{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.4999858203495, "eval_steps": 500, "global_step": 11019, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00045374881599918323, "grad_norm": 6.570525646209717, "learning_rate": 6.042296072507553e-07, "loss": 0.5776, "step": 10 }, { "epoch": 0.0009074976319983665, "grad_norm": 4.783041477203369, "learning_rate": 1.2084592145015106e-06, "loss": 0.5275, "step": 20 }, { "epoch": 0.0013612464479975498, "grad_norm": 2.321625232696533, "learning_rate": 1.8126888217522659e-06, "loss": 0.4461, "step": 30 }, { "epoch": 0.001814995263996733, "grad_norm": 1.6644396781921387, "learning_rate": 2.4169184290030213e-06, "loss": 0.2891, "step": 40 }, { "epoch": 0.002268744079995916, "grad_norm": 1.285487413406372, "learning_rate": 3.0211480362537765e-06, "loss": 0.1831, "step": 50 }, { "epoch": 0.0027224928959950997, "grad_norm": 1.067684292793274, "learning_rate": 3.6253776435045317e-06, "loss": 0.1383, "step": 60 }, { "epoch": 0.0031762417119942828, "grad_norm": 0.824091911315918, "learning_rate": 4.229607250755287e-06, "loss": 0.121, "step": 70 }, { "epoch": 0.003629990527993466, "grad_norm": 0.8687748312950134, "learning_rate": 4.833836858006043e-06, "loss": 0.0985, "step": 80 }, { "epoch": 0.004083739343992649, "grad_norm": 0.8202484250068665, "learning_rate": 5.438066465256799e-06, "loss": 0.089, "step": 90 }, { "epoch": 0.004537488159991832, "grad_norm": 0.7578614354133606, "learning_rate": 6.042296072507553e-06, "loss": 0.082, "step": 100 }, { "epoch": 0.004991236975991016, "grad_norm": 1.1080694198608398, "learning_rate": 6.646525679758309e-06, "loss": 0.0943, "step": 110 }, { "epoch": 0.005444985791990199, "grad_norm": 0.7602319717407227, "learning_rate": 7.2507552870090635e-06, "loss": 0.079, "step": 120 }, { "epoch": 0.005898734607989382, "grad_norm": 1.5247118473052979, "learning_rate": 7.85498489425982e-06, "loss": 0.0749, "step": 130 }, { "epoch": 0.0063524834239885655, "grad_norm": 1.1259148120880127, "learning_rate": 8.459214501510575e-06, "loss": 0.0785, "step": 140 }, { "epoch": 0.006806232239987749, "grad_norm": 0.7788676619529724, "learning_rate": 9.06344410876133e-06, "loss": 0.0697, "step": 150 }, { "epoch": 0.007259981055986932, "grad_norm": 0.8205882906913757, "learning_rate": 9.667673716012085e-06, "loss": 0.0735, "step": 160 }, { "epoch": 0.007713729871986115, "grad_norm": 0.5829521417617798, "learning_rate": 1.0271903323262842e-05, "loss": 0.06, "step": 170 }, { "epoch": 0.008167478687985298, "grad_norm": 0.5856772661209106, "learning_rate": 1.0876132930513597e-05, "loss": 0.0645, "step": 180 }, { "epoch": 0.008621227503984481, "grad_norm": 0.6676274538040161, "learning_rate": 1.1480362537764351e-05, "loss": 0.0717, "step": 190 }, { "epoch": 0.009074976319983665, "grad_norm": 0.6693158745765686, "learning_rate": 1.2084592145015106e-05, "loss": 0.0588, "step": 200 }, { "epoch": 0.009528725135982848, "grad_norm": 0.6060015559196472, "learning_rate": 1.2688821752265863e-05, "loss": 0.0574, "step": 210 }, { "epoch": 0.009982473951982032, "grad_norm": 0.5733058452606201, "learning_rate": 1.3293051359516618e-05, "loss": 0.0549, "step": 220 }, { "epoch": 0.010436222767981215, "grad_norm": 0.5038084387779236, "learning_rate": 1.3897280966767372e-05, "loss": 0.0531, "step": 230 }, { "epoch": 0.010889971583980399, "grad_norm": 0.5429157614707947, "learning_rate": 1.4501510574018127e-05, "loss": 0.0579, "step": 240 }, { "epoch": 0.01134372039997958, "grad_norm": 0.4899637699127197, "learning_rate": 1.5105740181268884e-05, "loss": 0.0518, "step": 250 }, { "epoch": 0.011797469215978764, "grad_norm": 0.4721384346485138, "learning_rate": 1.570996978851964e-05, "loss": 0.0619, "step": 260 }, { "epoch": 0.012251218031977948, "grad_norm": 0.5387476086616516, "learning_rate": 1.6314199395770393e-05, "loss": 0.0629, "step": 270 }, { "epoch": 0.012704966847977131, "grad_norm": 0.6214449405670166, "learning_rate": 1.691842900302115e-05, "loss": 0.06, "step": 280 }, { "epoch": 0.013158715663976315, "grad_norm": 0.6204676032066345, "learning_rate": 1.7522658610271906e-05, "loss": 0.0568, "step": 290 }, { "epoch": 0.013612464479975498, "grad_norm": 0.7833480834960938, "learning_rate": 1.812688821752266e-05, "loss": 0.0535, "step": 300 }, { "epoch": 0.014066213295974682, "grad_norm": 0.7017704248428345, "learning_rate": 1.8731117824773413e-05, "loss": 0.0587, "step": 310 }, { "epoch": 0.014519962111973863, "grad_norm": 0.620866060256958, "learning_rate": 1.933534743202417e-05, "loss": 0.0555, "step": 320 }, { "epoch": 0.014973710927973047, "grad_norm": 0.4685516655445099, "learning_rate": 1.9939577039274927e-05, "loss": 0.0505, "step": 330 }, { "epoch": 0.01542745974397223, "grad_norm": 0.5689406991004944, "learning_rate": 1.9999965008575334e-05, "loss": 0.0545, "step": 340 }, { "epoch": 0.015881208559971414, "grad_norm": 0.48428890109062195, "learning_rate": 1.999984405087852e-05, "loss": 0.0525, "step": 350 }, { "epoch": 0.016334957375970596, "grad_norm": 0.552220344543457, "learning_rate": 1.999963669596147e-05, "loss": 0.0488, "step": 360 }, { "epoch": 0.01678870619196978, "grad_norm": 0.5278618335723877, "learning_rate": 1.9999342945615705e-05, "loss": 0.0544, "step": 370 }, { "epoch": 0.017242455007968963, "grad_norm": 0.4623413681983948, "learning_rate": 1.9998962802379185e-05, "loss": 0.0463, "step": 380 }, { "epoch": 0.017696203823968148, "grad_norm": 0.4446093440055847, "learning_rate": 1.9998496269536293e-05, "loss": 0.0485, "step": 390 }, { "epoch": 0.01814995263996733, "grad_norm": 0.3841504156589508, "learning_rate": 1.9997943351117804e-05, "loss": 0.0497, "step": 400 }, { "epoch": 0.018603701455966515, "grad_norm": 0.39876046776771545, "learning_rate": 1.9997304051900853e-05, "loss": 0.0484, "step": 410 }, { "epoch": 0.019057450271965697, "grad_norm": 0.6340653300285339, "learning_rate": 1.9996578377408897e-05, "loss": 0.0496, "step": 420 }, { "epoch": 0.01951119908796488, "grad_norm": 0.48574307560920715, "learning_rate": 1.9995766333911663e-05, "loss": 0.0437, "step": 430 }, { "epoch": 0.019964947903964064, "grad_norm": 0.39103829860687256, "learning_rate": 1.999486792842508e-05, "loss": 0.05, "step": 440 }, { "epoch": 0.020418696719963245, "grad_norm": 0.5536549687385559, "learning_rate": 1.999388316871125e-05, "loss": 0.0508, "step": 450 }, { "epoch": 0.02087244553596243, "grad_norm": 0.5049840807914734, "learning_rate": 1.9992812063278354e-05, "loss": 0.0482, "step": 460 }, { "epoch": 0.021326194351961612, "grad_norm": 0.409262478351593, "learning_rate": 1.9991654621380593e-05, "loss": 0.037, "step": 470 }, { "epoch": 0.021779943167960798, "grad_norm": 0.39101433753967285, "learning_rate": 1.9990410853018094e-05, "loss": 0.0507, "step": 480 }, { "epoch": 0.02223369198395998, "grad_norm": 0.4060726761817932, "learning_rate": 1.998908076893684e-05, "loss": 0.0427, "step": 490 }, { "epoch": 0.02268744079995916, "grad_norm": 0.37995368242263794, "learning_rate": 1.9987664380628566e-05, "loss": 0.045, "step": 500 }, { "epoch": 0.023141189615958346, "grad_norm": 0.4126657545566559, "learning_rate": 1.9986161700330668e-05, "loss": 0.0422, "step": 510 }, { "epoch": 0.023594938431957528, "grad_norm": 0.35935208201408386, "learning_rate": 1.998457274102608e-05, "loss": 0.0471, "step": 520 }, { "epoch": 0.024048687247956713, "grad_norm": 0.31279709935188293, "learning_rate": 1.9982897516443194e-05, "loss": 0.0453, "step": 530 }, { "epoch": 0.024502436063955895, "grad_norm": 0.4056517481803894, "learning_rate": 1.9981136041055703e-05, "loss": 0.0461, "step": 540 }, { "epoch": 0.02495618487995508, "grad_norm": 0.40961775183677673, "learning_rate": 1.99792883300825e-05, "loss": 0.0459, "step": 550 }, { "epoch": 0.025409933695954262, "grad_norm": 0.46304839849472046, "learning_rate": 1.997735439948755e-05, "loss": 0.0458, "step": 560 }, { "epoch": 0.025863682511953444, "grad_norm": 0.32578155398368835, "learning_rate": 1.997533426597973e-05, "loss": 0.0456, "step": 570 }, { "epoch": 0.02631743132795263, "grad_norm": 0.5448132157325745, "learning_rate": 1.9973227947012713e-05, "loss": 0.0395, "step": 580 }, { "epoch": 0.02677118014395181, "grad_norm": 0.35044586658477783, "learning_rate": 1.9971035460784783e-05, "loss": 0.0455, "step": 590 }, { "epoch": 0.027224928959950996, "grad_norm": 0.3435221314430237, "learning_rate": 1.9968756826238713e-05, "loss": 0.0478, "step": 600 }, { "epoch": 0.027678677775950178, "grad_norm": 0.46500614285469055, "learning_rate": 1.9966392063061573e-05, "loss": 0.0477, "step": 610 }, { "epoch": 0.028132426591949363, "grad_norm": 0.3141709566116333, "learning_rate": 1.9963941191684585e-05, "loss": 0.0395, "step": 620 }, { "epoch": 0.028586175407948545, "grad_norm": 0.3839573860168457, "learning_rate": 1.9961404233282926e-05, "loss": 0.0389, "step": 630 }, { "epoch": 0.029039924223947727, "grad_norm": 0.43812301754951477, "learning_rate": 1.995878120977555e-05, "loss": 0.0443, "step": 640 }, { "epoch": 0.029493673039946912, "grad_norm": 0.3598954677581787, "learning_rate": 1.9956072143825006e-05, "loss": 0.0433, "step": 650 }, { "epoch": 0.029947421855946094, "grad_norm": 0.4609631896018982, "learning_rate": 1.9953277058837237e-05, "loss": 0.0417, "step": 660 }, { "epoch": 0.03040117067194528, "grad_norm": 0.5079893469810486, "learning_rate": 1.9950395978961376e-05, "loss": 0.0486, "step": 670 }, { "epoch": 0.03085491948794446, "grad_norm": 0.4226292073726654, "learning_rate": 1.9947428929089536e-05, "loss": 0.0423, "step": 680 }, { "epoch": 0.031308668303943646, "grad_norm": 0.3605279326438904, "learning_rate": 1.9944375934856606e-05, "loss": 0.0401, "step": 690 }, { "epoch": 0.03176241711994283, "grad_norm": 0.3350829780101776, "learning_rate": 1.9941237022640024e-05, "loss": 0.0394, "step": 700 }, { "epoch": 0.03221616593594201, "grad_norm": 0.4309473931789398, "learning_rate": 1.9938012219559536e-05, "loss": 0.0363, "step": 710 }, { "epoch": 0.03266991475194119, "grad_norm": 0.29544690251350403, "learning_rate": 1.9934701553476983e-05, "loss": 0.0437, "step": 720 }, { "epoch": 0.03312366356794038, "grad_norm": 0.4691392481327057, "learning_rate": 1.993130505299604e-05, "loss": 0.0428, "step": 730 }, { "epoch": 0.03357741238393956, "grad_norm": 0.351115345954895, "learning_rate": 1.9927822747461987e-05, "loss": 0.0384, "step": 740 }, { "epoch": 0.03403116119993874, "grad_norm": 0.3539256155490875, "learning_rate": 1.9924254666961446e-05, "loss": 0.0363, "step": 750 }, { "epoch": 0.034484910015937925, "grad_norm": 0.33034589886665344, "learning_rate": 1.9920600842322123e-05, "loss": 0.0322, "step": 760 }, { "epoch": 0.034938658831937114, "grad_norm": 0.2926701307296753, "learning_rate": 1.9916861305112536e-05, "loss": 0.0377, "step": 770 }, { "epoch": 0.035392407647936296, "grad_norm": 0.40202829241752625, "learning_rate": 1.9913036087641756e-05, "loss": 0.0371, "step": 780 }, { "epoch": 0.03584615646393548, "grad_norm": 0.404471218585968, "learning_rate": 1.9909125222959106e-05, "loss": 0.0336, "step": 790 }, { "epoch": 0.03629990527993466, "grad_norm": 0.4597315490245819, "learning_rate": 1.9905128744853903e-05, "loss": 0.0397, "step": 800 }, { "epoch": 0.03675365409593384, "grad_norm": 0.37393319606781006, "learning_rate": 1.9901046687855142e-05, "loss": 0.0453, "step": 810 }, { "epoch": 0.03720740291193303, "grad_norm": 0.4036656618118286, "learning_rate": 1.9896879087231212e-05, "loss": 0.0413, "step": 820 }, { "epoch": 0.03766115172793221, "grad_norm": 0.3243216872215271, "learning_rate": 1.989262597898959e-05, "loss": 0.0374, "step": 830 }, { "epoch": 0.03811490054393139, "grad_norm": 0.3784448802471161, "learning_rate": 1.9888287399876514e-05, "loss": 0.038, "step": 840 }, { "epoch": 0.038568649359930575, "grad_norm": 0.36255982518196106, "learning_rate": 1.9883863387376688e-05, "loss": 0.0383, "step": 850 }, { "epoch": 0.03902239817592976, "grad_norm": 0.3695404529571533, "learning_rate": 1.9879353979712953e-05, "loss": 0.0446, "step": 860 }, { "epoch": 0.039476146991928945, "grad_norm": 0.2772950828075409, "learning_rate": 1.987475921584594e-05, "loss": 0.0338, "step": 870 }, { "epoch": 0.03992989580792813, "grad_norm": 0.37159234285354614, "learning_rate": 1.987007913547375e-05, "loss": 0.0396, "step": 880 }, { "epoch": 0.04038364462392731, "grad_norm": 0.36864423751831055, "learning_rate": 1.9865313779031607e-05, "loss": 0.0412, "step": 890 }, { "epoch": 0.04083739343992649, "grad_norm": 0.4077175557613373, "learning_rate": 1.986046318769151e-05, "loss": 0.0434, "step": 900 }, { "epoch": 0.04129114225592568, "grad_norm": 0.331467866897583, "learning_rate": 1.9855527403361874e-05, "loss": 0.0428, "step": 910 }, { "epoch": 0.04174489107192486, "grad_norm": 0.3420073091983795, "learning_rate": 1.9850506468687164e-05, "loss": 0.0404, "step": 920 }, { "epoch": 0.04219863988792404, "grad_norm": 0.2998998165130615, "learning_rate": 1.9845400427047542e-05, "loss": 0.0373, "step": 930 }, { "epoch": 0.042652388703923225, "grad_norm": 0.36804765462875366, "learning_rate": 1.9840209322558476e-05, "loss": 0.0436, "step": 940 }, { "epoch": 0.043106137519922406, "grad_norm": 0.29252004623413086, "learning_rate": 1.983493320007036e-05, "loss": 0.0368, "step": 950 }, { "epoch": 0.043559886335921595, "grad_norm": 0.45206567645072937, "learning_rate": 1.9829572105168137e-05, "loss": 0.0387, "step": 960 }, { "epoch": 0.04401363515192078, "grad_norm": 0.4062231779098511, "learning_rate": 1.9824126084170907e-05, "loss": 0.0402, "step": 970 }, { "epoch": 0.04446738396791996, "grad_norm": 0.3019125163555145, "learning_rate": 1.9818595184131505e-05, "loss": 0.0437, "step": 980 }, { "epoch": 0.04492113278391914, "grad_norm": 0.40332818031311035, "learning_rate": 1.9812979452836117e-05, "loss": 0.0378, "step": 990 }, { "epoch": 0.04537488159991832, "grad_norm": 0.3606199324131012, "learning_rate": 1.9807278938803853e-05, "loss": 0.0412, "step": 1000 }, { "epoch": 0.04582863041591751, "grad_norm": 0.25153085589408875, "learning_rate": 1.980149369128634e-05, "loss": 0.0355, "step": 1010 }, { "epoch": 0.04628237923191669, "grad_norm": 0.4468913674354553, "learning_rate": 1.9795623760267294e-05, "loss": 0.0346, "step": 1020 }, { "epoch": 0.046736128047915874, "grad_norm": 0.3290547728538513, "learning_rate": 1.9789669196462072e-05, "loss": 0.038, "step": 1030 }, { "epoch": 0.047189876863915056, "grad_norm": 0.2987779676914215, "learning_rate": 1.978363005131725e-05, "loss": 0.0361, "step": 1040 }, { "epoch": 0.047643625679914245, "grad_norm": 0.28201788663864136, "learning_rate": 1.9777506377010182e-05, "loss": 0.036, "step": 1050 }, { "epoch": 0.04809737449591343, "grad_norm": 0.26327061653137207, "learning_rate": 1.9771298226448535e-05, "loss": 0.0343, "step": 1060 }, { "epoch": 0.04855112331191261, "grad_norm": 0.28660938143730164, "learning_rate": 1.9765005653269842e-05, "loss": 0.0322, "step": 1070 }, { "epoch": 0.04900487212791179, "grad_norm": 0.40603259205818176, "learning_rate": 1.9758628711841035e-05, "loss": 0.0383, "step": 1080 }, { "epoch": 0.04945862094391097, "grad_norm": 0.3024589419364929, "learning_rate": 1.975216745725797e-05, "loss": 0.0382, "step": 1090 }, { "epoch": 0.04991236975991016, "grad_norm": 0.42686691880226135, "learning_rate": 1.974562194534496e-05, "loss": 0.035, "step": 1100 }, { "epoch": 0.05036611857590934, "grad_norm": 0.4532322585582733, "learning_rate": 1.9738992232654296e-05, "loss": 0.0359, "step": 1110 }, { "epoch": 0.050819867391908524, "grad_norm": 0.3654768764972687, "learning_rate": 1.9732278376465746e-05, "loss": 0.0383, "step": 1120 }, { "epoch": 0.051273616207907706, "grad_norm": 0.42380237579345703, "learning_rate": 1.9725480434786065e-05, "loss": 0.0289, "step": 1130 }, { "epoch": 0.05172736502390689, "grad_norm": 0.4129980802536011, "learning_rate": 1.971859846634849e-05, "loss": 0.0376, "step": 1140 }, { "epoch": 0.052181113839906076, "grad_norm": 0.3185942769050598, "learning_rate": 1.9711632530612247e-05, "loss": 0.0367, "step": 1150 }, { "epoch": 0.05263486265590526, "grad_norm": 0.39448460936546326, "learning_rate": 1.970458268776202e-05, "loss": 0.0341, "step": 1160 }, { "epoch": 0.05308861147190444, "grad_norm": 0.2636372745037079, "learning_rate": 1.9697448998707448e-05, "loss": 0.0337, "step": 1170 }, { "epoch": 0.05354236028790362, "grad_norm": 0.2591952681541443, "learning_rate": 1.9690231525082576e-05, "loss": 0.0351, "step": 1180 }, { "epoch": 0.05399610910390281, "grad_norm": 0.2932235300540924, "learning_rate": 1.968293032924535e-05, "loss": 0.0296, "step": 1190 }, { "epoch": 0.05444985791990199, "grad_norm": 0.4766691029071808, "learning_rate": 1.9675545474277045e-05, "loss": 0.0362, "step": 1200 }, { "epoch": 0.054903606735901174, "grad_norm": 0.3045652210712433, "learning_rate": 1.966807702398176e-05, "loss": 0.0305, "step": 1210 }, { "epoch": 0.055357355551900356, "grad_norm": 0.4340307116508484, "learning_rate": 1.9660525042885828e-05, "loss": 0.0331, "step": 1220 }, { "epoch": 0.05581110436789954, "grad_norm": 0.3498646020889282, "learning_rate": 1.965288959623729e-05, "loss": 0.0375, "step": 1230 }, { "epoch": 0.056264853183898726, "grad_norm": 0.37352198362350464, "learning_rate": 1.964517075000531e-05, "loss": 0.0392, "step": 1240 }, { "epoch": 0.05671860199989791, "grad_norm": 0.3399907648563385, "learning_rate": 1.9637368570879612e-05, "loss": 0.0348, "step": 1250 }, { "epoch": 0.05717235081589709, "grad_norm": 0.4306923449039459, "learning_rate": 1.9629483126269904e-05, "loss": 0.0418, "step": 1260 }, { "epoch": 0.05762609963189627, "grad_norm": 0.33894944190979004, "learning_rate": 1.9621514484305308e-05, "loss": 0.0356, "step": 1270 }, { "epoch": 0.05807984844789545, "grad_norm": 0.4175716042518616, "learning_rate": 1.9613462713833734e-05, "loss": 0.0376, "step": 1280 }, { "epoch": 0.05853359726389464, "grad_norm": 