |
| "logps/rejected": -279.27752685546875, | |
| "loss": 0.9225, | |
| "rewards/accuracies": 0.4937500059604645, | |
| "rewards/chosen": 0.03222837299108505, | |
| "rewards/margins": -0.024351513013243675, | |
| "rewards/rejected": 0.05657988786697388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3019.197796031677, | |
| "learning_rate": 8.108108108108109e-09, | |
| "logits/chosen": -1.5479624271392822, | |
| "logits/rejected": -1.3802028894424438, | |
| "logps/chosen": -324.89044189453125, | |
| "logps/rejected": -286.2395324707031, | |
| "loss": 0.9562, | |
| "rewards/accuracies": 0.5218750238418579, | |
| "rewards/chosen": 0.031223665922880173, | |
| "rewards/margins": -0.0476018562912941, | |
| "rewards/rejected": 0.07882551848888397, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 2861.837005400921, | |
| "learning_rate": 9.997973265157192e-09, | |
| "logits/chosen": -1.5354044437408447, | |
| "logits/rejected": -1.3576419353485107, | |
| "logps/chosen": -325.43408203125, | |
| "logps/rejected": -285.6204528808594, | |
| "loss": 0.9309, | |
| "rewards/accuracies": 0.484375, | |
| "rewards/chosen": -0.08140890300273895, | |
| "rewards/margins": -0.13951030373573303, | |
| "rewards/rejected": 0.05810140445828438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 3285.7135249709568, | |
| "learning_rate": 9.961988113473708e-09, | |
| "logits/chosen": -1.534355640411377, | |
| "logits/rejected": -1.3875898122787476, | |
| "logps/chosen": -337.02044677734375, | |
| "logps/rejected": -297.35101318359375, | |
| "loss": 0.88, | |
| "rewards/accuracies": 0.546875, | |
| "rewards/chosen": 0.0009558796882629395, | |
| "rewards/margins": 0.08057532459497452, | |
| "rewards/rejected": -0.07961944490671158, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 2547.1665545835035, | |
| "learning_rate": 9.881337335184878e-09, | |
| "logits/chosen": -1.5822935104370117, | |
| "logits/rejected": -1.4333903789520264, | |
| "logps/chosen": -319.79644775390625, | |
| "logps/rejected": -285.0381164550781, | |
| "loss": 0.8105, | |
| "rewards/accuracies": 0.6156250238418579, | |
| "rewards/chosen": 0.09285839647054672, | |
| "rewards/margins": 0.40408092737197876, | |
| "rewards/rejected": -0.31122252345085144, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 3178.8313195657583, | |
| "learning_rate": 9.756746912994832e-09, | |
| "logits/chosen": -1.5119212865829468, | |
| "logits/rejected": -1.350838541984558, | |
| "logps/chosen": -312.1349182128906, | |
| "logps/rejected": -275.08660888671875, | |
| "loss": 0.7993, | |
| "rewards/accuracies": 0.5874999761581421, | |
| "rewards/chosen": -0.05482473224401474, | |
| "rewards/margins": 0.165395587682724, | |
| "rewards/rejected": -0.22022032737731934, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 2596.199281277795, | |
| "learning_rate": 9.589338354885628e-09, | |
| "logits/chosen": -1.5992329120635986, | |
| "logits/rejected": -1.4463211297988892, | |
| "logps/chosen": -323.2821960449219, | |
| "logps/rejected": -288.0993347167969, | |
| "loss": 0.7772, | |
| "rewards/accuracies": 0.574999988079071, | |
| "rewards/chosen": 0.20231203734874725, | |
| "rewards/margins": 0.4638887345790863, | |
| "rewards/rejected": -0.26157671213150024, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 2404.162696635418, | |
| "learning_rate": 9.380618598797472e-09, | |
| "logits/chosen": -1.6108148097991943, | |
| "logits/rejected": -1.4147026538848877, | |
| "logps/chosen": -319.95526123046875, | |