0.28998425602912903, "learning_rate": 1.9605327884421338e-05, "loss": 0.037, "step": 1290 }, { "epoch": 0.058987346079893824, "grad_norm": 0.39411577582359314, "learning_rate": 1.9597110066351875e-05, "loss": 0.0342, "step": 1300 }, { "epoch": 0.059441094895893005, "grad_norm": 0.2843569219112396, "learning_rate": 1.958880933062612e-05, "loss": 0.0328, "step": 1310 }, { "epoch": 0.05989484371189219, "grad_norm": 0.3382938504219055, "learning_rate": 1.958042574896124e-05, "loss": 0.0343, "step": 1320 }, { "epoch": 0.060348592527891376, "grad_norm": 0.3430584669113159, "learning_rate": 1.9571959393790174e-05, "loss": 0.0337, "step": 1330 }, { "epoch": 0.06080234134389056, "grad_norm": 0.3637918531894684, "learning_rate": 1.9563410338261022e-05, "loss": 0.0347, "step": 1340 }, { "epoch": 0.06125609015988974, "grad_norm": 0.34068816900253296, "learning_rate": 1.9554778656236402e-05, "loss": 0.0353, "step": 1350 }, { "epoch": 0.06170983897588892, "grad_norm": 0.316532701253891, "learning_rate": 1.9546064422292806e-05, "loss": 0.0319, "step": 1360 }, { "epoch": 0.0621635877918881, "grad_norm": 0.6372074484825134, "learning_rate": 1.9537267711719966e-05, "loss": 0.0384, "step": 1370 }, { "epoch": 0.06261733660788729, "grad_norm": 0.2703815996646881, "learning_rate": 1.9528388600520208e-05, "loss": 0.0335, "step": 1380 }, { "epoch": 0.06307108542388647, "grad_norm": 0.36061450839042664, "learning_rate": 1.9519427165407773e-05, "loss": 0.0324, "step": 1390 }, { "epoch": 0.06352483423988566, "grad_norm": 0.3043723702430725, "learning_rate": 1.9510383483808183e-05, "loss": 0.0332, "step": 1400 }, { "epoch": 0.06397858305588484, "grad_norm": 0.258369505405426, "learning_rate": 1.950125763385755e-05, "loss": 0.0301, "step": 1410 }, { "epoch": 0.06443233187188402, "grad_norm": 0.252562552690506, "learning_rate": 1.949204969440191e-05, "loss": 0.0361, "step": 1420 }, { "epoch": 0.06488608068788321, "grad_norm": 0.360517680644989, "learning_rate": 1.9482759744996537e-05, "loss": 0.035, "step": 1430 }, { "epoch": 0.06533982950388238, "grad_norm": 0.24595054984092712, "learning_rate": 1.9473387865905268e-05, "loss": 0.0364, "step": 1440 }, { "epoch": 0.06579357831988157, "grad_norm": 0.43690842390060425, "learning_rate": 1.9463934138099796e-05, "loss": 0.0342, "step": 1450 }, { "epoch": 0.06624732713588076, "grad_norm": 0.2412269413471222, "learning_rate": 1.945439864325897e-05, "loss": 0.031, "step": 1460 }, { "epoch": 0.06670107595187993, "grad_norm": 0.2904290556907654, "learning_rate": 1.944478146376811e-05, "loss": 0.0376, "step": 1470 }, { "epoch": 0.06715482476787912, "grad_norm": 0.3700315058231354, "learning_rate": 1.943508268271826e-05, "loss": 0.0355, "step": 1480 }, { "epoch": 0.0676085735838783, "grad_norm": 0.35990333557128906, "learning_rate": 1.9425302383905497e-05, "loss": 0.0344, "step": 1490 }, { "epoch": 0.06806232239987749, "grad_norm": 0.3826255202293396, "learning_rate": 1.941544065183021e-05, "loss": 0.0354, "step": 1500 }, { "epoch": 0.06851607121587668, "grad_norm": 0.34334129095077515, "learning_rate": 1.9405497571696347e-05, "loss": 0.0328, "step": 1510 }, { "epoch": 0.06896982003187585, "grad_norm": 0.2816310524940491, "learning_rate": 1.93954732294107e-05, "loss": 0.0335, "step": 1520 }, { "epoch": 0.06942356884787504, "grad_norm": 0.3202529847621918, "learning_rate": 1.9385367711582142e-05, "loss": 0.03, "step": 1530 }, { "epoch": 0.06987731766387423, "grad_norm": 0.3331971764564514, "learning_rate": 1.9375181105520907e-05, "loss": 0.0303, "step": 1540 }, { "epoch": 0.0703310664798734, "grad_norm": 0.2520907521247864, "learning_rate": 1.9364913499237814e-05, "loss": 0.0263, "step": 1550 }, { "epoch": 0.07078481529587259, "grad_norm": 0.2967125475406647, "learning_rate": 1.93545649814435e-05, "loss": 0.0276, "step": 1560 }, { "epoch": 0.07123856411187177, "grad_norm": 0.289743572473526, "learning_rate": 1.934413564154769e-05, "loss": 0.0275, "step": 1570 }, { "epoch": 0.07169231292787095, "grad_norm": 0.4368985593318939, "learning_rate": 1.9333625569658377e-05, "loss": 0.0381, "step": 1580 }, { "epoch": 0.07214606174387014, "grad_norm": 0.264926016330719, "learning_rate": 1.9323034856581083e-05, "loss": 0.0299, "step": 1590 }, { "epoch": 0.07259981055986932, "grad_norm": 0.3302227258682251, "learning_rate": 1.9312363593818045e-05, "loss": 0.0355, "step": 1600 }, { "epoch": 0.07305355937586851, "grad_norm": 0.386764258146286, "learning_rate": 1.930161187356745e-05, "loss": 0.0295, "step": 1610 }, { "epoch": 0.07350730819186768, "grad_norm": 0.44839608669281006, "learning_rate": 1.929077978872262e-05, "loss": 0.0356, "step": 1620 }, { "epoch": 0.07396105700786687, "grad_norm": 0.3206934630870819, "learning_rate": 1.9279867432871215e-05, "loss": 0.0322, "step": 1630 }, { "epoch": 0.07441480582386606, "grad_norm": 0.3327983617782593, "learning_rate": 1.9268874900294426e-05, "loss": 0.0348, "step": 1640 }, { "epoch": 0.07486855463986523, "grad_norm": 0.3196796476840973, "learning_rate": 1.9257802285966166e-05, "loss": 0.0309, "step": 1650 }, { "epoch": 0.07532230345586442, "grad_norm": 0.34416893124580383, "learning_rate": 1.924664968555223e-05, "loss": 0.0333, "step": 1660 }, { "epoch": 0.0757760522718636, "grad_norm": 0.38334083557128906, "learning_rate": 1.9235417195409487e-05, "loss": 0.0305, "step": 1670 }, { "epoch": 0.07622980108786279, "grad_norm": 0.4142295718193054, "learning_rate": 1.922410491258505e-05, "loss": 0.0333, "step": 1680 }, { "epoch": 0.07668354990386198, "grad_norm": 0.4339887797832489, "learning_rate": 1.9212712934815413e-05, "loss": 0.0387, "step": 1690 }, { "epoch": 0.07713729871986115, "grad_norm": 0.3214190900325775, "learning_rate": 1.9201241360525643e-05, "loss": 0.0328, "step": 1700 }, { "epoch": 0.07759104753586034, "grad_norm": 0.3599112927913666, "learning_rate": 1.9189690288828487e-05, "loss": 0.0331, "step": 1710 }, { "epoch": 0.07804479635185951, "grad_norm": 0.27780184149742126, "learning_rate": 1.9178059819523563e-05, "loss": 0.0307, "step": 1720 }, { "epoch": 0.0784985451678587, "grad_norm": 0.3802540898323059, "learning_rate": 1.9166350053096453e-05, "loss": 0.0342, "step": 1730 }, { "epoch": 0.07895229398385789, "grad_norm": 0.23420991003513336, "learning_rate": 1.9154561090717857e-05, "loss": 0.0304, "step": 1740 }, { "epoch": 0.07940604279985707, "grad_norm": 0.8895495533943176, "learning_rate": 1.9142693034242726e-05, "loss": 0.0317, "step": 1750 }, { "epoch": 0.07985979161585625, "grad_norm": 0.3928177058696747, "learning_rate": 1.913074598620937e-05, "loss": 0.0299, "step": 1760 }, { "epoch": 0.08031354043185543, "grad_norm": 0.2376619130373001, "learning_rate": 1.9118720049838567e-05, "loss": 0.029, "step": 1770 }, { "epoch": 0.08076728924785462, "grad_norm": 0.28894445300102234, "learning_rate": 1.9106615329032695e-05, "loss": 0.0324, "step": 1780 }, { "epoch": 0.0812210380638538, "grad_norm": 0.2802739441394806, "learning_rate": 1.9094431928374798e-05, "loss": 0.0313, "step": 1790 }, { "epoch": 0.08167478687985298, "grad_norm": 0.34238293766975403, "learning_rate": 1.9082169953127714e-05, "loss": 0.0308, "step": 1800 }, { "epoch": 0.08212853569585217, "grad_norm": 0.26249805092811584, "learning_rate": 1.9069829509233156e-05, "loss": 0.0284, "step": 1810 }, { "epoch": 0.08258228451185136, "grad_norm": 0.2603767216205597, "learning_rate": 1.9057410703310788e-05, "loss": 0.0306, "step": 1820 }, { "epoch": 0.08303603332785053, "grad_norm": 0.2957773506641388, "learning_rate": 1.9044913642657318e-05, "loss": 0.0331, "step": 1830 }, { "epoch": 0.08348978214384972, "grad_norm": 0.3028935492038727, "learning_rate": 1.9032338435245557e-05, "loss": 0.0329, "step": 1840 }, { "epoch": 0.0839435309598489, "grad_norm": 0.38610896468162537, "learning_rate": 1.9019685189723497e-05, "loss": 0.034, "step": 1850 }, { "epoch": 0.08439727977584809, "grad_norm": 0.36832401156425476, "learning_rate": 1.900695401541337e-05, "loss": 0.031, "step": 1860 }, { "epoch": 0.08485102859184727, "grad_norm": 0.48249903321266174, "learning_rate": 1.8994145022310693e-05, "loss": 0.0293, "step": 1870 }, { "epoch": 0.08530477740784645, "grad_norm": 0.31096184253692627, "learning_rate": 1.8981258321083335e-05, "loss": 0.0304, "step": 1880 }, { "epoch": 0.08575852622384564, "grad_norm": 0.32061338424682617, "learning_rate": 1.8968294023070548e-05, "loss": 0.0283, "step": 1890 }, { "epoch": 0.08621227503984481, "grad_norm": 0.3455403447151184, "learning_rate": 1.895525224028201e-05, "loss": 0.0317, "step": 1900 }, { "epoch": 0.086666023855844, "grad_norm": 0.32893112301826477, "learning_rate": 1.8942133085396855e-05, "loss": 0.0283, "step": 1910 }, { "epoch": 0.08711977267184319, "grad_norm": 0.30369892716407776, "learning_rate": 1.8928936671762704e-05, "loss": 0.0312, "step": 1920 }, { "epoch": 0.08757352148784237, "grad_norm": 0.37458205223083496, "learning_rate": 1.8915663113394677e-05, "loss": 0.0305, "step": 1930 }, { "epoch": 0.08802727030384155, "grad_norm": 0.37972351908683777, "learning_rate": 1.890231252497442e-05, "loss": 0.0288, "step": 1940 }, { "epoch": 0.08848101911984073, "grad_norm": 0.32377856969833374, "learning_rate": 1.8888885021849103e-05, "loss": 0.0307, "step": 1950 }, { "epoch": 0.08893476793583992, "grad_norm": 0.3826766312122345, "learning_rate": 1.8875380720030434e-05, "loss": 0.0342, "step": 1960 }, { "epoch": 0.0893885167518391, "grad_norm": 0.3065117597579956, "learning_rate": 1.886179973619364e-05, "loss": 0.0354, "step": 1970 }, { "epoch": 0.08984226556783828, "grad_norm": 0.35128670930862427, "learning_rate": 1.8848142187676485e-05, "loss": 0.0293, "step": 1980 }, { "epoch": 0.09029601438383747, "grad_norm": 0.21569295227527618, "learning_rate": 1.883440819247822e-05, "loss": 0.0353, "step": 1990 }, { "epoch": 0.09074976319983664, "grad_norm": 0.21139784157276154, "learning_rate": 1.8820597869258606e-05, "loss": 0.0302, "step": 2000 }, { "epoch": 0.09120351201583583, "grad_norm": 0.2579706609249115, "learning_rate": 1.8806711337336852e-05, "loss": 0.0291, "step": 2010 }, { "epoch": 0.09165726083183502, "grad_norm": 0.2702217102050781, "learning_rate": 1.8792748716690608e-05, "loss": 0.0351, "step": 2020 }, { "epoch": 0.0921110096478342, "grad_norm": 0.32564353942871094, "learning_rate": 1.8778710127954912e-05, "loss": 0.0329, "step": 2030 }, { "epoch": 0.09256475846383339, "grad_norm": 0.28494423627853394, "learning_rate": 1.8764595692421163e-05, "loss": 0.0298, "step": 2040 }, { "epoch": 0.09301850727983256, "grad_norm": 0.3416655659675598, "learning_rate": 1.8750405532036064e-05, "loss": 0.0311, "step": 2050 }, { "epoch": 0.09347225609583175, "grad_norm": 0.27889978885650635, "learning_rate": 1.8736139769400567e-05, "loss": 0.0316, "step": 2060 }, { "epoch": 0.09392600491183094, "grad_norm": 0.27466732263565063, "learning_rate": 1.8721798527768813e-05, "loss": 0.0311, "step": 2070 }, { "epoch": 0.09437975372783011, "grad_norm": 0.2739962935447693, "learning_rate": 1.870738193104708e-05, "loss": 0.0307, "step": 2080 }, { "epoch": 0.0948335025438293, "grad_norm": 0.18930114805698395, "learning_rate": 1.86928901037927e-05, "loss": 0.0285, "step": 2090 }, { "epoch": 0.09528725135982849, "grad_norm": 0.27138862013816833, "learning_rate": 1.8678323171212982e-05, "loss": 0.0345, "step": 2100 }, { "epoch": 0.09574100017582766, "grad_norm": 0.30654940009117126, "learning_rate": 1.866368125916414e-05, "loss": 0.027, "step": 2110 }, { "epoch": 0.09619474899182685, "grad_norm": 0.2858283221721649, "learning_rate": 1.864896449415019e-05, "loss": 0.024, "step": 2120 }, { "epoch": 0.09664849780782603, "grad_norm": 0.34073856472969055, "learning_rate": 1.863417300332188e-05, "loss": 0.0296, "step": 2130 }, { "epoch": 0.09710224662382522, "grad_norm": 0.27456143498420715, "learning_rate": 1.8619306914475573e-05, "loss": 0.0289, "step": 2140 }, { "epoch": 0.0975559954398244, "grad_norm": 0.22514624893665314, "learning_rate": 1.860436635605214e-05, "loss": 0.0332, "step": 2150 }, { "epoch": 0.09800974425582358, "grad_norm": 0.3091515600681305, "learning_rate": 1.8589351457135873e-05, "loss": 0.0285, "step": 2160 }, { "epoch": 0.09846349307182277, "grad_norm": 0.27328723669052124, "learning_rate": 1.8574262347453344e-05, "loss": 0.0309, "step": 2170 }, { "epoch": 0.09891724188782194, "grad_norm": 0.31947243213653564, "learning_rate": 1.85590991573723e-05, "loss": 0.0286, "step": 2180 }, { "epoch": 0.09937099070382113, "grad_norm": 0.25883498787879944, "learning_rate": 1.854386201790053e-05, "loss": 0.0266, "step": 2190 }, { "epoch": 0.09982473951982032, "grad_norm": 0.3067774474620819, "learning_rate": 1.8528551060684744e-05, "loss": 0.0303, "step": 2200 }, { "epoch": 0.1002784883358195, "grad_norm": 0.2517601251602173, "learning_rate": 1.851316641800941e-05, "loss": 0.0285, "step": 2210 }, { "epoch": 0.10073223715181868, "grad_norm": 0.22742106020450592, "learning_rate": 1.8497708222795638e-05, "loss": 0.0289, "step": 2220 }, { "epoch": 0.10118598596781786, "grad_norm": 0.2637586295604706, "learning_rate": 1.8482176608600025e-05, "loss": 0.03, "step": 2230 }, { "epoch": 0.10163973478381705, "grad_norm": 0.36147263646125793, "learning_rate": 1.846657170961349e-05, "loss": 0.0318, "step": 2240 }, { "epoch": 0.10209348359981624, "grad_norm": 0.5150363445281982, "learning_rate": 1.8450893660660126e-05, "loss": 0.0311, "step": 2250 }, { "epoch": 0.10254723241581541, "grad_norm": 0.24777275323867798, "learning_rate": 1.8435142597196033e-05, "loss": 0.0295, "step": 2260 }, { "epoch": 0.1030009812318146, "grad_norm": 0.3939498960971832, "learning_rate": 1.8419318655308135e-05, "loss": 0.0306, "step": 2270 }, { "epoch": 0.10345473004781378, "grad_norm": 0.3375140428543091, "learning_rate": 1.8403421971713034e-05, "loss": 0.0298, "step": 2280 }, { "epoch": 0.10390847886381296, "grad_norm": 0.26304638385772705, "learning_rate": 1.838745268375579e-05, "loss": 0.028, "step": 2290 }, { "epoch": 0.10436222767981215, "grad_norm": 0.3489622473716736, "learning_rate": 1.8371410929408767e-05, "loss": 0.0298, "step": 2300 }, { "epoch": 0.10481597649581133, "grad_norm": 0.3099193572998047, "learning_rate": 1.835529684727043e-05, "loss": 0.0251, "step": 2310 }, { "epoch": 0.10526972531181052, "grad_norm": 0.3792000710964203, "learning_rate": 1.8339110576564132e-05, "loss": 0.0232, "step": 2320 }, { "epoch": 0.10572347412780969, "grad_norm": 0.331638902425766, "learning_rate": 1.8322852257136935e-05, "loss": 0.0264, "step": 2330 }, { "epoch": 0.10617722294380888, "grad_norm": 0.2860846519470215, "learning_rate": 1.8306522029458395e-05, "loss": 0.0256, "step": 2340 }, { "epoch": 0.10663097175980807, "grad_norm": 0.2908225953578949, "learning_rate": 1.8290120034619335e-05, "loss": 0.0296, "step": 2350 }, { "epoch": 0.10708472057580724, "grad_norm": 0.32988736033439636, "learning_rate": 1.8273646414330645e-05, "loss": 0.0291, "step": 2360 }, { "epoch": 0.10753846939180643, "grad_norm": 0.3163841962814331, "learning_rate": 1.8257101310922042e-05, "loss": 0.0304, "step": 2370 }, { "epoch": 0.10799221820780562, "grad_norm": 0.25633612275123596, "learning_rate": 1.8240484867340852e-05, "loss": 0.0242, "step": 2380 }, { "epoch": 0.1084459670238048, "grad_norm": 0.27588725090026855, "learning_rate": 1.8223797227150762e-05, "loss": 0.0307, "step": 2390 }, { "epoch": 0.10889971583980398, "grad_norm": 0.2671939432621002, "learning_rate": 1.8207038534530598e-05, "loss": 0.0304, "step": 2400 }, { "epoch": 0.10935346465580316, "grad_norm": 0.24775387346744537, "learning_rate": 1.819020893427306e-05, "loss": 0.0235, "step": 2410 }, { "epoch": 0.10980721347180235, "grad_norm": 0.33271005749702454, "learning_rate": 1.817330857178349e-05, "loss": 0.0319, "step": 2420 }, { "epoch": 0.11026096228780154, "grad_norm": 0.28772467374801636, "learning_rate": 1.8156337593078594e-05, "loss": 0.0277, "step": 2430 }, { "epoch": 0.11071471110380071, "grad_norm": 0.33726418018341064, "learning_rate": 1.81392961447852e-05, "loss": 0.0259, "step": 2440 }, { "epoch": 0.1111684599197999, "grad_norm": 0.2909960448741913, "learning_rate": 1.8122184374138973e-05, "loss": 0.0268, "step": 2450 }, { "epoch": 0.11162220873579907, "grad_norm": 0.2372504621744156, "learning_rate": 1.810500242898317e-05, "loss": 0.0289, "step": 2460 }, { "epoch": 0.11207595755179826, "grad_norm": 0.22281192243099213, "learning_rate": 1.808775045776733e-05, "loss": 0.029, "step": 2470 }, { "epoch": 0.11252970636779745, "grad_norm": 0.3162948191165924, "learning_rate": 1.8070428609546012e-05, "loss": 0.0299, "step": 2480 }, { "epoch": 0.11298345518379663, "grad_norm": 0.31078866124153137, "learning_rate": 1.8053037033977513e-05, "loss": 0.0246, "step": 2490 }, { "epoch": 0.11343720399979582, "grad_norm": 0.32280248403549194, "learning_rate": 1.803557588132254e-05, "loss": 0.0282, "step": 2500 }, { "epoch": 0.11389095281579499, "grad_norm": 0.3646463453769684, "learning_rate": 1.8018045302442966e-05, "loss": 0.0312, "step": 2510 }, { "epoch": 0.11434470163179418, "grad_norm": 0.29229217767715454, "learning_rate": 1.8000445448800473e-05, "loss": 0.0259, "step": 2520 }, { "epoch": 0.11479845044779337, "grad_norm": 0.2488923817873001, "learning_rate": 1.7982776472455274e-05, "loss": 0.0287, "step": 2530 }, { "epoch": 0.11525219926379254, "grad_norm": 0.2847914397716522, "learning_rate": 1.7965038526064796e-05, "loss": 0.0345, "step": 2540 }, { "epoch": 0.11570594807979173, "grad_norm": 0.2764897048473358, "learning_rate": 1.794723176288236e-05, "loss": 0.0276, "step": 2550 }, { "epoch": 0.1161596968957909, "grad_norm": 0.3651575744152069, "learning_rate": 1.7929356336755842e-05, "loss": 0.029, "step": 2560 }, { "epoch": 0.1166134457117901, "grad_norm": 0.34031009674072266, "learning_rate": 1.7911412402126366e-05, "loss": 0.0305, "step": 2570 }, { "epoch": 0.11706719452778928, "grad_norm": 0.2787719666957855, "learning_rate": 1.789340011402696e-05, "loss": 0.032, "step": 2580 }, { "epoch": 0.11752094334378846, "grad_norm": 0.3492062985897064, "learning_rate": 1.7875319628081205e-05, "loss": 0.0268, "step": 2590 }, { "epoch": 0.11797469215978765, "grad_norm": 0.32178348302841187, "learning_rate": 1.785717110050192e-05, "loss": 0.0293, "step": 2600 }, { "epoch": 0.11842844097578682, "grad_norm": 0.4119739532470703, "learning_rate": 1.7838954688089777e-05, "loss": 0.0268, "step": 2610 }, { "epoch": 0.11888218979178601, "grad_norm": 0.25727635622024536, "learning_rate": 1.782067054823197e-05, "loss": 0.0286, "step": 2620 }, { "epoch": 0.1193359386077852, "grad_norm": 0.3362247049808502, "learning_rate": 1.7802318838900855e-05, "loss": 0.0301, "step": 2630 }, { "epoch": 0.11978968742378437, "grad_norm": 0.3058724105358124, "learning_rate": 1.7783899718652563e-05, "loss": 0.0261, "step": 2640 }, { "epoch": 0.12024343623978356, "grad_norm": 0.2798862159252167, "learning_rate": 1.776541334662566e-05, "loss": 0.0285, "step": 2650 }, { "epoch": 0.12069718505578275, "grad_norm": 0.29817041754722595, "learning_rate": 1.7746859882539747e-05, "loss": 0.027, "step": 2660 }, { "epoch": 0.12115093387178193, "grad_norm": 0.3289836049079895, "learning_rate": 1.7728239486694104e-05, "loss": 0.0309, "step": 2670 }, { "epoch": 0.12160468268778112, "grad_norm": 0.173284113407135, "learning_rate": 1.7709552319966275e-05, "loss": 0.0285, "step": 2680 }, { "epoch": 0.12205843150378029, "grad_norm": 0.3170483112335205, "learning_rate": 1.7690798543810715e-05, "loss": 0.03, "step": 2690 }, { "epoch": 0.12251218031977948, "grad_norm": 0.3354043662548065, "learning_rate": 1.7671978320257356e-05, "loss": 0.0297, "step": 2700 }, { "epoch": 0.12296592913577867, "grad_norm": 0.27378806471824646, "learning_rate": 1.7653091811910236e-05, "loss": 0.0255, "step": 2710 }, { "epoch": 0.12341967795177784, "grad_norm": 0.2813524901866913, "learning_rate": 1.763413918194608e-05, "loss": 0.0316, "step": 2720 }, { "epoch": 0.12387342676777703, "grad_norm": 0.24198800325393677, "learning_rate": 1.7615120594112895e-05, "loss": 0.0222, "step": 2730 }, { "epoch": 0.1243271755837762, "grad_norm": 0.25822484493255615, "learning_rate": 1.7596036212728558e-05, "loss": 0.0262, "step": 2740 }, { "epoch": 0.1247809243997754, "grad_norm": 0.2108188271522522, "learning_rate": 1.757688620267939e-05, "loss": 0.031, "step": 2750 }, { "epoch": 0.12523467321577458, "grad_norm": 0.2143239825963974, "learning_rate": 1.755767072941874e-05, "loss": 0.0286, "step": 2760 }, { "epoch": 0.12568842203177377, "grad_norm": 0.25193849205970764, "learning_rate": 1.7538389958965537e-05, "loss": 0.0319, "step": 2770 }, { "epoch": 0.12614217084777293, "grad_norm": 0.21443508565425873, "learning_rate": 1.7519044057902877e-05, "loss": 0.0284, "step": 2780 }, { "epoch": 0.12659591966377212, "grad_norm": 0.2336062341928482, "learning_rate": 1.749963319337658e-05, "loss": 0.0311, "step": 2790 }, { "epoch": 0.1270496684797713, "grad_norm": 0.30402058362960815, "learning_rate": 1.748015753309373e-05, "loss": 0.025, "step": 2800 }, { "epoch": 0.1275034172957705, "grad_norm": 0.2584312856197357, "learning_rate": 1.746061724532124e-05, "loss": 0.0289, "step": 2810 }, { "epoch": 0.1279571661117697, "grad_norm": 0.2967812418937683, "learning_rate": 1.7441012498884402e-05, "loss": 0.0252, "step": 2820 }, { "epoch": 0.12841091492776885, "grad_norm": 0.22338618338108063, "learning_rate": 1.7421343463165415e-05, "loss": 0.0278, "step": 2830 }, { "epoch": 0.12886466374376804, "grad_norm": 0.3240523636341095, "learning_rate": 1.7401610308101933e-05, "loss": 0.0265, "step": 2840 }, { "epoch": 0.12931841255976723, "grad_norm": 0.20629672706127167, "learning_rate": 1.7381813204185585e-05, "loss": 0.0235, "step": 2850 }, { "epoch": 0.12977216137576641, "grad_norm": 0.2057785987854004, "learning_rate": 1.7361952322460513e-05, "loss": 0.0266, "step": 2860 }, { "epoch": 0.1302259101917656, "grad_norm": 0.28149768710136414, "learning_rate": 1.7342027834521896e-05, "loss": 0.0247, "step": 2870 }, { "epoch": 0.13067965900776476, "grad_norm": 0.38402533531188965, "learning_rate": 1.7322039912514453e-05, "loss": 0.0213, "step": 2880 }, { "epoch": 0.13113340782376395, "grad_norm": 0.25240465998649597, "learning_rate": 1.7301988729130964e-05, "loss": 0.0246, "step": 2890 }, { "epoch": 0.13158715663976314, "grad_norm": 0.27071118354797363, "learning_rate": 1.7281874457610787e-05, "loss": 0.0247, "step": 2900 }, { "epoch": 0.13204090545576233, "grad_norm": 0.27154409885406494, "learning_rate": 1.7261697271738337e-05, "loss": 0.0299, "step": 2910 }, { "epoch": 0.13249465427176152, "grad_norm": 0.2589960992336273, "learning_rate": 1.724145734584162e-05, "loss": 0.0258, "step": 2920 }, { "epoch": 0.13294840308776068, "grad_norm": 0.26980119943618774, "learning_rate": 1.7221154854790696e-05, "loss": 0.0241, "step": 2930 }, { "epoch": 0.13340215190375987, "grad_norm": 0.3216455578804016, "learning_rate": 1.7200789973996172e-05, "loss": 0.0273, "step": 2940 }, { "epoch": 0.13385590071975906, "grad_norm": 0.25037115812301636, "learning_rate": 1.7180362879407707e-05, "loss": 0.0274, "step": 2950 }, { "epoch": 0.13430964953575825, "grad_norm": 0.25473201274871826, "learning_rate": 1.7159873747512472e-05, "loss": 0.0271, "step": 2960 }, { "epoch": 0.13476339835175744, "grad_norm": 0.25574159622192383, "learning_rate": 1.713932275533363e-05, "loss": 0.0278, "step": 2970 }, { "epoch": 0.1352171471677566, "grad_norm": 0.25640445947647095, "learning_rate": 1.7118710080428807e-05, "loss": 0.0263, "step": 2980 }, { "epoch": 0.13567089598375578, "grad_norm": 0.3601659834384918, "learning_rate": 1.7098035900888566e-05, "loss": 0.0274, "step": 2990 }, { "epoch": 0.13612464479975497, "grad_norm": 0.2547258138656616, "learning_rate": 1.7077300395334857e-05, "loss": 0.0315, "step": 3000 }, { "epoch": 0.13657839361575416, "grad_norm": 0.3644275367259979, "learning_rate": 1.7056503742919476e-05, "loss": 0.0282, "step": 3010 }, { "epoch": 0.13703214243175335, "grad_norm": 0.36293908953666687, "learning_rate": 1.703564612332252e-05, "loss": 0.0265, "step": 3020 }, { "epoch": 0.1374858912477525, "grad_norm": 0.21777909994125366, "learning_rate": 1.7014727716750842e-05, "loss": 0.0271, "step": 3030 }, { "epoch": 0.1379396400637517, "grad_norm": 0.29701927304267883, "learning_rate": 1.699374870393647e-05, "loss": 0.0252, "step": 3040 }, { "epoch": 0.1383933888797509, "grad_norm": 0.2054390013217926, "learning_rate": 1.697270926613507e-05, "loss": 0.026, "step": 3050 }, { "epoch": 0.13884713769575008, "grad_norm": 0.37679630517959595, "learning_rate": 1.6951609585124377e-05, "loss": 0.0316, "step": 3060 }, { "epoch": 0.13930088651174927, "grad_norm": 0.2522611618041992, "learning_rate": 1.6930449843202607e-05, "loss": 0.0271, "step": 3070 }, { "epoch": 0.13975463532774846, "grad_norm": 0.19608336687088013, "learning_rate": 1.69092302231869e-05, "loss": 0.0298, "step": 3080 }, { "epoch": 0.14020838414374762, "grad_norm": 0.2465701699256897, "learning_rate": 1.688795090841173e-05, "loss": 0.0251, "step": 3090 }, { "epoch": 0.1406621329597468, "grad_norm": 0.25562769174575806, "learning_rate": 1.686661208272734e-05, "loss": 0.0275, "step": 3100 }, { "epoch": 0.141115881775746, "grad_norm": 0.25319865345954895, "learning_rate": 1.6845213930498122e-05, "loss": 0.025, "step": 3110 }, { "epoch": 0.14156963059174518, "grad_norm": 0.24400335550308228, "learning_rate": 1.682375663660104e-05, "loss": 0.0259, "step": 3120 }, { "epoch": 0.14202337940774437, "grad_norm": 0.2539372742176056, "learning_rate": 1.680224038642405e-05, "loss": 0.0248, "step": 3130 }, { "epoch": 0.14247712822374353, "grad_norm": 0.2774992883205414, "learning_rate": 1.6780665365864465e-05, "loss": 0.0261, "step": 3140 }, { "epoch": 0.14293087703974272, "grad_norm": 0.2580750584602356, "learning_rate": 1.675903176132737e-05, "loss": 0.0242, "step": 3150 }, { "epoch": 0.1433846258557419, "grad_norm": 0.2549765408039093, "learning_rate": 1.6737339759724016e-05, "loss": 0.028, "step": 3160 }, { "epoch": 0.1438383746717411, "grad_norm": 0.26354891061782837, "learning_rate": 1.6715589548470187e-05, "loss": 0.0289, "step": 3170 }, { "epoch": 0.1442921234877403, "grad_norm": 0.22372102737426758, "learning_rate": 1.669378131548459e-05, "loss": 0.0284, "step": 3180 }, { "epoch": 0.14474587230373945, "grad_norm": 0.2107868492603302, "learning_rate": 1.6671915249187237e-05, "loss": 0.0229, "step": 3190 }, { "epoch": 0.14519962111973864, "grad_norm": 0.22089707851409912, "learning_rate": 1.6649991538497808e-05, "loss": 0.0251, "step": 3200 }, { "epoch": 0.14565336993573783, "grad_norm": 0.3006632328033447, "learning_rate": 1.6628010372834028e-05, "loss": 0.0318, "step": 3210 }, { "epoch": 0.14610711875173701, "grad_norm": 0.2658555507659912, "learning_rate": 1.660597194211001e-05, "loss": 0.0274, "step": 3220 }, { "epoch": 0.1465608675677362, "grad_norm": 0.22072288393974304, "learning_rate": 1.6583876436734646e-05, "loss": 0.0269, "step": 3230 }, { "epoch": 0.14701461638373536, "grad_norm": 0.3072430491447449, "learning_rate": 1.6561724047609936e-05, "loss": 0.0264, "step": 3240 }, { "epoch": 0.14746836519973455, "grad_norm": 0.4599568843841553, "learning_rate": 1.653951496612935e-05, "loss": 0.0207, "step": 3250 }, { "epoch": 0.14792211401573374, "grad_norm": 0.2594718337059021, "learning_rate": 1.6517249384176163e-05, "loss": 0.0211, "step": 3260 }, { "epoch": 0.14837586283173293, "grad_norm": 0.2798243761062622, "learning_rate": 1.6494927494121827e-05, "loss": 0.0246, "step": 3270 }, { "epoch": 0.14882961164773212, "grad_norm": 0.19761539995670319, "learning_rate": 1.647254948882426e-05, "loss": 0.0247, "step": 3280 }, { "epoch": 0.14928336046373128, "grad_norm": 0.2450396865606308, "learning_rate": 1.6450115561626237e-05, "loss": 0.0287, "step": 3290 }, { "epoch": 0.14973710927973047, "grad_norm": 0.25491470098495483, "learning_rate": 1.6427625906353667e-05, "loss": 0.0232, "step": 3300 }, { "epoch": 0.15019085809572966, "grad_norm": 0.25086021423339844, "learning_rate": 1.640508071731395e-05, "loss": 0.0277, "step": 3310 }, { "epoch": 0.15064460691172885, "grad_norm": 0.2692717909812927, "learning_rate": 1.6382480189294293e-05, "loss": 0.0197, "step": 3320 }, { "epoch": 0.15109835572772803, "grad_norm": 0.3244743347167969, "learning_rate": 1.635982451756002e-05, "loss": 0.0277, "step": 3330 }, { "epoch": 0.1515521045437272, "grad_norm": 0.2201894372701645, "learning_rate": 1.6337113897852887e-05, "loss": 0.0229, "step": 3340 }, { "epoch": 0.15200585335972638, "grad_norm": 0.3154199719429016, "learning_rate": 1.6314348526389396e-05, "loss": 0.0239, "step": 3350 }, { "epoch": 0.15245960217572557, "grad_norm": 0.22669443488121033, "learning_rate": 1.6291528599859102e-05, "loss": 0.0226, "step": 3360 }, { "epoch": 0.15291335099172476, "grad_norm": 0.29263025522232056, "learning_rate": 1.6268654315422892e-05, "loss": 0.028, "step": 3370 }, { "epoch": 0.15336709980772395, "grad_norm": 0.26775825023651123, "learning_rate": 1.6245725870711314e-05, "loss": 0.0262, "step": 3380 }, { "epoch": 0.1538208486237231, "grad_norm": 0.22253678739070892, "learning_rate": 1.6222743463822842e-05, "loss": 0.0223, "step": 3390 }, { "epoch": 0.1542745974397223, "grad_norm": 0.22490747272968292, "learning_rate": 1.6199707293322183e-05, "loss": 0.0246, "step": 3400 }, { "epoch": 0.1547283462557215, "grad_norm": 0.2597646713256836, "learning_rate": 1.6176617558238548e-05, "loss": 0.0301, "step": 3410 }, { "epoch": 0.15518209507172068, "grad_norm": 0.25990933179855347, "learning_rate": 1.615347445806394e-05, "loss": 0.0284, "step": 3420 }, { "epoch": 0.15563584388771987, "grad_norm": 0.2789154052734375, "learning_rate": 1.613027819275143e-05, "loss": 0.0255, "step": 3430 }, { "epoch": 0.15608959270371903, "grad_norm": 0.20941248536109924, "learning_rate": 1.6107028962713433e-05, "loss": 0.0252, "step": 3440 }, { "epoch": 0.15654334151971822, "grad_norm": 0.25744035840034485, "learning_rate": 1.608372696881996e-05, "loss": 0.0245, "step": 3450 }, { "epoch": 0.1569970903357174, "grad_norm": 0.2746187448501587, "learning_rate": 1.60603724123969e-05, "loss": 0.0243, "step": 3460 }, { "epoch": 0.1574508391517166, "grad_norm": 0.2338806539773941, "learning_rate": 1.603696549522428e-05, "loss": 0.0247, "step": 3470 }, { "epoch": 0.15790458796771578, "grad_norm": 0.21809513866901398, "learning_rate": 1.6013506419534505e-05, "loss": 0.0264, "step": 3480 }, { "epoch": 0.15835833678371494, "grad_norm": 0.26406624913215637, "learning_rate": 1.598999538801064e-05, "loss": 0.0232, "step": 3490 }, { "epoch": 0.15881208559971413, "grad_norm": 0.2770031988620758, "learning_rate": 1.5966432603784615e-05, "loss": 0.0249, "step": 3500 }, { "epoch": 0.15926583441571332, "grad_norm": 0.24770036339759827, "learning_rate": 1.594281827043552e-05, "loss": 0.0251, "step": 3510 }, { "epoch": 0.1597195832317125, "grad_norm": 0.3185284435749054, "learning_rate": 1.5919152591987814e-05, "loss": 0.0222, "step": 3520 }, { "epoch": 0.1601733320477117, "grad_norm": 0.1981068253517151, "learning_rate": 1.5895435772909564e-05, "loss": 0.0231, "step": 3530 }, { "epoch": 0.16062708086371086, "grad_norm": 0.24820560216903687, "learning_rate": 1.5871668018110694e-05, "loss": 0.0292, "step": 3540 }, { "epoch": 0.16108082967971005, "grad_norm": 0.20463721454143524, "learning_rate": 1.5847849532941196e-05, "loss": 0.0244, "step": 3550 }, { "epoch": 0.16153457849570924, "grad_norm": 0.32387474179267883, "learning_rate": 1.5823980523189373e-05, "loss": 0.0218, "step": 3560 }, { "epoch": 0.16198832731170842, "grad_norm": 0.23134641349315643, "learning_rate": 1.580006119508005e-05, "loss": 0.0235, "step": 3570 }, { "epoch": 0.1624420761277076, "grad_norm": 0.28199976682662964, "learning_rate": 1.5776091755272792e-05, "loss": 0.0221, "step": 3580 }, { "epoch": 0.16289582494370677, "grad_norm": 0.28213533759117126, "learning_rate": 1.5752072410860132e-05, "loss": 0.0309, "step": 3590 }, { "epoch": 0.16334957375970596, "grad_norm": 0.27364757657051086, "learning_rate": 1.5728003369365763e-05, "loss": 0.0242, "step": 3600 }, { "epoch": 0.16380332257570515, "grad_norm": 0.22550217807292938, "learning_rate": 1.5703884838742755e-05, "loss": 0.0256, "step": 3610 }, { "epoch": 0.16425707139170434, "grad_norm": 0.2727542221546173, "learning_rate": 1.5679717027371756e-05, "loss": 0.0264, "step": 3620 }, { "epoch": 0.16471082020770353, "grad_norm": 0.2520122230052948, "learning_rate": 1.5655500144059202e-05, "loss": 0.0225, "step": 3630 }, { "epoch": 0.16516456902370272, "grad_norm": 0.2648736238479614, "learning_rate": 1.5631234398035483e-05, "loss": 0.0251, "step": 3640 }, { "epoch": 0.16561831783970188, "grad_norm": 0.2814118564128876, "learning_rate": 1.5606919998953182e-05, "loss": 0.0266, "step": 3650 }, { "epoch": 0.16607206665570107, "grad_norm": 0.3294977843761444, "learning_rate": 1.5582557156885218e-05, "loss": 0.0258, "step": 3660 }, { "epoch": 0.16652581547170026, "grad_norm": 0.2448832392692566, "learning_rate": 1.5558146082323056e-05, "loss": 0.0267, "step": 3670 }, { "epoch": 0.16697956428769944, "grad_norm": 0.2970380187034607, "learning_rate": 1.5533686986174885e-05, "loss": 0.0227, "step": 3680 }, { "epoch": 0.16743331310369863, "grad_norm": 0.23803679645061493, "learning_rate": 1.5509180079763794e-05, "loss": 0.0284, "step": 3690 }, { "epoch": 0.1678870619196978, "grad_norm": 0.23536689579486847, "learning_rate": 1.548462557482594e-05, "loss": 0.0237, "step": 3700 }, { "epoch": 0.16834081073569698, "grad_norm": 0.19429349899291992, "learning_rate": 1.546002368350873e-05, "loss": 0.0262, "step": 3710 }, { "epoch": 0.16879455955169617, "grad_norm": 0.3040267527103424, "learning_rate": 1.5435374618368987e-05, "loss": 0.0253, "step": 3720 }, { "epoch": 0.16924830836769536, "grad_norm": 0.284315288066864, "learning_rate": 1.5410678592371097e-05, "loss": 0.0266, "step": 3730 }, { "epoch": 0.16970205718369455, "grad_norm": 0.2757561206817627, "learning_rate": 1.5385935818885185e-05, "loss": 0.0247, "step": 3740 }, { "epoch": 0.1701558059996937, "grad_norm": 0.22387561202049255, "learning_rate": 1.5361146511685275e-05, "loss": 0.0217, "step": 3750 }, { "epoch": 0.1706095548156929, "grad_norm": 0.18110151588916779, "learning_rate": 1.5336310884947424e-05, "loss": 0.0232, "step": 3760 }, { "epoch": 0.1710633036316921, "grad_norm": 0.2944502532482147, "learning_rate": 1.5311429153247898e-05, "loss": 0.0224, "step": 3770 }, { "epoch": 0.17151705244769128, "grad_norm": 0.2657409608364105, "learning_rate": 1.5286501531561292e-05, "loss": 0.0241, "step": 3780 }, { "epoch": 0.17197080126369046, "grad_norm": 0.2780546545982361, "learning_rate": 1.526152823525868e-05, "loss": 0.0267, "step": 3790 }, { "epoch": 0.17242455007968963, "grad_norm": 0.3222223222255707, "learning_rate": 1.5236509480105781e-05, "loss": 0.027, "step": 3800 }, { "epoch": 0.17287829889568881, "grad_norm": 0.2272912710905075, "learning_rate": 1.5211445482261039e-05, "loss": 0.0267, "step": 3810 }, { "epoch": 0.173332047711688, "grad_norm": 0.28601500391960144, "learning_rate": 1.5186336458273809e-05, "loss": 0.0232, "step": 3820 }, { "epoch": 0.1737857965276872, "grad_norm": 0.3215850293636322, "learning_rate": 1.5161182625082469e-05, "loss": 0.0251, "step": 3830 }, { "epoch": 0.17423954534368638, "grad_norm": 0.24761374294757843, "learning_rate": 1.5135984200012526e-05, "loss": 0.0287, "step": 3840 }, { "epoch": 0.17469329415968554, "grad_norm": 0.2844490706920624, "learning_rate": 1.511074140077477e-05, "loss": 0.0225, "step": 3850 }, { "epoch": 0.17514704297568473, "grad_norm": 0.2544344365596771, "learning_rate": 1.5085454445463367e-05, "loss": 0.0255, "step": 3860 }, { "epoch": 0.17560079179168392, "grad_norm": 