| "logps/rejected": -281.7666015625, | |
| "loss": 0.7649, | |
| "rewards/accuracies": 0.640625, | |
| "rewards/chosen": 0.2500740885734558, | |
| "rewards/margins": 0.5574880838394165, | |
| "rewards/rejected": -0.3074139356613159, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 2500.271614922207, | |
| "learning_rate": 9.132466447838596e-09, | |
| "logits/chosen": -1.542976975440979, | |
| "logits/rejected": -1.3676128387451172, | |
| "logps/chosen": -321.9007263183594, | |
| "logps/rejected": -282.65899658203125, | |
| "loss": 0.7305, | |
| "rewards/accuracies": 0.659375011920929, | |
| "rewards/chosen": 0.4254188537597656, | |
| "rewards/margins": 0.763160228729248, | |
| "rewards/rejected": -0.3377414047718048, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2525.572173445101, | |
| "learning_rate": 8.847115658129039e-09, | |
| "logits/chosen": -1.512939453125, | |
| "logits/rejected": -1.3849382400512695, | |
| "logps/chosen": -318.14813232421875, | |
| "logps/rejected": -287.1947937011719, | |
| "loss": 0.7164, | |
| "rewards/accuracies": 0.628125011920929, | |
| "rewards/chosen": 0.3916184604167938, | |
| "rewards/margins": 0.657262921333313, | |
| "rewards/rejected": -0.265644371509552, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2498.220455730566, | |
| "learning_rate": 8.527134831514116e-09, | |
| "logits/chosen": -1.5739517211914062, | |
| "logits/rejected": -1.41860032081604, | |
| "logps/chosen": -331.3175354003906, | |
| "logps/rejected": -297.8718566894531, | |
| "loss": 0.7018, | |
| "rewards/accuracies": 0.637499988079071, | |
| "rewards/chosen": 0.6175383925437927, | |
| "rewards/margins": 0.6906081438064575, | |
| "rewards/rejected": -0.07306969165802002, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2170.854176631694, | |
| "learning_rate": 8.175404294144481e-09, | |
| "logits/chosen": -1.616276502609253, | |
| "logits/rejected": -1.429518699645996, | |
| "logps/chosen": -317.1609802246094, | |
| "logps/rejected": -271.5557861328125, | |
| "loss": 0.6719, | |
| "rewards/accuracies": 0.6625000238418579, | |
| "rewards/chosen": 0.6955646872520447, | |
| "rewards/margins": 0.8560658693313599, | |
| "rewards/rejected": -0.160501167178154, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2147.543587634845, | |
| "learning_rate": 7.79509016905158e-09, | |
| "logits/chosen": -1.5726101398468018, | |
| "logits/rejected": -1.4245671033859253, | |
| "logps/chosen": -331.12109375, | |
| "logps/rejected": -294.2488098144531, | |
| "loss": 0.6686, | |
| "rewards/accuracies": 0.6968749761581421, | |
| "rewards/chosen": 0.9418653249740601, | |
| "rewards/margins": 0.9832620620727539, | |
| "rewards/rejected": -0.04139674827456474, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 2298.0130679506387, | |
| "learning_rate": 7.389615876105773e-09, | |
| "logits/chosen": -1.5536715984344482, | |
| "logits/rejected": -1.4254592657089233, | |
| "logps/chosen": -314.55267333984375, | |
| "logps/rejected": -291.81536865234375, | |
| "loss": 0.6793, | |
| "rewards/accuracies": 0.675000011920929, | |
| "rewards/chosen": 1.0258944034576416, | |
| "rewards/margins": 0.981005072593689, | |
| "rewards/rejected": 0.04488936811685562, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2220.286727308493, | |
| "learning_rate": 6.962631315901861e-09, | |
| "logits/chosen": -1.5181314945220947, | |
| "logits/rejected": -1.4019381999969482, | |
| "logps/chosen": -318.02752685546875, | |