0.20834238827228546, "learning_rate": 1.506012355255399e-05, "loss": 0.021, "step": 3870 }, { "epoch": 0.1760545406076831, "grad_norm": 0.28797847032546997, "learning_rate": 1.503474894090193e-05, "loss": 0.0275, "step": 3880 }, { "epoch": 0.1765082894236823, "grad_norm": 0.18112561106681824, "learning_rate": 1.5009330829740183e-05, "loss": 0.0204, "step": 3890 }, { "epoch": 0.17696203823968146, "grad_norm": 0.22110165655612946, "learning_rate": 1.4983869438677605e-05, "loss": 0.0257, "step": 3900 }, { "epoch": 0.17741578705568065, "grad_norm": 0.28787487745285034, "learning_rate": 1.4958364987696956e-05, "loss": 0.0207, "step": 3910 }, { "epoch": 0.17786953587167983, "grad_norm": 0.31027793884277344, "learning_rate": 1.4932817697153046e-05, "loss": 0.0266, "step": 3920 }, { "epoch": 0.17832328468767902, "grad_norm": 0.25544893741607666, "learning_rate": 1.4907227787770805e-05, "loss": 0.026, "step": 3930 }, { "epoch": 0.1787770335036782, "grad_norm": 0.25678592920303345, "learning_rate": 1.4881595480643379e-05, "loss": 0.0256, "step": 3940 }, { "epoch": 0.17923078231967737, "grad_norm": 0.2055646777153015, "learning_rate": 1.4855920997230238e-05, "loss": 0.0249, "step": 3950 }, { "epoch": 0.17968453113567656, "grad_norm": 0.30814501643180847, "learning_rate": 1.4830204559355234e-05, "loss": 0.0247, "step": 3960 }, { "epoch": 0.18013827995167575, "grad_norm": 0.2107338160276413, "learning_rate": 1.4804446389204715e-05, "loss": 0.0249, "step": 3970 }, { "epoch": 0.18059202876767494, "grad_norm": 0.2385590523481369, "learning_rate": 1.4778646709325573e-05, "loss": 0.023, "step": 3980 }, { "epoch": 0.18104577758367413, "grad_norm": 0.30539920926094055, "learning_rate": 1.4752805742623349e-05, "loss": 0.0238, "step": 3990 }, { "epoch": 0.1814995263996733, "grad_norm": 0.352479487657547, "learning_rate": 1.47269237123603e-05, "loss": 0.0272, "step": 4000 }, { "epoch": 0.18195327521567248, "grad_norm": 0.20750758051872253, "learning_rate": 1.470100084215345e-05, "loss": 0.0247, "step": 4010 }, { "epoch": 0.18240702403167167, "grad_norm": 0.30754831433296204, "learning_rate": 1.4675037355972693e-05, "loss": 0.0287, "step": 4020 }, { "epoch": 0.18286077284767085, "grad_norm": 0.28221386671066284, "learning_rate": 1.4649033478138825e-05, "loss": 0.023, "step": 4030 }, { "epoch": 0.18331452166367004, "grad_norm": 0.2374511957168579, "learning_rate": 1.4622989433321627e-05, "loss": 0.0285, "step": 4040 }, { "epoch": 0.1837682704796692, "grad_norm": 0.1986793875694275, "learning_rate": 1.459690544653792e-05, "loss": 0.0253, "step": 4050 }, { "epoch": 0.1842220192956684, "grad_norm": 0.2326020747423172, "learning_rate": 1.457078174314961e-05, "loss": 0.0236, "step": 4060 }, { "epoch": 0.18467576811166758, "grad_norm": 0.21970577538013458, "learning_rate": 1.4544618548861753e-05, "loss": 0.0229, "step": 4070 }, { "epoch": 0.18512951692766677, "grad_norm": 0.21649987995624542, "learning_rate": 1.45184160897206e-05, "loss": 0.0194, "step": 4080 }, { "epoch": 0.18558326574366596, "grad_norm": 0.22389715909957886, "learning_rate": 1.4492174592111642e-05, "loss": 0.0258, "step": 4090 }, { "epoch": 0.18603701455966512, "grad_norm": 0.2992272973060608, "learning_rate": 1.4465894282757662e-05, "loss": 0.0234, "step": 4100 }, { "epoch": 0.1864907633756643, "grad_norm": 0.2702163755893707, "learning_rate": 1.4439575388716768e-05, "loss": 0.0236, "step": 4110 }, { "epoch": 0.1869445121916635, "grad_norm": 0.21369431912899017, "learning_rate": 1.441321813738044e-05, "loss": 0.0221, "step": 4120 }, { "epoch": 0.1873982610076627, "grad_norm": 0.28000566363334656, "learning_rate": 1.4386822756471545e-05, "loss": 0.0257, "step": 4130 }, { "epoch": 0.18785200982366188, "grad_norm": 0.21276937425136566, "learning_rate": 1.43603894740424e-05, "loss": 0.0229, "step": 4140 }, { "epoch": 0.18830575863966104, "grad_norm": 0.2979341149330139, "learning_rate": 1.4333918518472773e-05, "loss": 0.0245, "step": 4150 }, { "epoch": 0.18875950745566022, "grad_norm": 0.2029874473810196, "learning_rate": 1.4307410118467932e-05, "loss": 0.0198, "step": 4160 }, { "epoch": 0.1892132562716594, "grad_norm": 0.19624759256839752, "learning_rate": 1.428086450305666e-05, "loss": 0.0249, "step": 4170 }, { "epoch": 0.1896670050876586, "grad_norm": 0.21640922129154205, "learning_rate": 1.4254281901589263e-05, "loss": 0.0253, "step": 4180 }, { "epoch": 0.1901207539036578, "grad_norm": 0.20204633474349976, "learning_rate": 1.4227662543735618e-05, "loss": 0.0243, "step": 4190 }, { "epoch": 0.19057450271965698, "grad_norm": 0.2619876563549042, "learning_rate": 1.4201006659483156e-05, "loss": 0.023, "step": 4200 }, { "epoch": 0.19102825153565614, "grad_norm": 0.2339455932378769, "learning_rate": 1.4174314479134909e-05, "loss": 0.0207, "step": 4210 }, { "epoch": 0.19148200035165533, "grad_norm": 0.2705822288990021, "learning_rate": 1.4147586233307485e-05, "loss": 0.0282, "step": 4220 }, { "epoch": 0.19193574916765452, "grad_norm": 0.2909568250179291, "learning_rate": 1.4120822152929099e-05, "loss": 0.0262, "step": 4230 }, { "epoch": 0.1923894979836537, "grad_norm": 0.2662507891654968, "learning_rate": 1.4094022469237577e-05, "loss": 0.0256, "step": 4240 }, { "epoch": 0.1928432467996529, "grad_norm": 0.20035651326179504, "learning_rate": 1.4067187413778338e-05, "loss": 0.0218, "step": 4250 }, { "epoch": 0.19329699561565206, "grad_norm": 0.3585357367992401, "learning_rate": 1.4040317218402426e-05, "loss": 0.0217, "step": 4260 }, { "epoch": 0.19375074443165125, "grad_norm": 0.2663518786430359, "learning_rate": 1.4013412115264477e-05, "loss": 0.0225, "step": 4270 }, { "epoch": 0.19420449324765043, "grad_norm": 0.18744990229606628, "learning_rate": 1.398647233682073e-05, "loss": 0.0238, "step": 4280 }, { "epoch": 0.19465824206364962, "grad_norm": 0.24274271726608276, "learning_rate": 1.3959498115827007e-05, "loss": 0.0202, "step": 4290 }, { "epoch": 0.1951119908796488, "grad_norm": 0.2325545698404312, "learning_rate": 1.3932489685336722e-05, "loss": 0.0269, "step": 4300 }, { "epoch": 0.19556573969564797, "grad_norm": 0.264298677444458, "learning_rate": 1.3905447278698838e-05, "loss": 0.0253, "step": 4310 }, { "epoch": 0.19601948851164716, "grad_norm": 0.2430010437965393, "learning_rate": 1.3878371129555874e-05, "loss": 0.0231, "step": 4320 }, { "epoch": 0.19647323732764635, "grad_norm": 0.20793242752552032, "learning_rate": 1.3851261471841891e-05, "loss": 0.0243, "step": 4330 }, { "epoch": 0.19692698614364554, "grad_norm": 0.6175364255905151, "learning_rate": 1.382411853978044e-05, "loss": 0.0225, "step": 4340 }, { "epoch": 0.19738073495964473, "grad_norm": 0.21603089570999146, "learning_rate": 1.3796942567882565e-05, "loss": 0.0194, "step": 4350 }, { "epoch": 0.1978344837756439, "grad_norm": 0.25952887535095215, "learning_rate": 1.3769733790944777e-05, "loss": 0.024, "step": 4360 }, { "epoch": 0.19828823259164308, "grad_norm": 0.22179457545280457, "learning_rate": 1.3742492444047e-05, "loss": 0.0227, "step": 4370 }, { "epoch": 0.19874198140764227, "grad_norm": 0.32841038703918457, "learning_rate": 1.3715218762550584e-05, "loss": 0.0228, "step": 4380 }, { "epoch": 0.19919573022364145, "grad_norm": 0.24638161063194275, "learning_rate": 1.368791298209622e-05, "loss": 0.0237, "step": 4390 }, { "epoch": 0.19964947903964064, "grad_norm": 0.2410752773284912, "learning_rate": 1.3660575338601945e-05, "loss": 0.0232, "step": 4400 }, { "epoch": 0.2001032278556398, "grad_norm": 0.2882155179977417, "learning_rate": 1.363320606826108e-05, "loss": 0.0254, "step": 4410 }, { "epoch": 0.200556976671639, "grad_norm": 0.21610230207443237, "learning_rate": 1.36058054075402e-05, "loss": 0.0221, "step": 4420 }, { "epoch": 0.20101072548763818, "grad_norm": 0.19741304218769073, "learning_rate": 1.3578373593177091e-05, "loss": 0.0215, "step": 4430 }, { "epoch": 0.20146447430363737, "grad_norm": 0.2795509696006775, "learning_rate": 1.35509108621787e-05, "loss": 0.0232, "step": 4440 }, { "epoch": 0.20191822311963656, "grad_norm": 0.2761068344116211, "learning_rate": 1.3523417451819087e-05, "loss": 0.0218, "step": 4450 }, { "epoch": 0.20237197193563572, "grad_norm": 0.26296836137771606, "learning_rate": 1.3495893599637385e-05, "loss": 0.0234, "step": 4460 }, { "epoch": 0.2028257207516349, "grad_norm": 0.24709446728229523, "learning_rate": 1.3468339543435725e-05, "loss": 0.0217, "step": 4470 }, { "epoch": 0.2032794695676341, "grad_norm": 0.23241135478019714, "learning_rate": 1.3440755521277209e-05, "loss": 0.0271, "step": 4480 }, { "epoch": 0.20373321838363329, "grad_norm": 0.19572514295578003, "learning_rate": 1.3413141771483842e-05, "loss": 0.023, "step": 4490 }, { "epoch": 0.20418696719963247, "grad_norm": 0.22248703241348267, "learning_rate": 1.3385498532634465e-05, "loss": 0.0231, "step": 4500 }, { "epoch": 0.20464071601563164, "grad_norm": 0.27304351329803467, "learning_rate": 1.3357826043562698e-05, "loss": 0.0252, "step": 4510 }, { "epoch": 0.20509446483163082, "grad_norm": 0.2136859893798828, "learning_rate": 1.3330124543354888e-05, "loss": 0.0239, "step": 4520 }, { "epoch": 0.20554821364763, "grad_norm": 0.2939571440219879, "learning_rate": 1.3302394271348026e-05, "loss": 0.0264, "step": 4530 }, { "epoch": 0.2060019624636292, "grad_norm": 0.2361244112253189, "learning_rate": 1.3274635467127688e-05, "loss": 0.0206, "step": 4540 }, { "epoch": 0.2064557112796284, "grad_norm": 0.2681204080581665, "learning_rate": 1.3246848370525973e-05, "loss": 0.0235, "step": 4550 }, { "epoch": 0.20690946009562755, "grad_norm": 0.21554698050022125, "learning_rate": 1.3219033221619408e-05, "loss": 0.023, "step": 4560 }, { "epoch": 0.20736320891162674, "grad_norm": 0.21627721190452576, "learning_rate": 1.3191190260726903e-05, "loss": 0.0219, "step": 4570 }, { "epoch": 0.20781695772762593, "grad_norm": 0.26984405517578125, "learning_rate": 1.3163319728407645e-05, "loss": 0.0227, "step": 4580 }, { "epoch": 0.20827070654362512, "grad_norm": 0.3547725975513458, "learning_rate": 1.3135421865459042e-05, "loss": 0.0261, "step": 4590 }, { "epoch": 0.2087244553596243, "grad_norm": 0.21738028526306152, "learning_rate": 1.3107496912914636e-05, "loss": 0.0224, "step": 4600 }, { "epoch": 0.20917820417562347, "grad_norm": 0.23205725848674774, "learning_rate": 1.307954511204202e-05, "loss": 0.0246, "step": 4610 }, { "epoch": 0.20963195299162266, "grad_norm": 0.23356084525585175, "learning_rate": 1.3051566704340746e-05, "loss": 0.0218, "step": 4620 }, { "epoch": 0.21008570180762184, "grad_norm": 0.23249253630638123, "learning_rate": 1.3023561931540247e-05, "loss": 0.0255, "step": 4630 }, { "epoch": 0.21053945062362103, "grad_norm": 0.21810343861579895, "learning_rate": 1.2995531035597753e-05, "loss": 0.0216, "step": 4640 }, { "epoch": 0.21099319943962022, "grad_norm": 0.2629944086074829, "learning_rate": 1.2967474258696186e-05, "loss": 0.0201, "step": 4650 }, { "epoch": 0.21144694825561938, "grad_norm": 0.23742488026618958, "learning_rate": 1.2939391843242082e-05, "loss": 0.0275, "step": 4660 }, { "epoch": 0.21190069707161857, "grad_norm": 0.22963425517082214, "learning_rate": 1.291128403186349e-05, "loss": 0.0224, "step": 4670 }, { "epoch": 0.21235444588761776, "grad_norm": 0.2870836555957794, "learning_rate": 1.2883151067407866e-05, "loss": 0.0221, "step": 4680 }, { "epoch": 0.21280819470361695, "grad_norm": 0.1531621664762497, "learning_rate": 1.2854993192940005e-05, "loss": 0.0225, "step": 4690 }, { "epoch": 0.21326194351961614, "grad_norm": 0.18853625655174255, "learning_rate": 1.2826810651739899e-05, "loss": 0.0235, "step": 4700 }, { "epoch": 0.2137156923356153, "grad_norm": 0.20390278100967407, "learning_rate": 1.279860368730067e-05, "loss": 0.0236, "step": 4710 }, { "epoch": 0.2141694411516145, "grad_norm": 0.2495160847902298, "learning_rate": 1.2770372543326454e-05, "loss": 0.0244, "step": 4720 }, { "epoch": 0.21462318996761368, "grad_norm": 0.22217145562171936, "learning_rate": 1.2742117463730289e-05, "loss": 0.0205, "step": 4730 }, { "epoch": 0.21507693878361286, "grad_norm": 0.21736115217208862, "learning_rate": 1.2713838692632015e-05, "loss": 0.0244, "step": 4740 }, { "epoch": 0.21553068759961205, "grad_norm": 0.22751232981681824, "learning_rate": 1.2685536474356161e-05, "loss": 0.0257, "step": 4750 }, { "epoch": 0.21598443641561124, "grad_norm": 0.20530980825424194, "learning_rate": 1.2657211053429844e-05, "loss": 0.02, "step": 4760 }, { "epoch": 0.2164381852316104, "grad_norm": 0.26674145460128784, "learning_rate": 1.2628862674580642e-05, "loss": 0.024, "step": 4770 }, { "epoch": 0.2168919340476096, "grad_norm": 0.26255202293395996, "learning_rate": 1.2600491582734484e-05, "loss": 0.0242, "step": 4780 }, { "epoch": 0.21734568286360878, "grad_norm": 0.2915859818458557, "learning_rate": 1.2572098023013544e-05, "loss": 0.0243, "step": 4790 }, { "epoch": 0.21779943167960797, "grad_norm": 0.1989348977804184, "learning_rate": 1.254368224073411e-05, "loss": 0.0213, "step": 4800 }, { "epoch": 0.21825318049560716, "grad_norm": 0.23927143216133118, "learning_rate": 1.251524448140447e-05, "loss": 0.0258, "step": 4810 }, { "epoch": 0.21870692931160632, "grad_norm": 0.2916087806224823, "learning_rate": 1.2486784990722791e-05, "loss": 0.0284, "step": 4820 }, { "epoch": 0.2191606781276055, "grad_norm": 0.18311503529548645, "learning_rate": 1.2458304014574996e-05, "loss": 0.0206, "step": 4830 }, { "epoch": 0.2196144269436047, "grad_norm": 0.313259482383728, "learning_rate": 1.242980179903264e-05, "loss": 0.0256, "step": 4840 }, { "epoch": 0.22006817575960388, "grad_norm": 0.2421349138021469, "learning_rate": 1.2401278590350782e-05, "loss": 0.0242, "step": 4850 }, { "epoch": 0.22052192457560307, "grad_norm": 0.24458634853363037, "learning_rate": 1.2372734634965861e-05, "loss": 0.0254, "step": 4860 }, { "epoch": 0.22097567339160223, "grad_norm": 0.23112539947032928, "learning_rate": 1.234417017949356e-05, "loss": 0.022, "step": 4870 }, { "epoch": 0.22142942220760142, "grad_norm": 0.27848610281944275, "learning_rate": 1.2315585470726685e-05, "loss": 0.0263, "step": 4880 }, { "epoch": 0.2218831710236006, "grad_norm": 0.22646069526672363, "learning_rate": 1.2286980755633027e-05, "loss": 0.0256, "step": 4890 }, { "epoch": 0.2223369198395998, "grad_norm": 0.2723843455314636, "learning_rate": 1.225835628135322e-05, "loss": 0.0216, "step": 4900 }, { "epoch": 0.222790668655599, "grad_norm": 0.31213846802711487, "learning_rate": 1.2229712295198633e-05, "loss": 0.0228, "step": 4910 }, { "epoch": 0.22324441747159815, "grad_norm": 0.2371712476015091, "learning_rate": 1.2201049044649192e-05, "loss": 0.0276, "step": 4920 }, { "epoch": 0.22369816628759734, "grad_norm": 0.2553006410598755, "learning_rate": 1.217236677735128e-05, "loss": 0.0204, "step": 4930 }, { "epoch": 0.22415191510359653, "grad_norm": 0.2048044055700302, "learning_rate": 1.2143665741115581e-05, "loss": 0.0192, "step": 4940 }, { "epoch": 0.22460566391959572, "grad_norm": 0.27982667088508606, "learning_rate": 1.2114946183914935e-05, "loss": 0.0192, "step": 4950 }, { "epoch": 0.2250594127355949, "grad_norm": 0.28141453862190247, "learning_rate": 1.2086208353882203e-05, "loss": 0.026, "step": 4960 }, { "epoch": 0.22551316155159407, "grad_norm": 0.25562092661857605, "learning_rate": 1.2057452499308117e-05, "loss": 0.022, "step": 4970 }, { "epoch": 0.22596691036759325, "grad_norm": 0.2604532241821289, "learning_rate": 1.2028678868639147e-05, "loss": 0.021, "step": 4980 }, { "epoch": 0.22642065918359244, "grad_norm": 0.277159720659256, "learning_rate": 1.1999887710475337e-05, "loss": 0.0199, "step": 4990 }, { "epoch": 0.22687440799959163, "grad_norm": 0.21274346113204956, "learning_rate": 1.197107927356817e-05, "loss": 0.0207, "step": 5000 }, { "epoch": 0.22732815681559082, "grad_norm": 0.32817763090133667, "learning_rate": 1.1942253806818414e-05, "loss": 0.0239, "step": 5010 }, { "epoch": 0.22778190563158998, "grad_norm": 0.24582712352275848, "learning_rate": 1.1913411559273973e-05, "loss": 0.0221, "step": 5020 }, { "epoch": 0.22823565444758917, "grad_norm": 0.27864110469818115, "learning_rate": 1.1884552780127736e-05, "loss": 0.0239, "step": 5030 }, { "epoch": 0.22868940326358836, "grad_norm": 0.23668569326400757, "learning_rate": 1.1855677718715417e-05, "loss": 0.023, "step": 5040 }, { "epoch": 0.22914315207958755, "grad_norm": 0.2114197015762329, "learning_rate": 1.1826786624513416e-05, "loss": 0.0253, "step": 5050 }, { "epoch": 0.22959690089558674, "grad_norm": 0.2612532675266266, "learning_rate": 1.1797879747136645e-05, "loss": 0.0192, "step": 5060 }, { "epoch": 0.2300506497115859, "grad_norm": 0.2169615775346756, "learning_rate": 1.1768957336336384e-05, "loss": 0.0214, "step": 5070 }, { "epoch": 0.23050439852758509, "grad_norm": 0.19392265379428864, "learning_rate": 1.1740019641998124e-05, "loss": 0.0206, "step": 5080 }, { "epoch": 0.23095814734358427, "grad_norm": 0.2681560516357422, "learning_rate": 1.171106691413939e-05, "loss": 0.0217, "step": 5090 }, { "epoch": 0.23141189615958346, "grad_norm": 0.18221773207187653, "learning_rate": 1.1682099402907612e-05, "loss": 0.0242, "step": 5100 }, { "epoch": 0.23186564497558265, "grad_norm": 0.278082013130188, "learning_rate": 1.1653117358577937e-05, "loss": 0.022, "step": 5110 }, { "epoch": 0.2323193937915818, "grad_norm": 0.23688696324825287, "learning_rate": 1.1624121031551073e-05, "loss": 0.0222, "step": 5120 }, { "epoch": 0.232773142607581, "grad_norm": 0.20439651608467102, "learning_rate": 1.1595110672351132e-05, "loss": 0.0182, "step": 5130 }, { "epoch": 0.2332268914235802, "grad_norm": 0.24752862751483917, "learning_rate": 1.1566086531623464e-05, "loss": 0.0219, "step": 5140 }, { "epoch": 0.23368064023957938, "grad_norm": 0.23867738246917725, "learning_rate": 1.1537048860132487e-05, "loss": 0.0222, "step": 5150 }, { "epoch": 0.23413438905557857, "grad_norm": 