| "logps/rejected": -291.03936767578125, | |
| "loss": 0.6742, | |
| "rewards/accuracies": 0.628125011920929, | |
| "rewards/chosen": 0.9784830808639526, | |
| "rewards/margins": 0.819505512714386, | |
| "rewards/rejected": 0.15897764265537262, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2125.4983562302123, | |
| "learning_rate": 6.517980014965139e-09, | |
| "logits/chosen": -1.5958881378173828, | |
| "logits/rejected": -1.4071909189224243, | |
| "logps/chosen": -331.4378356933594, | |
| "logps/rejected": -289.5236511230469, | |
| "loss": 0.6456, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 1.1029136180877686, | |
| "rewards/margins": 1.160766363143921, | |
| "rewards/rejected": -0.05785265564918518, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 2116.9259500110184, | |
| "learning_rate": 6.059664528022266e-09, | |
| "logits/chosen": -1.5962104797363281, | |
| "logits/rejected": -1.445967197418213, | |
| "logps/chosen": -315.10467529296875, | |
| "logps/rejected": -276.73443603515625, | |
| "loss": 0.6191, | |
| "rewards/accuracies": 0.6812499761581421, | |
| "rewards/chosen": 1.123002052307129, | |
| "rewards/margins": 1.1910655498504639, | |
| "rewards/rejected": -0.0680634081363678, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2067.8979230397717, | |
| "learning_rate": 5.591810408770492e-09, | |
| "logits/chosen": -1.55275559425354, | |
| "logits/rejected": -1.3787180185317993, | |
| "logps/chosen": -315.572509765625, | |
| "logps/rejected": -278.71087646484375, | |
| "loss": 0.6052, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": 1.2037546634674072, | |
| "rewards/margins": 1.2858160734176636, | |
| "rewards/rejected": -0.0820615291595459, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2203.6189854484824, | |
| "learning_rate": 5.118629073464423e-09, | |
| "logits/chosen": -1.5673738718032837, | |
| "logits/rejected": -1.3565856218338013, | |
| "logps/chosen": -325.91680908203125, | |
| "logps/rejected": -282.65869140625, | |
| "loss": 0.6024, | |
| "rewards/accuracies": 0.746874988079071, | |
| "rewards/chosen": 1.4020355939865112, | |
| "rewards/margins": 1.1880966424942017, | |
| "rewards/rejected": 0.21393892168998718, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2263.504332795979, | |
| "learning_rate": 4.644379891605983e-09, | |
| "logits/chosen": -1.611310601234436, | |
| "logits/rejected": -1.4343440532684326, | |
| "logps/chosen": -324.752197265625, | |
| "logps/rejected": -291.36102294921875, | |
| "loss": 0.5985, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": 1.2598803043365479, | |
| "rewards/margins": 1.2701908349990845, | |
| "rewards/rejected": -0.010310685262084007, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2324.309417872748, | |
| "learning_rate": 4.173331844980362e-09, | |
| "logits/chosen": -1.5291264057159424, | |
| "logits/rejected": -1.4033840894699097, | |
| "logps/chosen": -323.9982604980469, | |
| "logps/rejected": -293.4136047363281, | |
| "loss": 0.5948, | |
| "rewards/accuracies": 0.7281249761581421, | |
| "rewards/chosen": 1.1985571384429932, | |
| "rewards/margins": 1.105764627456665, | |
| "rewards/rejected": 0.09279236942529678, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 2275.313721629071, | |
| "learning_rate": 3.7097251001664824e-09, | |
| "logits/chosen": -1.5342741012573242, | |
| "logits/rejected": -1.3754017353057861, | |
| "logps/chosen": -323.9897766113281, | |
| "logps/rejected": -287.0173645019531, | |
| "loss": 0.577, | |
| "rewards/accuracies": 0.71875, | |
| "rewards/chosen": 1.2511075735092163, | |
| "rewards/margins": 1.3087403774261475, | |
| "rewards/rejected": -0.05763290077447891, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 2261.889907648677, | |
| "learning_rate": 3.2577328404292057e-09, | |
| "logits/chosen": -1.5497777462005615, | |
| "logits/rejected": -1.4208284616470337, | |
| "logps/chosen": -312.53802490234375, | |
| "logps/rejected": -285.97076416015625, | |
| "loss": 0.5741, | |
| "rewards/accuracies": 0.699999988079071, | |
| "rewards/chosen": 1.4049217700958252, | |
| "rewards/margins": 1.3057136535644531, | |
| "rewards/rejected": 0.09920807182788849, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 2520.220972155196, | |
| "learning_rate": 2.821423700565763e-09, | |
| "logits/chosen": -1.5996572971343994, | |
| "logits/rejected": -1.4216984510421753, | |
| "logps/chosen": -350.76129150390625, | |
| "logps/rejected": -306.58831787109375, | |
| "loss": 0.5681, | |
| "rewards/accuracies": 0.762499988079071, | |
| "rewards/chosen": 1.537647008895874, | |
| "rewards/margins": 1.4706511497497559, | |
| "rewards/rejected": 0.06699595600366592, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 2185.2135747623915, | |
| "learning_rate": 2.4047251428513483e-09, | |
| "logits/chosen": -1.61586594581604, | |
| "logits/rejected": -1.4618706703186035, | |
| "logps/chosen": -325.3050537109375, | |
| "logps/rejected": -291.10345458984375, | |
| "loss": 0.5977, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 1.5201152563095093, | |
| "rewards/margins": 1.4326369762420654, | |
| "rewards/rejected": 0.08747831732034683, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 1735.3140228188304, | |
| "learning_rate": 2.011388103757442e-09, | |
| "logits/chosen": -1.5243465900421143, | |
| "logits/rejected": -1.3802506923675537, | |
| "logps/chosen": -316.4330139160156, | |
| "logps/rejected": -285.81353759765625, | |
| "loss": 0.5429, | |
| "rewards/accuracies": 0.7406250238418579, | |
| "rewards/chosen": 1.550986647605896, | |
| "rewards/margins": 1.45218026638031, | |
| "rewards/rejected": 0.09880634397268295, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2121.5830866823144, | |
| "learning_rate": 1.644953229677474e-09, | |
| "logits/chosen": -1.6015859842300415, | |
| "logits/rejected": -1.4193016290664673, | |
| "logps/chosen": -326.1202087402344, | |
| "logps/rejected": -284.7384033203125, | |
| "loss": 0.5887, | |
| "rewards/accuracies": 0.746874988079071, | |
| "rewards/chosen": 1.580999732017517, | |
| "rewards/margins": 1.3716144561767578, | |
| "rewards/rejected": 0.20938535034656525, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 2103.020456118981, | |
| "learning_rate": 1.308719005590957e-09, | |
| "logits/chosen": -1.509340524673462, | |
| "logits/rejected": -1.3944005966186523, | |
| "logps/chosen": -318.451416015625, | |
| "logps/rejected": -282.4563293457031, | |
| "loss": 0.5721, | |
| "rewards/accuracies": 0.731249988079071, | |
| "rewards/chosen": 1.603921890258789, | |
| "rewards/margins": 1.4211392402648926, | |
| "rewards/rejected": 0.182782843708992, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 2010.5734100649909, | |
| "learning_rate": 1.005712063557776e-09, | |
| "logits/chosen": -1.6272541284561157, | |
| "logits/rejected": -1.4480578899383545, | |
| "logps/chosen": -324.20068359375, | |
| "logps/rejected": -290.54803466796875, | |
| "loss": 0.5898, | |