0.23973336815834045, "learning_rate": 1.1507997908759525e-05, "loss": 0.0221, "step": 5160 }, { "epoch": 0.23458813787157773, "grad_norm": 0.2094511240720749, "learning_rate": 1.1478933928500635e-05, "loss": 0.0225, "step": 5170 }, { "epoch": 0.23504188668757692, "grad_norm": 0.2605903148651123, "learning_rate": 1.1449857170464445e-05, "loss": 0.0214, "step": 5180 }, { "epoch": 0.2354956355035761, "grad_norm": 0.355555921792984, "learning_rate": 1.1420767885869974e-05, "loss": 0.0235, "step": 5190 }, { "epoch": 0.2359493843195753, "grad_norm": 0.31669801473617554, "learning_rate": 1.1391666326044484e-05, "loss": 0.0205, "step": 5200 }, { "epoch": 0.23640313313557448, "grad_norm": 0.16547736525535583, "learning_rate": 1.1362552742421269e-05, "loss": 0.0215, "step": 5210 }, { "epoch": 0.23685688195157364, "grad_norm": 0.22537292540073395, "learning_rate": 1.1333427386537537e-05, "loss": 0.0218, "step": 5220 }, { "epoch": 0.23731063076757283, "grad_norm": 0.22958503663539886, "learning_rate": 1.1304290510032184e-05, "loss": 0.02, "step": 5230 }, { "epoch": 0.23776437958357202, "grad_norm": 0.17777228355407715, "learning_rate": 1.1275142364643645e-05, "loss": 0.0228, "step": 5240 }, { "epoch": 0.2382181283995712, "grad_norm": 0.25912711024284363, "learning_rate": 1.1245983202207729e-05, "loss": 0.0199, "step": 5250 }, { "epoch": 0.2386718772155704, "grad_norm": 0.20890118181705475, "learning_rate": 1.1216813274655417e-05, "loss": 0.0192, "step": 5260 }, { "epoch": 0.23912562603156956, "grad_norm": 0.24683567881584167, "learning_rate": 1.1187632834010707e-05, "loss": 0.0198, "step": 5270 }, { "epoch": 0.23957937484756875, "grad_norm": 0.19287711381912231, "learning_rate": 1.1158442132388427e-05, "loss": 0.0242, "step": 5280 }, { "epoch": 0.24003312366356794, "grad_norm": 0.38850992918014526, "learning_rate": 1.1129241421992059e-05, "loss": 0.0244, "step": 5290 }, { "epoch": 0.24048687247956713, "grad_norm": 0.2065545618534088, "learning_rate": 1.1100030955111554e-05, "loss": 0.0188, "step": 5300 }, { "epoch": 0.24094062129556632, "grad_norm": 0.2508976459503174, "learning_rate": 1.1070810984121164e-05, "loss": 0.0185, "step": 5310 }, { "epoch": 0.2413943701115655, "grad_norm": 0.2615440785884857, "learning_rate": 1.1041581761477252e-05, "loss": 0.0223, "step": 5320 }, { "epoch": 0.24184811892756466, "grad_norm": 0.29849186539649963, "learning_rate": 1.1012343539716115e-05, "loss": 0.0258, "step": 5330 }, { "epoch": 0.24230186774356385, "grad_norm": 0.23321117460727692, "learning_rate": 1.0983096571451805e-05, "loss": 0.024, "step": 5340 }, { "epoch": 0.24275561655956304, "grad_norm": 0.2524389624595642, "learning_rate": 1.0953841109373935e-05, "loss": 0.0231, "step": 5350 }, { "epoch": 0.24320936537556223, "grad_norm": 0.186526358127594, "learning_rate": 1.0924577406245507e-05, "loss": 0.0201, "step": 5360 }, { "epoch": 0.24366311419156142, "grad_norm": 0.18058817088603973, "learning_rate": 1.0895305714900721e-05, "loss": 0.0167, "step": 5370 }, { "epoch": 0.24411686300756058, "grad_norm": 0.2251308709383011, "learning_rate": 1.0866026288242803e-05, "loss": 0.0215, "step": 5380 }, { "epoch": 0.24457061182355977, "grad_norm": 0.2567005157470703, "learning_rate": 1.0836739379241805e-05, "loss": 0.0244, "step": 5390 }, { "epoch": 0.24502436063955896, "grad_norm": 0.2576402425765991, "learning_rate": 1.0807445240932422e-05, "loss": 0.0288, "step": 5400 }, { "epoch": 0.24547810945555815, "grad_norm": 0.1856900155544281, "learning_rate": 1.0778144126411815e-05, "loss": 0.0197, "step": 5410 }, { "epoch": 0.24593185827155734, "grad_norm": 0.2417580783367157, "learning_rate": 1.0748836288837418e-05, "loss": 0.0243, "step": 5420 }, { "epoch": 0.2463856070875565, "grad_norm": 0.18128962814807892, "learning_rate": 1.0719521981424745e-05, "loss": 0.0195, "step": 5430 }, { "epoch": 0.24683935590355569, "grad_norm": 0.30921271443367004, "learning_rate": 1.0690201457445218e-05, "loss": 0.0191, "step": 5440 }, { "epoch": 0.24729310471955487, "grad_norm": 0.24406775832176208, "learning_rate": 1.0660874970223963e-05, "loss": 0.0218, "step": 5450 }, { "epoch": 0.24774685353555406, "grad_norm": 0.32797232270240784, "learning_rate": 1.0631542773137627e-05, "loss": 0.0208, "step": 5460 }, { "epoch": 0.24820060235155325, "grad_norm": 0.3248281180858612, "learning_rate": 1.060220511961219e-05, "loss": 0.0231, "step": 5470 }, { "epoch": 0.2486543511675524, "grad_norm": 0.24134427309036255, "learning_rate": 1.0572862263120784e-05, "loss": 0.0206, "step": 5480 }, { "epoch": 0.2491080999835516, "grad_norm": 0.1702623963356018, "learning_rate": 1.0543514457181476e-05, "loss": 0.0219, "step": 5490 }, { "epoch": 0.2495618487995508, "grad_norm": 0.1670210063457489, "learning_rate": 1.051416195535511e-05, "loss": 0.0208, "step": 5500 }, { "epoch": 0.25001559761555, "grad_norm": 0.22409462928771973, "learning_rate": 1.0484805011243102e-05, "loss": 0.0212, "step": 5510 }, { "epoch": 0.25046934643154917, "grad_norm": 0.18599118292331696, "learning_rate": 1.0455443878485238e-05, "loss": 0.0231, "step": 5520 }, { "epoch": 0.25092309524754836, "grad_norm": 0.23653936386108398, "learning_rate": 1.0426078810757502e-05, "loss": 0.0227, "step": 5530 }, { "epoch": 0.25137684406354754, "grad_norm": 0.23654955625534058, "learning_rate": 1.039671006176987e-05, "loss": 0.0203, "step": 5540 }, { "epoch": 0.2518305928795467, "grad_norm": 0.29107680916786194, "learning_rate": 1.0367337885264128e-05, "loss": 0.0246, "step": 5550 }, { "epoch": 0.25228434169554587, "grad_norm": 0.19438305497169495, "learning_rate": 1.0337962535011679e-05, "loss": 0.0212, "step": 5560 }, { "epoch": 0.25273809051154505, "grad_norm": 0.14470505714416504, "learning_rate": 1.0308584264811332e-05, "loss": 0.0184, "step": 5570 }, { "epoch": 0.25319183932754424, "grad_norm": 0.21843239665031433, "learning_rate": 1.0279203328487142e-05, "loss": 0.018, "step": 5580 }, { "epoch": 0.25364558814354343, "grad_norm": 0.20726455748081207, "learning_rate": 1.0249819979886184e-05, "loss": 0.0187, "step": 5590 }, { "epoch": 0.2540993369595426, "grad_norm": 0.21845829486846924, "learning_rate": 1.0220434472876384e-05, "loss": 0.0178, "step": 5600 }, { "epoch": 0.2545530857755418, "grad_norm": 0.20182789862155914, "learning_rate": 1.0191047061344315e-05, "loss": 0.0198, "step": 5610 }, { "epoch": 0.255006834591541, "grad_norm": 0.20133326947689056, "learning_rate": 1.0161657999192998e-05, "loss": 0.0192, "step": 5620 }, { "epoch": 0.2554605834075402, "grad_norm": 0.22368073463439941, "learning_rate": 1.0132267540339726e-05, "loss": 0.0208, "step": 5630 }, { "epoch": 0.2559143322235394, "grad_norm": 0.19817300140857697, "learning_rate": 1.010287593871385e-05, "loss": 0.0184, "step": 5640 }, { "epoch": 0.25636808103953856, "grad_norm": 0.2092844545841217, "learning_rate": 1.0073483448254599e-05, "loss": 0.0199, "step": 5650 }, { "epoch": 0.2568218298555377, "grad_norm": 0.37341657280921936, "learning_rate": 1.0044090322908884e-05, "loss": 0.0162, "step": 5660 }, { "epoch": 0.2572755786715369, "grad_norm": 0.20919254422187805, "learning_rate": 1.0014696816629093e-05, "loss": 0.0215, "step": 5670 }, { "epoch": 0.2577293274875361, "grad_norm": 0.26721906661987305, "learning_rate": 9.985303183370909e-06, "loss": 0.0214, "step": 5680 }, { "epoch": 0.25818307630353526, "grad_norm": 0.17902706563472748, "learning_rate": 9.95590967709112e-06, "loss": 0.022, "step": 5690 }, { "epoch": 0.25863682511953445, "grad_norm": 0.20274867117404938, "learning_rate": 9.926516551745401e-06, "loss": 0.018, "step": 5700 }, { "epoch": 0.25909057393553364, "grad_norm": 0.21461789309978485, "learning_rate": 9.897124061286152e-06, "loss": 0.0172, "step": 5710 }, { "epoch": 0.25954432275153283, "grad_norm": 0.21908989548683167, "learning_rate": 9.867732459660277e-06, "loss": 0.0193, "step": 5720 }, { "epoch": 0.259998071567532, "grad_norm": 0.25718387961387634, "learning_rate": 9.838342000807006e-06, "loss": 0.0218, "step": 5730 }, { "epoch": 0.2604518203835312, "grad_norm": 0.21390610933303833, "learning_rate": 9.808952938655689e-06, "loss": 0.0227, "step": 5740 }, { "epoch": 0.2609055691995304, "grad_norm": 0.2882938086986542, "learning_rate": 9.77956552712362e-06, "loss": 0.0247, "step": 5750 }, { "epoch": 0.26135931801552953, "grad_norm": 0.17672798037528992, "learning_rate": 9.75018002011382e-06, "loss": 0.0191, "step": 5760 }, { "epoch": 0.2618130668315287, "grad_norm": 0.25841259956359863, "learning_rate": 9.720796671512863e-06, "loss": 0.0217, "step": 5770 }, { "epoch": 0.2622668156475279, "grad_norm": 0.20599308609962463, "learning_rate": 9.69141573518867e-06, "loss": 0.0219, "step": 5780 }, { "epoch": 0.2627205644635271, "grad_norm": 0.1963510364294052, "learning_rate": 9.662037464988323e-06, "loss": 0.0209, "step": 5790 }, { "epoch": 0.2631743132795263, "grad_norm": 0.21905919909477234, "learning_rate": 9.63266211473587e-06, "loss": 0.0201, "step": 5800 }, { "epoch": 0.2636280620955255, "grad_norm": 0.2846311926841736, "learning_rate": 9.603289938230132e-06, "loss": 0.0206, "step": 5810 }, { "epoch": 0.26408181091152466, "grad_norm": 0.17411284148693085, "learning_rate": 9.573921189242501e-06, "loss": 0.0198, "step": 5820 }, { "epoch": 0.26453555972752385, "grad_norm": 0.23678627610206604, "learning_rate": 9.544556121514765e-06, "loss": 0.0222, "step": 5830 }, { "epoch": 0.26498930854352304, "grad_norm": 0.23285925388336182, "learning_rate": 9.5151949887569e-06, "loss": 0.0213, "step": 5840 }, { "epoch": 0.2654430573595222, "grad_norm": 0.2179705798625946, "learning_rate": 9.485838044644891e-06, "loss": 0.0214, "step": 5850 }, { "epoch": 0.26589680617552136, "grad_norm": 0.20862144231796265, "learning_rate": 9.456485542818527e-06, "loss": 0.0204, "step": 5860 }, { "epoch": 0.26635055499152055, "grad_norm": 0.2824237644672394, "learning_rate": 9.427137736879222e-06, "loss": 0.019, "step": 5870 }, { "epoch": 0.26680430380751974, "grad_norm": 0.2021375149488449, "learning_rate": 9.397794880387812e-06, "loss": 0.0222, "step": 5880 }, { "epoch": 0.2672580526235189, "grad_norm": 0.2058638036251068, "learning_rate": 9.368457226862378e-06, "loss": 0.0181, "step": 5890 }, { "epoch": 0.2677118014395181, "grad_norm": 0.25774434208869934, "learning_rate": 9.339125029776039e-06, "loss": 0.0214, "step": 5900 }, { "epoch": 0.2681655502555173, "grad_norm": 0.2747572660446167, "learning_rate": 9.309798542554782e-06, "loss": 0.0199, "step": 5910 }, { "epoch": 0.2686192990715165, "grad_norm": 0.2012614607810974, "learning_rate": 9.280478018575257e-06, "loss": 0.0224, "step": 5920 }, { "epoch": 0.2690730478875157, "grad_norm": 0.2688499987125397, "learning_rate": 9.251163711162584e-06, "loss": 0.0228, "step": 5930 }, { "epoch": 0.26952679670351487, "grad_norm": 0.20391063392162323, "learning_rate": 9.221855873588187e-06, "loss": 0.0188, "step": 5940 }, { "epoch": 0.26998054551951406, "grad_norm": 0.259417861700058, "learning_rate": 9.192554759067581e-06, "loss": 0.0238, "step": 5950 }, { "epoch": 0.2704342943355132, "grad_norm": 0.15208792686462402, "learning_rate": 9.163260620758197e-06, "loss": 0.0179, "step": 5960 }, { "epoch": 0.2708880431515124, "grad_norm": 0.19771994650363922, "learning_rate": 9.133973711757198e-06, "loss": 0.0205, "step": 5970 }, { "epoch": 0.27134179196751157, "grad_norm": 0.2707306444644928, "learning_rate": 9.10469428509928e-06, "loss": 0.0213, "step": 5980 }, { "epoch": 0.27179554078351076, "grad_norm": 0.2664511501789093, "learning_rate": 9.075422593754498e-06, "loss": 0.0181, "step": 5990 }, { "epoch": 0.27224928959950995, "grad_norm": 0.2898205518722534, "learning_rate": 9.046158890626069e-06, "loss": 0.0229, "step": 6000 }, { "epoch": 0.27270303841550914, "grad_norm": 0.213274285197258, "learning_rate": 9.016903428548195e-06, "loss": 0.0193, "step": 6010 }, { "epoch": 0.2731567872315083, "grad_norm": 0.28087136149406433, "learning_rate": 8.987656460283885e-06, "loss": 0.0178, "step": 6020 }, { "epoch": 0.2736105360475075, "grad_norm": 0.21582555770874023, "learning_rate": 8.958418238522748e-06, "loss": 0.0224, "step": 6030 }, { "epoch": 0.2740642848635067, "grad_norm": 0.19979237020015717, "learning_rate": 8.929189015878838e-06, "loss": 0.0192, "step": 6040 }, { "epoch": 0.2745180336795059, "grad_norm": 0.3200356662273407, "learning_rate": 8.899969044888448e-06, "loss": 0.0191, "step": 6050 }, { "epoch": 0.274971782495505, "grad_norm": 0.24702613055706024, "learning_rate": 8.870758578007944e-06, "loss": 0.022, "step": 6060 }, { "epoch": 0.2754255313115042, "grad_norm": 0.24897615611553192, "learning_rate": 8.841557867611576e-06, "loss": 0.0199, "step": 6070 }, { "epoch": 0.2758792801275034, "grad_norm": 0.26184073090553284, "learning_rate": 8.812367165989295e-06, "loss": 0.0196, "step": 6080 }, { "epoch": 0.2763330289435026, "grad_norm": 0.1785680651664734, "learning_rate": 8.783186725344588e-06, "loss": 0.0196, "step": 6090 }, { "epoch": 0.2767867777595018, "grad_norm": 0.29078930616378784, "learning_rate": 8.754016797792276e-06, "loss": 0.0237, "step": 6100 }, { "epoch": 0.27724052657550097, "grad_norm": 0.2173246145248413, "learning_rate": 8.72485763535636e-06, "loss": 0.017, "step": 6110 }, { "epoch": 0.27769427539150016, "grad_norm": 0.3195157051086426, "learning_rate": 8.695709489967821e-06, "loss": 0.0203, "step": 6120 }, { "epoch": 0.27814802420749934, "grad_norm": 0.25643035769462585, "learning_rate": 8.666572613462465e-06, "loss": 0.0208, "step": 6130 }, { "epoch": 0.27860177302349853, "grad_norm": 0.21728429198265076, "learning_rate": 8.63744725757873e-06, "loss": 0.0189, "step": 6140 }, { "epoch": 0.2790555218394977, "grad_norm": 0.154546320438385, "learning_rate": 8.60833367395552e-06, "loss": 0.0202, "step": 6150 }, { "epoch": 0.2795092706554969, "grad_norm": 0.19910423457622528, "learning_rate": 8.579232114130027e-06, "loss": 0.0197, "step": 6160 }, { "epoch": 0.27996301947149604, "grad_norm": 0.19797872006893158, "learning_rate": 8.550142829535559e-06, "loss": 0.016, "step": 6170 }, { "epoch": 0.28041676828749523, "grad_norm": 0.2792125344276428, "learning_rate": 8.521066071499368e-06, "loss": 0.018, "step": 6180 }, { "epoch": 0.2808705171034944, "grad_norm": 0.17021611332893372, "learning_rate": 8.492002091240478e-06, "loss": 0.0193, "step": 6190 }, { "epoch": 0.2813242659194936, "grad_norm": 0.1742016226053238, "learning_rate": 8.462951139867514e-06, "loss": 0.0204, "step": 6200 }, { "epoch": 0.2817780147354928, "grad_norm": 0.2557216286659241, "learning_rate": 8.43391346837654e-06, "loss": 0.0197, "step": 6210 }, { "epoch": 0.282231763551492, "grad_norm": 0.22996285557746887, "learning_rate": 8.404889327648873e-06, "loss": 0.0171, "step": 6220 }, { "epoch": 0.2826855123674912, "grad_norm": 0.2642570734024048, "learning_rate": 8.375878968448934e-06, "loss": 0.0195, "step": 6230 }, { "epoch": 0.28313926118349036, "grad_norm": 0.20180673897266388, "learning_rate": 8.346882641422066e-06, "loss": 0.0194, "step": 6240 }, { "epoch": 0.28359300999948955, "grad_norm": 0.2699906826019287, "learning_rate": 8.317900597092388e-06, "loss": 0.0197, "step": 6250 }, { "epoch": 0.28404675881548874, "grad_norm": 0.2641448676586151, "learning_rate": 8.288933085860611e-06, "loss": 0.0195, "step": 6260 }, { "epoch": 0.2845005076314879, "grad_norm": 0.18801520764827728, "learning_rate": 8.25998035800188e-06, "loss": 0.0205, "step": 6270 }, { "epoch": 0.28495425644748706, "grad_norm": 0.1635589599609375, "learning_rate": 8.231042663663619e-06, "loss": 0.0223, "step": 6280 }, { "epoch": 0.28540800526348625, "grad_norm": 0.2192503809928894, "learning_rate": 8.202120252863359e-06, "loss": 0.0178, "step": 6290 }, { "epoch": 0.28586175407948544, "grad_norm": 0.41989174485206604, "learning_rate": 8.173213375486589e-06, "loss": 0.0197, "step": 6300 }, { "epoch": 0.28631550289548463, "grad_norm": 0.1972309798002243, "learning_rate": 8.144322281284586e-06, "loss": 0.0222, "step": 6310 }, { "epoch": 0.2867692517114838, "grad_norm": 0.22701092064380646, "learning_rate": 8.11544721987227e-06, "loss": 0.0221, "step": 6320 }, { "epoch": 0.287223000527483, "grad_norm": 0.2854195237159729, "learning_rate": 8.086588440726034e-06, "loss": 0.0196, "step": 6330 }, { "epoch": 0.2876767493434822, "grad_norm": 0.22627361118793488, "learning_rate": 8.057746193181591e-06, "loss": 0.0208, "step": 6340 }, { "epoch": 0.2881304981594814, "grad_norm": 0.3699786961078644, "learning_rate": 8.028920726431832e-06, "loss": 0.0193, "step": 6350 }, { "epoch": 0.2885842469754806, "grad_norm": 0.20992033183574677, "learning_rate": 8.000112289524666e-06, "loss": 0.021, "step": 6360 }, { "epoch": 0.2890379957914797, "grad_norm": 0.23770368099212646, "learning_rate": 7.971321131360855e-06, "loss": 0.0194, "step": 6370 }, { "epoch": 0.2894917446074789, "grad_norm": 0.17278876900672913, "learning_rate": 7.942547500691884e-06, "loss": 0.0199, "step": 6380 }, { "epoch": 0.2899454934234781, "grad_norm": 0.1980457752943039, "learning_rate": 7.913791646117798e-06, "loss": 0.0204, "step": 6390 }, { "epoch": 0.2903992422394773, "grad_norm": 0.20043553411960602, "learning_rate": 7.885053816085067e-06, "loss": 0.023, "step": 6400 }, { "epoch": 0.29085299105547646, "grad_norm": 0.20739471912384033, "learning_rate": 7.85633425888442e-06, "loss": 0.0201, "step": 6410 }, { "epoch": 0.29130673987147565, "grad_norm": 0.2559764087200165, "learning_rate": 7.827633222648722e-06, "loss": 0.022, "step": 6420 }, { "epoch": 0.29176048868747484, "grad_norm": 0.2904471457004547, "learning_rate": 7.798950955350812e-06, "loss": 0.023, "step": 6430 }, { "epoch": 0.29221423750347403, "grad_norm": 0.267575204372406, "learning_rate": 7.770287704801374e-06, "loss": 0.0198, "step": 6440 }, { "epoch": 0.2926679863194732, "grad_norm": 0.24424748122692108, "learning_rate": 7.741643718646783e-06, "loss": 0.022, "step": 6450 }, { "epoch": 0.2931217351354724, "grad_norm": 0.5289587378501892, "learning_rate": 7.713019244366977e-06, "loss": 0.0205, "step": 6460 }, { "epoch": 0.29357548395147154, "grad_norm": 0.21434202790260315, "learning_rate": 7.684414529273315e-06, "loss": 0.0196, "step": 6470 }, { "epoch": 0.2940292327674707, "grad_norm": 0.16888993978500366, "learning_rate": 7.655829820506442e-06, "loss": 0.0193, "step": 6480 }, { "epoch": 0.2944829815834699, "grad_norm": 0.18300025165081024, "learning_rate": 7.627265365034141e-06, "loss": 0.0197, "step": 6490 }, { "epoch": 0.2949367303994691, "grad_norm": 0.2743901014328003, "learning_rate": 7.59872140964922e-06, "loss": 0.0213, "step": 6500 }, { "epoch": 0.2953904792154683, "grad_norm": 0.24953070282936096, "learning_rate": 7.570198200967363e-06, "loss": 0.0193, "step": 6510 }, { "epoch": 0.2958442280314675, "grad_norm": 0.18799956142902374, "learning_rate": 7.5416959854250076e-06, "loss": 0.0179, "step": 6520 }, { "epoch": 0.29629797684746667, "grad_norm": 0.2509974241256714, "learning_rate": 7.513215009277212e-06, "loss": 0.0234, "step": 6530 }, { "epoch": 0.29675172566346586, "grad_norm": 0.3564259707927704, "learning_rate": 7.484755518595534e-06, "loss": 0.024, "step": 6540 }, { "epoch": 0.29720547447946505, "grad_norm": 0.23024022579193115, "learning_rate": 7.456317759265893e-06, "loss": 0.0175, "step": 6550 }, { "epoch": 0.29765922329546424, "grad_norm": 0.2363850176334381, "learning_rate": 7.4279019769864605e-06, "loss": 0.0217, "step": 6560 }, { "epoch": 0.29811297211146337, "grad_norm": 0.26667794585227966, "learning_rate": 7.399508417265517e-06, "loss": 0.0205, "step": 6570 }, { "epoch": 0.29856672092746256, "grad_norm": 0.27227628231048584, "learning_rate": 7.3711373254193595e-06, "loss": 0.019, "step": 6580 }, { "epoch": 0.29902046974346175, "grad_norm": 0.21537235379219055, "learning_rate": 7.342788946570159e-06, "loss": 0.017, "step": 6590 }, { "epoch": 0.29947421855946094, "grad_norm": 0.22837001085281372, "learning_rate": 7.314463525643842e-06, "loss": 0.0206, "step": 6600 }, { "epoch": 0.2999279673754601, "grad_norm": 0.2210777848958969, "learning_rate": 7.286161307367989e-06, "loss": 0.0198, "step": 6610 }, { "epoch": 0.3003817161914593, "grad_norm": 0.19690561294555664, "learning_rate": 7.257882536269716e-06, "loss": 0.0183, "step": 6620 }, { "epoch": 0.3008354650074585, "grad_norm": 0.2845943570137024, "learning_rate": 7.2296274566735494e-06, "loss": 0.0206, "step": 6630 }, { "epoch": 0.3012892138234577, "grad_norm": 0.25788959860801697, "learning_rate": 7.201396312699334e-06, "loss": 0.0172, "step": 6640 }, { "epoch": 0.3017429626394569, "grad_norm": 0.17646299302577972, "learning_rate": 7.173189348260105e-06, "loss": 0.0185, "step": 6650 }, { "epoch": 0.30219671145545607, "grad_norm": 0.18369096517562866, "learning_rate": 7.145006807060002e-06, "loss": 0.0171, "step": 6660 }, { "epoch": 0.3026504602714552, "grad_norm": 0.2480320781469345, "learning_rate": 7.116848932592136e-06, "loss": 0.0213, "step": 6670 }, { "epoch": 0.3031042090874544, "grad_norm": 0.18188251554965973, "learning_rate": 7.088715968136513e-06, "loss": 0.0227, "step": 6680 }, { "epoch": 0.3035579579034536, "grad_norm": 0.2878642678260803, "learning_rate": 7.06060815675792e-06, "loss": 0.0187, "step": 6690 }, { "epoch": 0.30401170671945277, "grad_norm": 0.21322709321975708, "learning_rate": 7.032525741303815e-06, "loss": 0.0196, "step": 6700 }, { "epoch": 0.30446545553545196, "grad_norm": 0.22454646229743958, "learning_rate": 7.00446896440225e-06, "loss": 0.0216, "step": 6710 }, { "epoch": 0.30491920435145115, "grad_norm": 0.2175014615058899, "learning_rate": 6.976438068459756e-06, "loss": 0.0183, "step": 6720 }, { "epoch": 0.30537295316745033, "grad_norm": 0.2045365571975708, "learning_rate": 6.948433295659258e-06, "loss": 0.0209, "step": 6730 }, { "epoch": 0.3058267019834495, "grad_norm": 0.26839253306388855, "learning_rate": 6.920454887957984e-06, "loss": 0.0206, "step": 6740 }, { "epoch": 0.3062804507994487, "grad_norm": 0.3331947326660156, "learning_rate": 6.892503087085365e-06, "loss": 0.0219, "step": 6750 }, { "epoch": 0.3067341996154479, "grad_norm": 0.20764468610286713, "learning_rate": 6.864578134540961e-06, "loss": 0.0197, "step": 6760 }, { "epoch": 0.3071879484314471, "grad_norm": 0.2201288789510727, "learning_rate": 6.83668027159236e-06, "loss": 0.0205, "step": 6770 }, { "epoch": 0.3076416972474462, "grad_norm": 0.269337922334671, "learning_rate": 6.8088097392731035e-06, "loss": 0.0232, "step": 6780 }, { "epoch": 0.3080954460634454, "grad_norm": 0.35234272480010986, "learning_rate": 6.7809667783805934e-06, "loss": 0.0196, "step": 6790 }, { "epoch": 0.3085491948794446, "grad_norm": 0.1890508532524109, "learning_rate": 6.753151629474028e-06, "loss": 0.0186, "step": 6800 }, { "epoch": 0.3090029436954438, "grad_norm": 0.2536371350288391, "learning_rate": 6.725364532872312e-06, "loss": 0.0209, "step": 6810 }, { "epoch": 0.309456692511443, "grad_norm": 0.2378954291343689, "learning_rate": 6.697605728651977e-06, "loss": 0.0184, "step": 6820 }, { "epoch": 0.30991044132744217, "grad_norm": 0.19659966230392456, "learning_rate": 6.669875456645115e-06, "loss": 0.0194, "step": 6830 }, { "epoch": 0.31036419014344135, "grad_norm": 0.22342044115066528, "learning_rate": 6.642173956437306e-06, "loss": 0.0168, "step": 6840 }, { "epoch": 0.31081793895944054, "grad_norm": 0.2003069370985031, "learning_rate": 6.614501467365539e-06, "loss": 0.0166, "step": 6850 }, { "epoch": 0.31127168777543973, "grad_norm": 0.201027050614357, "learning_rate": 6.586858228516162e-06, "loss": 0.0185, "step": 6860 }, { "epoch": 0.3117254365914389, "grad_norm": 0.27186739444732666, "learning_rate": 6.559244478722792e-06, "loss": 0.0205, "step": 6870 }, { "epoch": 0.31217918540743805, "grad_norm": 0.23874634504318237, "learning_rate": 6.531660456564282e-06, "loss": 0.0235, "step": 6880 }, { "epoch": 0.31263293422343724, "grad_norm": 0.22016221284866333, "learning_rate": 6.504106400362621e-06, "loss": 0.0178, "step": 6890 }, { "epoch": 0.31308668303943643, "grad_norm": 0.17675325274467468, "learning_rate": 6.476582548180912e-06, "loss": 0.02, "step": 6900 }, { "epoch": 0.3135404318554356, "grad_norm": 0.2020025998353958, "learning_rate": 6.449089137821301e-06, "loss": 0.0211, "step": 6910 }, { "epoch": 0.3139941806714348, "grad_norm": 0.24167606234550476, "learning_rate": 6.421626406822909e-06, "loss": 0.0179, "step": 6920 }, { "epoch": 0.314447929487434, "grad_norm": 0.35695886611938477, "learning_rate": 6.394194592459801e-06, "loss": 0.0244, "step": 6930 }, { "epoch": 0.3149016783034332, "grad_norm": 0.2835392951965332, "learning_rate": 6.366793931738922e-06, "loss": 0.0221, "step": 6940 }, { "epoch": 0.3153554271194324, "grad_norm": 0.1999538689851761, "learning_rate": 6.339424661398058e-06, "loss": 0.018, "step": 6950 }, { "epoch": 0.31580917593543156, "grad_norm": 0.26503786444664, "learning_rate": 6.312087017903783e-06, "loss": 0.02, "step": 6960 }, { "epoch": 0.31626292475143075, "grad_norm": 0.219223752617836, "learning_rate": 6.284781237449419e-06, "loss": 0.0215, "step": 6970 }, { "epoch": 0.3167166735674299, "grad_norm": 0.22497336566448212, "learning_rate": 6.257507555953002e-06, "loss": 0.02, "step": 6980 }, { "epoch": 0.3171704223834291, "grad_norm": 0.24237129092216492, "learning_rate": 6.230266209055229e-06, "loss": 0.0178, "step": 6990 }, { "epoch": 0.31762417119942826, "grad_norm": 0.23940913379192352, "learning_rate": 6.20305743211744e-06, "loss": 0.0192, "step": 7000 }, { "epoch": 0.31807792001542745, "grad_norm": 0.26866596937179565, "learning_rate": 6.175881460219565e-06, "loss": 0.0169, "step": 7010 }, { "epoch": 0.31853166883142664, "grad_norm": 0.20896877348423004, "learning_rate": 6.148738528158109e-06, "loss": 0.0178, "step": 7020 }, { "epoch": 0.31898541764742583, "grad_norm": 0.15849801898002625, "learning_rate": 6.1216288704441255e-06, "loss": 0.0165, "step": 7030 }, { "epoch": 0.319439166463425, "grad_norm": 0.13429750502109528, "learning_rate": 6.094552721301164e-06, "loss": 0.0203, "step": 7040 }, { "epoch": 0.3198929152794242, "grad_norm": 0.21678827702999115, "learning_rate": 6.067510314663283e-06, "loss": 0.0181, "step": 7050 }, { "epoch": 0.3203466640954234, "grad_norm": 0.2233075499534607, "learning_rate": 6.0405018841729934e-06, "loss": 0.0166, "step": 7060 }, { "epoch": 0.3208004129114226, "grad_norm": 0.2141415774822235, "learning_rate": 6.013527663179275e-06, "loss": 0.0202, "step": 7070 }, { "epoch": 0.3212541617274217, "grad_norm": 0.2212049514055252, "learning_rate": 5.986587884735526e-06, "loss": 0.0226, "step": 7080 }, { "epoch": 0.3217079105434209, "grad_norm": 0.2664652466773987, "learning_rate": 5.9596827815975775e-06, "loss": 0.0205, "step": 7090 }, { "epoch": 0.3221616593594201, "grad_norm": 0.260939359664917, "learning_rate": 5.9328125862216676e-06, "loss": 0.0186, "step": 7100 }, { "epoch": 0.3226154081754193, "grad_norm": 0.2290606051683426, "learning_rate": 5.90597753076243e-06, "loss": 0.0213, "step": 7110 }, { "epoch": 0.32306915699141847, "grad_norm": 0.23798388242721558, "learning_rate": 5.879177847070906e-06, "loss": 0.0181, "step": 7120 }, { "epoch": 0.32352290580741766, "grad_norm": 0.2059733271598816, "learning_rate": 5.8524137666925174e-06, "loss": 0.0167, "step": 7130 }, { "epoch": 0.32397665462341685, "grad_norm": 0.24933315813541412, "learning_rate": 5.825685520865092e-06, "loss": 0.0206, "step": 7140 }, { "epoch": 0.32443040343941604, "grad_norm": 0.2619118094444275, "learning_rate": 5.798993340516843e-06, "loss": 0.0197, "step": 7150 }, { "epoch": 0.3248841522554152, "grad_norm": 0.2078435719013214, "learning_rate": 5.772337456264386e-06, "loss": 0.0197, "step": 7160 }, { "epoch": 0.3253379010714144, "grad_norm": 0.2079591602087021, "learning_rate": 5.745718098410737e-06, "loss": 0.019, "step": 7170 }, { "epoch": 0.32579164988741355, "grad_norm": 0.24563409388065338, "learning_rate": 5.719135496943343e-06, "loss": 0.017, "step": 7180 }, { "epoch": 0.32624539870341274, "grad_norm": 0.2117510437965393, "learning_rate": 5.69258988153207e-06, "loss": 0.018, "step": 7190 }, { "epoch": 0.3266991475194119, "grad_norm": 0.25902894139289856, "learning_rate": 5.666081481527232e-06, "loss": 0.0208, "step": 7200 }, { "epoch": 0.3271528963354111, "grad_norm": 0.23517221212387085, "learning_rate": 5.639610525957604e-06, "loss": 0.0202, "step": 7210 }, { "epoch": 0.3276066451514103, "grad_norm": 0.19750145077705383, "learning_rate": 5.613177243528458e-06, "loss": 0.0187, "step": 7220 }, { "epoch": 0.3280603939674095, "grad_norm": 0.21305380761623383, "learning_rate": 5.586781862619566e-06, "loss": 0.0177, "step": 7230 }, { "epoch": 0.3285141427834087, "grad_norm": 0.20237411558628082, "learning_rate": 5.560424611283231e-06, "loss": 0.0197, "step": 7240 }, { "epoch": 0.32896789159940787, "grad_norm": 0.29556071758270264, "learning_rate": 5.53410571724234e-06, "loss": 0.02, "step": 7250 }, { "epoch": 0.32942164041540706, "grad_norm": 0.28244778513908386, "learning_rate": 5.507825407888362e-06, "loss": 0.0194, "step": 7260 }, { "epoch": 0.32987538923140625, "grad_norm": 0.24878670275211334, "learning_rate": 5.481583910279402e-06, "loss": 0.0214, "step": 7270 }, { "epoch": 0.33032913804740544, "grad_norm": 0.2051086574792862, "learning_rate": 5.4553814511382485e-06, "loss": 0.0184, "step": 7280 }, { "epoch": 0.33078288686340457, "grad_norm": 0.2465798258781433, "learning_rate": 5.429218256850393e-06, "loss": 0.0195, "step": 7290 }, { "epoch": 0.33123663567940376, "grad_norm": 0.22624416649341583, "learning_rate": 5.403094553462083e-06, "loss": 0.0193, "step": 7300 }, { "epoch": 0.33169038449540295, "grad_norm": 0.1823493242263794, "learning_rate": 5.377010566678371e-06, "loss": 0.0226, "step": 7310 }, { "epoch": 0.33214413331140213, "grad_norm": 0.21976806223392487, "learning_rate": 5.350966521861178e-06, "loss": 0.0165, "step": 7320 }, { "epoch": 0.3325978821274013, "grad_norm": 0.2302631437778473, "learning_rate": 5.324962644027312e-06, "loss": 0.0219, "step": 7330 }, { "epoch": 0.3330516309434005, "grad_norm": 0.15457415580749512, "learning_rate": 5.298999157846555e-06, "loss": 0.0173, "step": 7340 }, { "epoch": 0.3335053797593997, "grad_norm": 0.20404797792434692, "learning_rate": 5.273076287639704e-06, "loss": 0.0172, "step": 7350 }, { "epoch": 0.3339591285753989, "grad_norm": 0.17461298406124115, "learning_rate": 5.247194257376653e-06, "loss": 0.0193, "step": 7360 }, { "epoch": 0.3344128773913981, "grad_norm": 0.23847347497940063, "learning_rate": 5.221353290674429e-06, "loss": 0.0177, "step": 7370 }, { "epoch": 0.33486662620739727, "grad_norm": 0.20395506918430328, "learning_rate": 5.1955536107952885e-06, "loss": 0.0163, "step": 7380 }, { "epoch": 0.3353203750233964, "grad_norm": 0.22624146938323975, "learning_rate": 5.169795440644767e-06, "loss": 0.0229, "step": 7390 }, { "epoch": 0.3357741238393956, "grad_norm": 0.22374692559242249, "learning_rate": 5.144079002769766e-06, "loss": 0.0167, "step": 7400 }, { "epoch": 0.3362278726553948, "grad_norm": 0.21310916543006897, "learning_rate": 5.118404519356621e-06, "loss": 0.019, "step": 7410 }, { "epoch": 0.33668162147139397, "grad_norm": 0.26056787371635437, "learning_rate": 5.0927722122292e-06, "loss": 0.0162, "step": 7420 }, { "epoch": 0.33713537028739315, "grad_norm": 0.24963398277759552, "learning_rate": 5.067182302846958e-06, "loss": 0.0181, "step": 7430 }, { "epoch": 0.33758911910339234, "grad_norm": 0.25973621010780334, "learning_rate": 5.041635012303048e-06, "loss": 0.019, "step": 7440 }, { "epoch": 0.33804286791939153, "grad_norm": 0.23397290706634521, "learning_rate": 5.016130561322399e-06, "loss": 0.0157, "step": 7450 }, { "epoch": 0.3384966167353907, "grad_norm": 0.21731317043304443, "learning_rate": 4.990669170259816e-06, "loss": 0.0196, "step": 7460 }, { "epoch": 0.3389503655513899, "grad_norm": 0.1664239913225174, "learning_rate": 4.965251059098074e-06, "loss": 0.0164, "step": 7470 }, { "epoch": 0.3394041143673891, "grad_norm": 0.22290387749671936, "learning_rate": 4.93987644744601e-06, "loss": 0.0205, "step": 7480 }, { "epoch": 0.33985786318338823, "grad_norm": 0.23020334541797638, "learning_rate": 4.9145455545366335e-06, "loss": 0.0158, "step": 7490 }, { "epoch": 0.3403116119993874, "grad_norm": 0.3099934756755829, "learning_rate": 4.889258599225233e-06, "loss": 0.0214, "step": 7500 }, { "epoch": 0.3407653608153866, "grad_norm": 0.17612917721271515, "learning_rate": 4.864015799987474e-06, "loss": 0.0173, "step": 7510 }, { "epoch": 0.3412191096313858, "grad_norm": 0.1966807246208191, "learning_rate": 4.838817374917534e-06, "loss": 0.021, "step": 7520 }, { "epoch": 0.341672858447385, "grad_norm": 0.21183498203754425, "learning_rate": 4.8136635417261935e-06, "loss": 0.0201, "step": 7530 }, { "epoch": 0.3421266072633842, "grad_norm": 0.1787811666727066, "learning_rate": 4.788554517738967e-06, "loss": 0.0188, "step": 7540 }, { "epoch": 0.34258035607938336, "grad_norm": 0.2662833034992218, "learning_rate": 4.763490519894223e-06, "loss": 0.0189, "step": 7550 }, { "epoch": 0.34303410489538255, "grad_norm": 0.24709156155586243, "learning_rate": 4.738471764741319e-06, "loss": 0.0162, "step": 7560 }, { "epoch": 0.34348785371138174, "grad_norm": 0.18904812633991241, "learning_rate": 4.713498468438709e-06, "loss": 0.0221, "step": 7570 }, { "epoch": 0.34394160252738093, "grad_norm": 0.3029699921607971, "learning_rate": 4.6885708467521015e-06, "loss": 0.0199, "step": 7580 }, { "epoch": 0.34439535134338006, "grad_norm": 0.25844594836235046, "learning_rate": 4.6636891150525765e-06, "loss": 0.0212, "step": 7590 }, { "epoch": 0.34484910015937925, "grad_norm": 0.2067583203315735, "learning_rate": 4.638853488314727e-06, "loss": 0.0197, "step": 7600 }, { "epoch": 0.34530284897537844, "grad_norm": 0.27335113286972046, "learning_rate": 4.614064181114817e-06, "loss": 0.0174, "step": 7610 }, { "epoch": 0.34575659779137763, "grad_norm": 0.2858226001262665, "learning_rate": 4.589321407628907e-06, "loss": 0.0183, "step": 7620 }, { "epoch": 0.3462103466073768, "grad_norm": 0.18462637066841125, "learning_rate": 4.5646253816310175e-06, "loss": 0.0184, "step": 7630 }, { "epoch": 0.346664095423376, "grad_norm": 0.22316311299800873, "learning_rate": 4.539976316491272e-06, "loss": 0.0213, "step": 7640 }, { "epoch": 0.3471178442393752, "grad_norm": 0.22587211430072784, "learning_rate": 4.515374425174062e-06, "loss": 0.0164, "step": 7650 }, { "epoch": 0.3475715930553744, "grad_norm": 0.2643914818763733, "learning_rate": 4.49081992023621e-06, "loss": 0.0163, "step": 7660 }, { "epoch": 0.3480253418713736, "grad_norm": 0.20600655674934387, "learning_rate": 4.466313013825119e-06, "loss": 0.0174, "step": 7670 }, { "epoch": 0.34847909068737276, "grad_norm": 0.2640753388404846, "learning_rate": 4.4418539176769456e-06, "loss": 0.0182, "step": 7680 }, { "epoch": 0.3489328395033719, "grad_norm": 0.21331435441970825, "learning_rate": 4.417442843114786e-06, "loss": 0.0191, "step": 7690 }, { "epoch": 0.3493865883193711, "grad_norm": 0.2072087824344635, "learning_rate": 4.393080001046818e-06, "loss": 0.0176, "step": 7700 }, { "epoch": 0.34984033713537027, "grad_norm": 0.24886004626750946, "learning_rate": 4.368765601964516e-06, "loss": 0.0196, "step": 7710 }, { "epoch": 0.35029408595136946, "grad_norm": 0.26744478940963745, "learning_rate": 4.3444998559408025e-06, "loss": 0.0174, "step": 7720 }, { "epoch": 0.35074783476736865, "grad_norm": 0.21310736238956451, "learning_rate": 4.320282972628246e-06, "loss": 0.0189, "step": 7730 }, { "epoch": 0.35120158358336784, "grad_norm": 0.2466854304075241, "learning_rate": 4.2961151612572495e-06, "loss": 0.0208, "step": 7740 }, { "epoch": 0.351655332399367, "grad_norm": 0.23447340726852417, "learning_rate": 4.2719966306342386e-06, "loss": 0.0194, "step": 