| "rewards/accuracies": 0.6968749761581421, | |
| "rewards/chosen": 1.3664501905441284, | |
| "rewards/margins": 1.1471518278121948, | |
| "rewards/rejected": 0.21929831802845, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 1862.455491029429, | |
| "learning_rate": 7.386599383124321e-10, | |
| "logits/chosen": -1.563561201095581, | |
| "logits/rejected": -1.3803369998931885, | |
| "logps/chosen": -321.889404296875, | |
| "logps/rejected": -285.8083190917969, | |
| "loss": 0.5879, | |
| "rewards/accuracies": 0.7124999761581421, | |
| "rewards/chosen": 1.4487113952636719, | |
| "rewards/margins": 1.3910987377166748, | |
| "rewards/rejected": 0.057612527161836624, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 1875.0391267528262, | |
| "learning_rate": 5.099665152003929e-10, | |
| "logits/chosen": -1.5980346202850342, | |
| "logits/rejected": -1.3878109455108643, | |
| "logps/chosen": -333.843994140625, | |
| "logps/rejected": -289.8874816894531, | |
| "loss": 0.5634, | |
| "rewards/accuracies": 0.7593749761581421, | |
| "rewards/chosen": 1.5412708520889282, | |
| "rewards/margins": 1.3988701105117798, | |
| "rewards/rejected": 0.14240065217018127, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 2232.545936783362, | |
| "learning_rate": 3.216903914633745e-10, | |
| "logits/chosen": -1.5563807487487793, | |
| "logits/rejected": -1.4342092275619507, | |
| "logps/chosen": -325.34674072265625, | |
| "logps/rejected": -296.1554870605469, | |
| "loss": 0.5762, | |
| "rewards/accuracies": 0.706250011920929, | |
| "rewards/chosen": 1.3614461421966553, | |
| "rewards/margins": 1.3264009952545166, | |
| "rewards/rejected": 0.03504505008459091, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 1895.2431252651277, | |
| "learning_rate": 1.7552634565570324e-10, | |
| "logits/chosen": -1.5503065586090088, | |
| "logits/rejected": -1.381874680519104, | |
| "logps/chosen": -329.953857421875, | |
| "logps/rejected": -292.89447021484375, | |
| "loss": 0.5681, | |
| "rewards/accuracies": 0.7718750238418579, | |
| "rewards/chosen": 1.7590471506118774, | |
| "rewards/margins": 1.6621748208999634, | |
| "rewards/rejected": 0.09687252342700958, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 2070.257116146559, | |
| "learning_rate": 7.279008199590543e-11, | |
| "logits/chosen": -1.541084885597229, | |
| "logits/rejected": -1.378144383430481, | |
| "logps/chosen": -326.51507568359375, | |
| "logps/rejected": -291.95123291015625, | |
| "loss": 0.5797, | |
| "rewards/accuracies": 0.7281249761581421, | |
| "rewards/chosen": 1.5987285375595093, | |
| "rewards/margins": 1.4538962841033936, | |
| "rewards/rejected": 0.1448323279619217, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 2166.9724743285583, | |
| "learning_rate": 1.4406386978128017e-11, | |
| "logits/chosen": -1.6209802627563477, | |
| "logits/rejected": -1.42485511302948, | |
| "logps/chosen": -331.2142639160156, | |
| "logps/rejected": -291.69842529296875, | |
| "loss": 0.5582, | |
| "rewards/accuracies": 0.778124988079071, | |
| "rewards/chosen": 1.724250078201294, | |
| "rewards/margins": 1.5519315004348755, | |
| "rewards/rejected": 0.1723184883594513, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 368, | |
| "total_flos": 0.0, | |
| "train_loss": 0.26489045179408527, | |
| "train_runtime": 4520.7899, | |
| "train_samples_per_second": 20.835, | |
| "train_steps_per_second": 0.081 | |
| } | |
| ], | |
| "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 | |
| } | |