7750 }, { "epoch": 0.3521090812153662, "grad_norm": 0.24329732358455658, "learning_rate": 4.247927589139869e-06, "loss": 0.0192, "step": 7760 }, { "epoch": 0.3525628300313654, "grad_norm": 0.1723080426454544, "learning_rate": 4.223908244727211e-06, "loss": 0.0178, "step": 7770 }, { "epoch": 0.3530165788473646, "grad_norm": 0.17599564790725708, "learning_rate": 4.199938804919957e-06, "loss": 0.0155, "step": 7780 }, { "epoch": 0.3534703276633637, "grad_norm": 0.20683996379375458, "learning_rate": 4.176019476810631e-06, "loss": 0.0217, "step": 7790 }, { "epoch": 0.3539240764793629, "grad_norm": 0.21528351306915283, "learning_rate": 4.152150467058805e-06, "loss": 0.0199, "step": 7800 }, { "epoch": 0.3543778252953621, "grad_norm": 0.2037600576877594, "learning_rate": 4.128331981889309e-06, "loss": 0.0194, "step": 7810 }, { "epoch": 0.3548315741113613, "grad_norm": 0.26022252440452576, "learning_rate": 4.104564227090437e-06, "loss": 0.0194, "step": 7820 }, { "epoch": 0.3552853229273605, "grad_norm": 0.2321041226387024, "learning_rate": 4.080847408012189e-06, "loss": 0.0168, "step": 7830 }, { "epoch": 0.35573907174335967, "grad_norm": 0.19480140507221222, "learning_rate": 4.057181729564478e-06, "loss": 0.0171, "step": 7840 }, { "epoch": 0.35619282055935886, "grad_norm": 0.25008445978164673, "learning_rate": 4.033567396215387e-06, "loss": 0.0171, "step": 7850 }, { "epoch": 0.35664656937535805, "grad_norm": 0.26359230279922485, "learning_rate": 4.0100046119893654e-06, "loss": 0.0205, "step": 7860 }, { "epoch": 0.35710031819135724, "grad_norm": 0.21542894840240479, "learning_rate": 3.986493580465498e-06, "loss": 0.017, "step": 7870 }, { "epoch": 0.3575540670073564, "grad_norm": 0.21818456053733826, "learning_rate": 3.963034504775727e-06, "loss": 0.0187, "step": 7880 }, { "epoch": 0.3580078158233556, "grad_norm": 0.2781013250350952, "learning_rate": 3.939627587603103e-06, "loss": 0.0232, "step": 7890 }, { "epoch": 0.35846156463935475, "grad_norm": 0.28666985034942627, "learning_rate": 3.9162730311800455e-06, "loss": 0.0191, "step": 7900 }, { "epoch": 0.35891531345535393, "grad_norm": 0.16474290192127228, "learning_rate": 3.8929710372865696e-06, "loss": 0.0197, "step": 7910 }, { "epoch": 0.3593690622713531, "grad_norm": 0.3215365409851074, "learning_rate": 3.869721807248571e-06, "loss": 0.0183, "step": 7920 }, { "epoch": 0.3598228110873523, "grad_norm": 0.3871438503265381, "learning_rate": 3.8465255419360635e-06, "loss": 0.0204, "step": 7930 }, { "epoch": 0.3602765599033515, "grad_norm": 0.17167294025421143, "learning_rate": 3.823382441761454e-06, "loss": 0.0149, "step": 7940 }, { "epoch": 0.3607303087193507, "grad_norm": 0.1664257049560547, "learning_rate": 3.8002927066778193e-06, "loss": 0.0182, "step": 7950 }, { "epoch": 0.3611840575353499, "grad_norm": 0.18233603239059448, "learning_rate": 3.7772565361771596e-06, "loss": 0.021, "step": 7960 }, { "epoch": 0.36163780635134907, "grad_norm": 0.19882334768772125, "learning_rate": 3.75427412928869e-06, "loss": 0.0221, "step": 7970 }, { "epoch": 0.36209155516734826, "grad_norm": 0.2725437581539154, "learning_rate": 3.731345684577109e-06, "loss": 0.0235, "step": 7980 }, { "epoch": 0.36254530398334744, "grad_norm": 0.20906633138656616, "learning_rate": 3.7084714001409016e-06, "loss": 0.0195, "step": 7990 }, { "epoch": 0.3629990527993466, "grad_norm": 0.1636902093887329, "learning_rate": 3.6856514736106063e-06, "loss": 0.0167, "step": 8000 }, { "epoch": 0.36345280161534577, "grad_norm": 0.18917632102966309, "learning_rate": 3.6628861021471185e-06, "loss": 0.019, "step": 8010 }, { "epoch": 0.36390655043134496, "grad_norm": 0.22050239145755768, "learning_rate": 3.6401754824399837e-06, "loss": 0.0174, "step": 8020 }, { "epoch": 0.36436029924734414, "grad_norm": 0.20476284623146057, "learning_rate": 3.6175198107057107e-06, "loss": 0.0176, "step": 8030 }, { "epoch": 0.36481404806334333, "grad_norm": 0.38357430696487427, "learning_rate": 3.5949192826860513e-06, "loss": 0.016, "step": 8040 }, { "epoch": 0.3652677968793425, "grad_norm": 0.20643745362758636, "learning_rate": 3.572374093646336e-06, "loss": 0.0169, "step": 8050 }, { "epoch": 0.3657215456953417, "grad_norm": 0.23504672944545746, "learning_rate": 3.5498844383737653e-06, "loss": 0.0201, "step": 8060 }, { "epoch": 0.3661752945113409, "grad_norm": 0.23273056745529175, "learning_rate": 3.5274505111757405e-06, "loss": 0.0167, "step": 8070 }, { "epoch": 0.3666290433273401, "grad_norm": 0.21831920742988586, "learning_rate": 3.5050725058781765e-06, "loss": 0.021, "step": 8080 }, { "epoch": 0.3670827921433393, "grad_norm": 0.2628321647644043, "learning_rate": 3.482750615823838e-06, "loss": 0.019, "step": 8090 }, { "epoch": 0.3675365409593384, "grad_norm": 0.15779148042201996, "learning_rate": 3.4604850338706554e-06, "loss": 0.0187, "step": 8100 }, { "epoch": 0.3679902897753376, "grad_norm": 0.17342814803123474, "learning_rate": 3.4382759523900678e-06, "loss": 0.0164, "step": 8110 }, { "epoch": 0.3684440385913368, "grad_norm": 0.2353195995092392, "learning_rate": 3.4161235632653587e-06, "loss": 0.0174, "step": 8120 }, { "epoch": 0.368897787407336, "grad_norm": 0.24086785316467285, "learning_rate": 3.394028057889992e-06, "loss": 0.0189, "step": 8130 }, { "epoch": 0.36935153622333516, "grad_norm": 0.2332620620727539, "learning_rate": 3.3719896271659734e-06, "loss": 0.0203, "step": 8140 }, { "epoch": 0.36980528503933435, "grad_norm": 0.3041565716266632, "learning_rate": 3.3500084615021912e-06, "loss": 0.0185, "step": 8150 }, { "epoch": 0.37025903385533354, "grad_norm": 0.19355733692646027, "learning_rate": 3.3280847508127644e-06, "loss": 0.0172, "step": 8160 }, { "epoch": 0.37071278267133273, "grad_norm": 0.2077585905790329, "learning_rate": 3.306218684515413e-06, "loss": 0.0176, "step": 8170 }, { "epoch": 0.3711665314873319, "grad_norm": 0.23010016977787018, "learning_rate": 3.284410451529816e-06, "loss": 0.0151, "step": 8180 }, { "epoch": 0.3716202803033311, "grad_norm": 0.2166825830936432, "learning_rate": 3.2626602402759865e-06, "loss": 0.0174, "step": 8190 }, { "epoch": 0.37207402911933024, "grad_norm": 0.29504096508026123, "learning_rate": 3.240968238672633e-06, "loss": 0.0189, "step": 8200 }, { "epoch": 0.37252777793532943, "grad_norm": 0.23190848529338837, "learning_rate": 3.2193346341355413e-06, "loss": 0.021, "step": 8210 }, { "epoch": 0.3729815267513286, "grad_norm": 0.22032791376113892, "learning_rate": 3.1977596135759524e-06, "loss": 0.0182, "step": 8220 }, { "epoch": 0.3734352755673278, "grad_norm": 0.26597803831100464, "learning_rate": 3.176243363398961e-06, "loss": 0.0196, "step": 8230 }, { "epoch": 0.373889024383327, "grad_norm": 0.41944679617881775, "learning_rate": 3.1547860695018793e-06, "loss": 0.0211, "step": 8240 }, { "epoch": 0.3743427731993262, "grad_norm": 0.19766631722450256, "learning_rate": 3.13338791727266e-06, "loss": 0.0195, "step": 8250 }, { "epoch": 0.3747965220153254, "grad_norm": 0.24090297520160675, "learning_rate": 3.1120490915882694e-06, "loss": 0.0188, "step": 8260 }, { "epoch": 0.37525027083132456, "grad_norm": 0.18546974658966064, "learning_rate": 3.090769776813106e-06, "loss": 0.017, "step": 8270 }, { "epoch": 0.37570401964732375, "grad_norm": 0.20832188427448273, "learning_rate": 3.0695501567973983e-06, "loss": 0.0149, "step": 8280 }, { "epoch": 0.37615776846332294, "grad_norm": 0.3066066801548004, "learning_rate": 3.0483904148756284e-06, "loss": 0.0182, "step": 8290 }, { "epoch": 0.37661151727932207, "grad_norm": 0.23836109042167664, "learning_rate": 3.0272907338649337e-06, "loss": 0.0204, "step": 8300 }, { "epoch": 0.37706526609532126, "grad_norm": 0.2404983788728714, "learning_rate": 3.006251296063536e-06, "loss": 0.0155, "step": 8310 }, { "epoch": 0.37751901491132045, "grad_norm": 0.205276221036911, "learning_rate": 2.985272283249161e-06, "loss": 0.0181, "step": 8320 }, { "epoch": 0.37797276372731964, "grad_norm": 0.23927940428256989, "learning_rate": 2.9643538766774793e-06, "loss": 0.0174, "step": 8330 }, { "epoch": 0.3784265125433188, "grad_norm": 0.1981741040945053, "learning_rate": 2.943496257080527e-06, "loss": 0.0166, "step": 8340 }, { "epoch": 0.378880261359318, "grad_norm": 0.1484595388174057, "learning_rate": 2.9226996046651435e-06, "loss": 0.0189, "step": 8350 }, { "epoch": 0.3793340101753172, "grad_norm": 0.21288150548934937, "learning_rate": 2.901964099111435e-06, "loss": 0.0169, "step": 8360 }, { "epoch": 0.3797877589913164, "grad_norm": 0.1986217498779297, "learning_rate": 2.881289919571193e-06, "loss": 0.02, "step": 8370 }, { "epoch": 0.3802415078073156, "grad_norm": 0.2168169915676117, "learning_rate": 2.860677244666373e-06, "loss": 0.019, "step": 8380 }, { "epoch": 0.38069525662331477, "grad_norm": 0.22702045738697052, "learning_rate": 2.840126252487532e-06, "loss": 0.0227, "step": 8390 }, { "epoch": 0.38114900543931396, "grad_norm": 0.2849196195602417, "learning_rate": 2.8196371205922955e-06, "loss": 0.0192, "step": 8400 }, { "epoch": 0.3816027542553131, "grad_norm": 0.19728435575962067, "learning_rate": 2.799210026003831e-06, "loss": 0.014, "step": 8410 }, { "epoch": 0.3820565030713123, "grad_norm": 0.23504720628261566, "learning_rate": 2.7788451452093067e-06, "loss": 0.0196, "step": 8420 }, { "epoch": 0.38251025188731147, "grad_norm": 0.2267087996006012, "learning_rate": 2.75854265415838e-06, "loss": 0.0175, "step": 8430 }, { "epoch": 0.38296400070331066, "grad_norm": 0.21299123764038086, "learning_rate": 2.738302728261665e-06, "loss": 0.0203, "step": 8440 }, { "epoch": 0.38341774951930985, "grad_norm": 0.19512321054935455, "learning_rate": 2.7181255423892192e-06, "loss": 0.0173, "step": 8450 }, { "epoch": 0.38387149833530904, "grad_norm": 0.22525905072689056, "learning_rate": 2.6980112708690374e-06, "loss": 0.0197, "step": 8460 }, { "epoch": 0.3843252471513082, "grad_norm": 0.22992050647735596, "learning_rate": 2.677960087485547e-06, "loss": 0.0184, "step": 8470 }, { "epoch": 0.3847789959673074, "grad_norm": 0.19968663156032562, "learning_rate": 2.657972165478103e-06, "loss": 0.0152, "step": 8480 }, { "epoch": 0.3852327447833066, "grad_norm": 0.24329829216003418, "learning_rate": 2.638047677539487e-06, "loss": 0.0169, "step": 8490 }, { "epoch": 0.3856864935993058, "grad_norm": 0.18489454686641693, "learning_rate": 2.618186795814418e-06, "loss": 0.0165, "step": 8500 }, { "epoch": 0.3861402424153049, "grad_norm": 0.14432741701602936, "learning_rate": 2.598389691898072e-06, "loss": 0.0201, "step": 8510 }, { "epoch": 0.3865939912313041, "grad_norm": 0.23615561425685883, "learning_rate": 2.578656536834586e-06, "loss": 0.0209, "step": 8520 }, { "epoch": 0.3870477400473033, "grad_norm": 0.3034942150115967, "learning_rate": 2.5589875011156008e-06, "loss": 0.0212, "step": 8530 }, { "epoch": 0.3875014888633025, "grad_norm": 0.1807272732257843, "learning_rate": 2.539382754678764e-06, "loss": 0.0186, "step": 8540 }, { "epoch": 0.3879552376793017, "grad_norm": 0.22360515594482422, "learning_rate": 2.519842466906276e-06, "loss": 0.0152, "step": 8550 }, { "epoch": 0.38840898649530087, "grad_norm": 0.3116665184497833, "learning_rate": 2.5003668066234233e-06, "loss": 0.017, "step": 8560 }, { "epoch": 0.38886273531130006, "grad_norm": 0.1775924563407898, "learning_rate": 2.480955942097121e-06, "loss": 0.0201, "step": 8570 }, { "epoch": 0.38931648412729924, "grad_norm": 0.17597609758377075, "learning_rate": 2.4616100410344634e-06, "loss": 0.0195, "step": 8580 }, { "epoch": 0.38977023294329843, "grad_norm": 0.24290397763252258, "learning_rate": 2.442329270581262e-06, "loss": 0.0215, "step": 8590 }, { "epoch": 0.3902239817592976, "grad_norm": 0.2394474297761917, "learning_rate": 2.4231137973206097e-06, "loss": 0.024, "step": 8600 }, { "epoch": 0.39067773057529676, "grad_norm": 0.3511979281902313, "learning_rate": 2.4039637872714417e-06, "loss": 0.0173, "step": 8610 }, { "epoch": 0.39113147939129594, "grad_norm": 0.22668935358524323, "learning_rate": 2.3848794058871073e-06, "loss": 0.0164, "step": 8620 }, { "epoch": 0.39158522820729513, "grad_norm": 0.20268695056438446, "learning_rate": 2.3658608180539243e-06, "loss": 0.02, "step": 8630 }, { "epoch": 0.3920389770232943, "grad_norm": 0.179142564535141, "learning_rate": 2.3469081880897694e-06, "loss": 0.0169, "step": 8640 }, { "epoch": 0.3924927258392935, "grad_norm": 0.21003682911396027, "learning_rate": 2.328021679742648e-06, "loss": 0.0151, "step": 8650 }, { "epoch": 0.3929464746552927, "grad_norm": 0.22208799421787262, "learning_rate": 2.309201456189286e-06, "loss": 0.0172, "step": 8660 }, { "epoch": 0.3934002234712919, "grad_norm": 0.22922950983047485, "learning_rate": 2.290447680033725e-06, "loss": 0.0184, "step": 8670 }, { "epoch": 0.3938539722872911, "grad_norm": 0.182240828871727, "learning_rate": 2.2717605133059007e-06, "loss": 0.0197, "step": 8680 }, { "epoch": 0.39430772110329027, "grad_norm": 0.2676272392272949, "learning_rate": 2.253140117460255e-06, "loss": 0.0173, "step": 8690 }, { "epoch": 0.39476146991928945, "grad_norm": 0.1963319331407547, "learning_rate": 2.2345866533743453e-06, "loss": 0.0171, "step": 8700 }, { "epoch": 0.3952152187352886, "grad_norm": 0.22058439254760742, "learning_rate": 2.2161002813474397e-06, "loss": 0.0174, "step": 8710 }, { "epoch": 0.3956689675512878, "grad_norm": 0.20596040785312653, "learning_rate": 2.197681161099149e-06, "loss": 0.0136, "step": 8720 }, { "epoch": 0.39612271636728696, "grad_norm": 0.19986265897750854, "learning_rate": 2.179329451768031e-06, "loss": 0.018, "step": 8730 }, { "epoch": 0.39657646518328615, "grad_norm": 0.1921948492527008, "learning_rate": 2.161045311910227e-06, "loss": 0.017, "step": 8740 }, { "epoch": 0.39703021399928534, "grad_norm": 0.219204381108284, "learning_rate": 2.1428288994980816e-06, "loss": 0.0165, "step": 8750 }, { "epoch": 0.39748396281528453, "grad_norm": 0.27743470668792725, "learning_rate": 2.124680371918796e-06, "loss": 0.0201, "step": 8760 }, { "epoch": 0.3979377116312837, "grad_norm": 0.19118790328502655, "learning_rate": 2.106599885973044e-06, "loss": 0.0158, "step": 8770 }, { "epoch": 0.3983914604472829, "grad_norm": 0.27478182315826416, "learning_rate": 2.088587597873637e-06, "loss": 0.0175, "step": 8780 }, { "epoch": 0.3988452092632821, "grad_norm": 0.23517444729804993, "learning_rate": 2.070643663244163e-06, "loss": 0.0171, "step": 8790 }, { "epoch": 0.3992989580792813, "grad_norm": 0.2089490443468094, "learning_rate": 2.052768237117644e-06, "loss": 0.0196, "step": 8800 }, { "epoch": 0.3997527068952804, "grad_norm": 0.22132115066051483, "learning_rate": 2.034961473935203e-06, "loss": 0.0142, "step": 8810 }, { "epoch": 0.4002064557112796, "grad_norm": 0.15413549542427063, "learning_rate": 2.0172235275447284e-06, "loss": 0.0167, "step": 8820 }, { "epoch": 0.4006602045272788, "grad_norm": 0.3665509819984436, "learning_rate": 1.9995545511995316e-06, "loss": 0.0191, "step": 8830 }, { "epoch": 0.401113953343278, "grad_norm": 0.2389543503522873, "learning_rate": 1.9819546975570382e-06, "loss": 0.0168, "step": 8840 }, { "epoch": 0.4015677021592772, "grad_norm": 0.2531464397907257, "learning_rate": 1.9644241186774593e-06, "loss": 0.0181, "step": 8850 }, { "epoch": 0.40202145097527636, "grad_norm": 0.1910611242055893, "learning_rate": 1.9469629660224907e-06, "loss": 0.0185, "step": 8860 }, { "epoch": 0.40247519979127555, "grad_norm": 0.2145034521818161, "learning_rate": 1.9295713904539892e-06, "loss": 0.0143, "step": 8870 }, { "epoch": 0.40292894860727474, "grad_norm": 0.1535291224718094, "learning_rate": 1.912249542232675e-06, "loss": 0.0159, "step": 8880 }, { "epoch": 0.40338269742327393, "grad_norm": 0.21727003157138824, "learning_rate": 1.8949975710168357e-06, "loss": 0.0192, "step": 8890 }, { "epoch": 0.4038364462392731, "grad_norm": 0.18695808947086334, "learning_rate": 1.8778156258610292e-06, "loss": 0.0186, "step": 8900 }, { "epoch": 0.40429019505527225, "grad_norm": 0.1732257604598999, "learning_rate": 1.8607038552148039e-06, "loss": 0.0183, "step": 8910 }, { "epoch": 0.40474394387127144, "grad_norm": 0.2799364924430847, "learning_rate": 1.8436624069214071e-06, "loss": 0.0147, "step": 8920 }, { "epoch": 0.4051976926872706, "grad_norm": 0.2145470529794693, "learning_rate": 1.8266914282165116e-06, "loss": 0.0174, "step": 8930 }, { "epoch": 0.4056514415032698, "grad_norm": 0.1563456952571869, "learning_rate": 1.80979106572694e-06, "loss": 0.0169, "step": 8940 }, { "epoch": 0.406105190319269, "grad_norm": 0.2046218365430832, "learning_rate": 1.792961465469404e-06, "loss": 0.019, "step": 8950 }, { "epoch": 0.4065589391352682, "grad_norm": 0.33911705017089844, "learning_rate": 1.7762027728492405e-06, "loss": 0.0193, "step": 8960 }, { "epoch": 0.4070126879512674, "grad_norm": 0.2194845974445343, "learning_rate": 1.759515132659153e-06, "loss": 0.0178, "step": 8970 }, { "epoch": 0.40746643676726657, "grad_norm": 0.19535672664642334, "learning_rate": 1.742898689077961e-06, "loss": 0.0178, "step": 8980 }, { "epoch": 0.40792018558326576, "grad_norm": 0.16949088871479034, "learning_rate": 1.726353585669356e-06, "loss": 0.0164, "step": 8990 }, { "epoch": 0.40837393439926495, "grad_norm": 0.2303561270236969, "learning_rate": 1.7098799653806663e-06, "loss": 0.0153, "step": 9000 }, { "epoch": 0.40882768321526414, "grad_norm": 0.23082293570041656, "learning_rate": 1.6934779705416082e-06, "loss": 0.0157, "step": 9010 }, { "epoch": 0.40928143203126327, "grad_norm": 0.26789599657058716, "learning_rate": 1.6771477428630656e-06, "loss": 0.0181, "step": 9020 }, { "epoch": 0.40973518084726246, "grad_norm": 0.22070877254009247, "learning_rate": 1.6608894234358708e-06, "loss": 0.0168, "step": 9030 }, { "epoch": 0.41018892966326165, "grad_norm": 0.182155042886734, "learning_rate": 1.6447031527295744e-06, "loss": 0.0202, "step": 9040 }, { "epoch": 0.41064267847926084, "grad_norm": 0.2134721875190735, "learning_rate": 1.628589070591232e-06, "loss": 0.0192, "step": 9050 }, { "epoch": 0.41109642729526, "grad_norm": 0.1833111196756363, "learning_rate": 1.6125473162442107e-06, "loss": 0.0174, "step": 9060 }, { "epoch": 0.4115501761112592, "grad_norm": 0.31482499837875366, "learning_rate": 1.5965780282869693e-06, "loss": 0.0173, "step": 9070 }, { "epoch": 0.4120039249272584, "grad_norm": 0.1493026167154312, "learning_rate": 1.5806813446918657e-06, "loss": 0.0144, "step": 9080 }, { "epoch": 0.4124576737432576, "grad_norm": 0.18066266179084778, "learning_rate": 1.56485740280397e-06, "loss": 0.0165, "step": 9090 }, { "epoch": 0.4129114225592568, "grad_norm": 0.19344116747379303, "learning_rate": 1.5491063393398742e-06, "loss": 0.0219, "step": 9100 }, { "epoch": 0.41336517137525597, "grad_norm": 0.24727752804756165, "learning_rate": 1.5334282903865116e-06, "loss": 0.0179, "step": 9110 }, { "epoch": 0.4138189201912551, "grad_norm": 0.152756005525589, "learning_rate": 1.5178233913999784e-06, "loss": 0.0168, "step": 9120 }, { "epoch": 0.4142726690072543, "grad_norm": 0.22353465855121613, "learning_rate": 1.5022917772043633e-06, "loss": 0.0165, "step": 9130 }, { "epoch": 0.4147264178232535, "grad_norm": 0.15244455635547638, "learning_rate": 1.4868335819905922e-06, "loss": 0.0143, "step": 9140 }, { "epoch": 0.41518016663925267, "grad_norm": 0.23933374881744385, "learning_rate": 1.4714489393152586e-06, "loss": 0.0167, "step": 9150 }, { "epoch": 0.41563391545525186, "grad_norm": 0.1905471682548523, "learning_rate": 1.4561379820994692e-06, "loss": 0.0144, "step": 9160 }, { "epoch": 0.41608766427125105, "grad_norm": 0.19611003994941711, "learning_rate": 1.4409008426277028e-06, "loss": 0.0198, "step": 9170 }, { "epoch": 0.41654141308725023, "grad_norm": 0.23017026484012604, "learning_rate": 1.4257376525466594e-06, "loss": 0.0185, "step": 9180 }, { "epoch": 0.4169951619032494, "grad_norm": 0.21117550134658813, "learning_rate": 1.4106485428641292e-06, "loss": 0.0168, "step": 9190 }, { "epoch": 0.4174489107192486, "grad_norm": 0.21176713705062866, "learning_rate": 1.3956336439478612e-06, "loss": 0.0174, "step": 9200 }, { "epoch": 0.4179026595352478, "grad_norm": 0.2167995274066925, "learning_rate": 1.3806930855244315e-06, "loss": 0.0157, "step": 9210 }, { "epoch": 0.41835640835124693, "grad_norm": 0.19552898406982422, "learning_rate": 1.3658269966781223e-06, "loss": 0.0165, "step": 9220 }, { "epoch": 0.4188101571672461, "grad_norm": 0.20337951183319092, "learning_rate": 1.3510355058498114e-06, "loss": 0.0182, "step": 9230 }, { "epoch": 0.4192639059832453, "grad_norm": 0.16430819034576416, "learning_rate": 1.3363187408358612e-06, "loss": 0.0154, "step": 9240 }, { "epoch": 0.4197176547992445, "grad_norm": 0.20898699760437012, "learning_rate": 1.3216768287870185e-06, "loss": 0.0152, "step": 9250 }, { "epoch": 0.4201714036152437, "grad_norm": 0.24020332098007202, "learning_rate": 1.3071098962073004e-06, "loss": 0.0188, "step": 9260 }, { "epoch": 0.4206251524312429, "grad_norm": 0.16636548936367035, "learning_rate": 1.292618068952921e-06, "loss": 0.0171, "step": 9270 }, { "epoch": 0.42107890124724207, "grad_norm": 0.20785503089427948, "learning_rate": 1.2782014722311897e-06, "loss": 0.0183, "step": 9280 }, { "epoch": 0.42153265006324125, "grad_norm": 0.26195552945137024, "learning_rate": 1.2638602305994364e-06, "loss": 0.0177, "step": 9290 }, { "epoch": 0.42198639887924044, "grad_norm": 0.1636352241039276, "learning_rate": 1.2495944679639383e-06, "loss": 0.0197, "step": 9300 }, { "epoch": 0.42244014769523963, "grad_norm": 0.15810459852218628, "learning_rate": 1.2354043075788391e-06, "loss": 0.0181, "step": 9310 }, { "epoch": 0.42289389651123876, "grad_norm": 0.21599866449832916, "learning_rate": 1.2212898720450915e-06, "loss": 0.0199, "step": 9320 }, { "epoch": 0.42334764532723795, "grad_norm": 0.21545834839344025, "learning_rate": 1.2072512833093964e-06, "loss": 0.0205, "step": 9330 }, { "epoch": 0.42380139414323714, "grad_norm": 0.2618306577205658, "learning_rate": 1.1932886626631512e-06, "loss": 0.0201, "step": 9340 }, { "epoch": 0.42425514295923633, "grad_norm": 0.2640337347984314, "learning_rate": 1.179402130741396e-06, "loss": 0.0144, "step": 9350 }, { "epoch": 0.4247088917752355, "grad_norm": 0.292324423789978, "learning_rate": 1.165591807521781e-06, "loss": 0.0196, "step": 9360 }, { "epoch": 0.4251626405912347, "grad_norm": 0.22311925888061523, "learning_rate": 1.1518578123235191e-06, "loss": 0.0143, "step": 9370 }, { "epoch": 0.4256163894072339, "grad_norm": 0.24455425143241882, "learning_rate": 1.1382002638063584e-06, "loss": 0.0161, "step": 9380 }, { "epoch": 0.4260701382232331, "grad_norm": 0.22929251194000244, "learning_rate": 1.1246192799695666e-06, "loss": 0.0175, "step": 9390 }, { "epoch": 0.4265238870392323, "grad_norm": 0.2091277539730072, "learning_rate": 1.1111149781508968e-06, "loss": 0.0166, "step": 9400 }, { "epoch": 0.42697763585523146, "grad_norm": 0.22935499250888824, "learning_rate": 1.0976874750255828e-06, "loss": 0.0179, "step": 9410 }, { "epoch": 0.4274313846712306, "grad_norm": 0.19092696905136108, "learning_rate": 1.0843368866053271e-06, "loss": 0.0152, "step": 9420 }, { "epoch": 0.4278851334872298, "grad_norm": 0.2236206978559494, "learning_rate": 1.0710633282372996e-06, "loss": 0.0171, "step": 9430 }, { "epoch": 0.428338882303229, "grad_norm": 0.22642573714256287, "learning_rate": 1.0578669146031484e-06, "loss": 0.0179, "step": 9440 }, { "epoch": 0.42879263111922816, "grad_norm": 0.3372604250907898, "learning_rate": 1.0447477597179945e-06, "loss": 0.0166, "step": 9450 }, { "epoch": 0.42924637993522735, "grad_norm": 0.2291509509086609, "learning_rate": 1.0317059769294557e-06, "loss": 0.0177, "step": 9460 }, { "epoch": 0.42970012875122654, "grad_norm": 0.2076577991247177, "learning_rate": 1.0187416789166672e-06, "loss": 0.0158, "step": 9470 }, { "epoch": 0.43015387756722573, "grad_norm": 0.18335948884487152, "learning_rate": 1.0058549776893068e-06, "loss": 0.0201, "step": 9480 }, { "epoch": 0.4306076263832249, "grad_norm": 0.2721617519855499, "learning_rate": 9.930459845866313e-07, "loss": 0.0182, "step": 9490 }, { "epoch": 0.4310613751992241, "grad_norm": 0.23250319063663483, "learning_rate": 9.803148102765026e-07, "loss": 0.0169, "step": 9500 }, { "epoch": 0.4315151240152233, "grad_norm": 0.21075530350208282, "learning_rate": 9.676615647544452e-07, "loss": 0.0155, "step": 9510 }, { "epoch": 0.4319688728312225, "grad_norm": 0.3027089834213257, "learning_rate": 9.550863573426838e-07, "loss": 0.0185, "step": 9520 }, { "epoch": 0.4324226216472216, "grad_norm": 0.26451584696769714, "learning_rate": 9.425892966892136e-07, "loss": 0.0178, "step": 9530 }, { "epoch": 0.4328763704632208, "grad_norm": 0.22204019129276276, "learning_rate": 9.301704907668474e-07, "loss": 0.0144, "step": 9540 }, { "epoch": 0.43333011927922, "grad_norm": 0.1676533967256546, "learning_rate": 9.178300468722901e-07, "loss": 0.0182, "step": 9550 }, { "epoch": 0.4337838680952192, "grad_norm": 0.23854704201221466, "learning_rate": 9.055680716252068e-07, "loss": 0.0157, "step": 9560 }, { "epoch": 0.43423761691121837, "grad_norm": 0.1891033798456192, "learning_rate": 8.933846709673078e-07, "loss": 0.0168, "step": 9570 }, { "epoch": 0.43469136572721756, "grad_norm": 0.22702954709529877, "learning_rate": 8.812799501614311e-07, "loss": 0.018, "step": 9580 }, { "epoch": 0.43514511454321675, "grad_norm": 0.16833138465881348, "learning_rate": 8.692540137906314e-07, "loss": 0.015, "step": 9590 }, { "epoch": 0.43559886335921594, "grad_norm": 0.21077820658683777, "learning_rate": 8.573069657572752e-07, "loss": 0.0166, "step": 9600 }, { "epoch": 0.4360526121752151, "grad_norm": 0.2160915732383728, "learning_rate": 8.454389092821458e-07, "loss": 0.016, "step": 9610 }, { "epoch": 0.4365063609912143, "grad_norm": 0.17159336805343628, "learning_rate": 8.336499469035509e-07, "loss": 0.0213, "step": 9620 }, { "epoch": 0.43696010980721345, "grad_norm": 0.17026923596858978, "learning_rate": 8.219401804764382e-07, "loss": 0.0176, "step": 9630 }, { "epoch": 0.43741385862321264, "grad_norm": 0.2646191716194153, "learning_rate": 8.10309711171512e-07, "loss": 0.0177, "step": 9640 }, { "epoch": 0.4378676074392118, "grad_norm": 0.21445144712924957, "learning_rate": 7.987586394743608e-07, "loss": 0.0175, "step": 9650 }, { "epoch": 0.438321356255211, "grad_norm": 0.22055840492248535, "learning_rate": 7.872870651845888e-07, "loss": 0.0154, "step": 9660 }, { "epoch": 0.4387751050712102, "grad_norm": 0.30352237820625305, "learning_rate": 7.758950874149541e-07, "loss": 0.0191, "step": 9670 }, { "epoch": 0.4392288538872094, "grad_norm": 0.2708531320095062, "learning_rate": 7.645828045905157e-07, "loss": 0.0207, "step": 9680 }, { "epoch": 0.4396826027032086, "grad_norm": 0.1980200707912445, "learning_rate": 7.533503144477738e-07, "loss": 0.0165, "step": 9690 }, { "epoch": 0.44013635151920777, "grad_norm": 0.24033893644809723, "learning_rate": 7.421977140338376e-07, "loss": 0.0215, "step": 9700 }, { "epoch": 0.44059010033520696, "grad_norm": 0.25309786200523376, "learning_rate": 7.311250997055752e-07, "loss": 0.0163, "step": 9710 }, { "epoch": 0.44104384915120615, "grad_norm": 0.24630549550056458, "learning_rate": 7.201325671287862e-07, "loss": 0.0203, "step": 9720 }, { "epoch": 0.4414975979672053, "grad_norm": 0.21025419235229492, "learning_rate": 7.092202112773817e-07, "loss": 0.0185, "step": 9730 }, { "epoch": 0.44195134678320447, "grad_norm": 0.17289038002490997, "learning_rate": 6.983881264325521e-07, "loss": 0.0133, "step": 9740 }, { "epoch": 0.44240509559920366, "grad_norm": 0.16652344167232513, "learning_rate": 6.876364061819574e-07, "loss": 0.0165, "step": 9750 }, { "epoch": 0.44285884441520285, "grad_norm": 0.20287272334098816, "learning_rate": 6.769651434189195e-07, "loss": 0.0154, "step": 9760 }, { "epoch": 0.44331259323120203, "grad_norm": 0.29289719462394714, "learning_rate": 6.663744303416231e-07, "loss": 0.0167, "step": 9770 }, { "epoch": 0.4437663420472012, "grad_norm": 0.2103530913591385, "learning_rate": 6.558643584523117e-07, "loss": 0.0168, "step": 9780 }, { "epoch": 0.4442200908632004, "grad_norm": 0.17945852875709534, "learning_rate": 6.454350185564994e-07, "loss": 0.0185, "step": 9790 }, { "epoch": 0.4446738396791996, "grad_norm": 0.18782606720924377, "learning_rate": 6.350865007621887e-07, "loss": 0.0161, "step": 9800 }, { "epoch": 0.4451275884951988, "grad_norm": 0.18094444274902344, "learning_rate": 6.248188944790933e-07, "loss": 0.0154, "step": 9810 }, { "epoch": 0.445581337311198, "grad_norm": 0.14802467823028564, "learning_rate": 6.146322884178591e-07, "loss": 0.0162, "step": 9820 }, { "epoch": 0.4460350861271971, "grad_norm": 0.31010594964027405, "learning_rate": 6.045267705893043e-07, "loss": 0.0167, "step": 9830 }, { "epoch": 0.4464888349431963, "grad_norm": 0.18781137466430664, "learning_rate": 5.945024283036549e-07, "loss": 0.0166, "step": 9840 }, { "epoch": 0.4469425837591955, "grad_norm": 0.1975107640028, "learning_rate": 5.845593481697931e-07, "loss": 0.0164, "step": 9850 }, { "epoch": 0.4473963325751947, "grad_norm": 0.23337914049625397, "learning_rate": 5.746976160945051e-07, "loss": 0.0161, "step": 9860 }, { "epoch": 0.44785008139119387, "grad_norm": 0.3309672772884369, "learning_rate": 5.649173172817457e-07, "loss": 0.02, "step": 9870 }, { "epoch": 0.44830383020719305, "grad_norm": 0.23723341524600983, "learning_rate": 5.55218536231894e-07, "loss": 0.0183, "step": 9880 }, { "epoch": 0.44875757902319224, "grad_norm": 0.19621120393276215, "learning_rate": 5.456013567410312e-07, "loss": 0.0167, "step": 9890 }, { "epoch": 0.44921132783919143, "grad_norm": 0.2704184651374817, "learning_rate": 5.360658619002068e-07, "loss": 0.0169, "step": 9900 }, { "epoch": 0.4496650766551906, "grad_norm": 0.16981199383735657, "learning_rate": 5.266121340947327e-07, "loss": 0.0171, "step": 9910 }, { "epoch": 0.4501188254711898, "grad_norm": 0.16770265996456146, "learning_rate": 5.172402550034639e-07, "loss": 0.0165, "step": 9920 }, { "epoch": 0.45057257428718894, "grad_norm": 0.1658024936914444, "learning_rate": 5.079503055980939e-07, "loss": 0.0152, "step": 9930 }, { "epoch": 0.45102632310318813, "grad_norm": 0.15647588670253754, "learning_rate": 4.987423661424517e-07, "loss": 0.0177, "step": 9940 }, { "epoch": 0.4514800719191873, "grad_norm": 0.16305598616600037, "learning_rate": 4.896165161918176e-07, "loss": 0.0162, "step": 9950 }, { "epoch": 0.4519338207351865, "grad_norm": 0.2395927459001541, "learning_rate": 4.805728345922267e-07, "loss": 0.0164, "step": 9960 }, { "epoch": 0.4523875695511857, "grad_norm": 0.2572346329689026, "learning_rate": 4.716113994797944e-07, "loss": 0.0202, "step": 9970 }, { "epoch": 0.4528413183671849, "grad_norm": 0.19618025422096252, "learning_rate": 4.627322882800345e-07, "loss": 0.0189, "step": 9980 }, { "epoch": 0.4532950671831841, "grad_norm": 0.20489995181560516, "learning_rate": 4.5393557770719744e-07, "loss": 0.0169, "step": 9990 }, { "epoch": 0.45374881599918326, "grad_norm": 0.35343989729881287, "learning_rate": 4.4522134376359995e-07, "loss": 0.0174, "step": 10000 }, { "epoch": 0.45420256481518245, "grad_norm": 0.17002807557582855, "learning_rate": 4.3658966173897866e-07, "loss": 0.0158, "step": 10010 }, { "epoch": 0.45465631363118164, "grad_norm": 0.20579101145267487, "learning_rate": 4.2804060620982747e-07, "loss": 0.0143, "step": 10020 }, { "epoch": 0.4551100624471808, "grad_norm": 0.22663666307926178, "learning_rate": 4.1957425103876235e-07, "loss": 0.0183, "step": 10030 }, { "epoch": 0.45556381126317996, "grad_norm": 0.2365342378616333, "learning_rate": 4.111906693738799e-07, "loss": 0.0157, "step": 10040 }, { "epoch": 0.45601756007917915, "grad_norm": 0.23625770211219788, "learning_rate": 4.02889933648124e-07, "loss": 0.0166, "step": 10050 }, { "epoch": 0.45647130889517834, "grad_norm": 0.18118730187416077, "learning_rate": 3.946721155786615e-07, "loss": 0.0147, "step": 10060 }, { "epoch": 0.45692505771117753, "grad_norm": 0.21234753727912903, "learning_rate": 3.865372861662664e-07, "loss": 0.0156, "step": 10070 }, { "epoch": 0.4573788065271767, "grad_norm": 0.2700849771499634, "learning_rate": 3.784855156946965e-07, "loss": 0.0179, "step": 10080 }, { "epoch": 0.4578325553431759, "grad_norm": 0.21397168934345245, "learning_rate": 3.705168737300968e-07, "loss": 0.018, "step": 10090 }, { "epoch": 0.4582863041591751, "grad_norm": 0.23623831570148468, "learning_rate": 3.626314291203914e-07, "loss": 0.0189, "step": 10100 }, { "epoch": 0.4587400529751743, "grad_norm": 0.29518523812294006, "learning_rate": 3.548292499946937e-07, "loss": 0.0177, "step": 10110 }, { "epoch": 0.4591938017911735, "grad_norm": 0.2397976815700531, "learning_rate": 3.4711040376271264e-07, "loss": 0.0167, "step": 10120 }, { "epoch": 0.45964755060717266, "grad_norm": 0.15850749611854553, "learning_rate": 3.394749571141731e-07, "loss": 0.0176, "step": 10130 }, { "epoch": 0.4601012994231718, "grad_norm": 0.27368271350860596, "learning_rate": 3.319229760182441e-07, "loss": 0.0178, "step": 10140 }, { "epoch": 0.460555048239171, "grad_norm": 0.26129502058029175, "learning_rate": 3.244545257229559e-07, "loss": 0.0197, "step": 10150 }, { "epoch": 0.46100879705517017, "grad_norm": 0.18075808882713318, "learning_rate": 3.170696707546539e-07, "loss": 0.0145, "step": 10160 }, { "epoch": 0.46146254587116936, "grad_norm": 0.2580951452255249, "learning_rate": 3.0976847491742347e-07, "loss": 0.0168, "step": 10170 }, { "epoch": 0.46191629468716855, "grad_norm": 0.24518164992332458, "learning_rate": 3.0255100129255364e-07, "loss": 0.0179, "step": 10180 }, { "epoch": 0.46237004350316774, "grad_norm": 0.25864318013191223, "learning_rate": 2.9541731223797997e-07, "loss": 0.0173, "step": 10190 }, { "epoch": 0.4628237923191669, "grad_norm": 0.19043289124965668, "learning_rate": 2.883674693877558e-07, "loss": 0.0189, "step": 10200 }, { "epoch": 0.4632775411351661, "grad_norm": 0.23077310621738434, "learning_rate": 2.8140153365151304e-07, "loss": 0.0199, "step": 10210 }, { "epoch": 0.4637312899511653, "grad_norm": 0.1325322985649109, "learning_rate": 2.7451956521393983e-07, "loss": 0.0162, "step": 10220 }, { "epoch": 0.4641850387671645, "grad_norm": 0.19644874334335327, "learning_rate": 2.677216235342561e-07, "loss": 0.0159, "step": 10230 }, { "epoch": 0.4646387875831636, "grad_norm": 0.2231120467185974, "learning_rate": 2.6100776734570345e-07, "loss": 0.0163, "step": 10240 }, { "epoch": 0.4650925363991628, "grad_norm": 0.18576791882514954, "learning_rate": 2.543780546550401e-07, "loss": 0.0163, "step": 10250 }, { "epoch": 0.465546285215162, "grad_norm": 0.28033897280693054, "learning_rate": 2.478325427420336e-07, "loss": 0.0171, "step": 10260 }, { "epoch": 0.4660000340311612, "grad_norm": 0.18283602595329285, "learning_rate": 2.4137128815896803e-07, "loss": 0.0193, "step": 10270 }, { "epoch": 0.4664537828471604, "grad_norm": 0.2163003385066986, "learning_rate": 2.3499434673015852e-07, "loss": 0.016, "step": 10280 }, { "epoch": 0.46690753166315957, "grad_norm": 0.19510361552238464, "learning_rate": 2.2870177355146406e-07, "loss": 0.0165, "step": 10290 }, { "epoch": 0.46736128047915876, "grad_norm": 0.18789814412593842, "learning_rate": 2.2249362298981892e-07, "loss": 0.0184, "step": 10300 }, { "epoch": 0.46781502929515795, "grad_norm": 0.19117625057697296, "learning_rate": 2.1636994868275085e-07, "loss": 0.0147, "step": 10310 }, { "epoch": 0.46826877811115714, "grad_norm": 0.1819297969341278, "learning_rate": 2.1033080353793144e-07, "loss": 0.0173, "step": 10320 }, { "epoch": 0.4687225269271563, "grad_norm": 0.19878485798835754, "learning_rate": 2.043762397327087e-07, "loss": 0.0158, "step": 10330 }, { "epoch": 0.46917627574315546, "grad_norm": 0.2619016766548157, "learning_rate": 1.985063087136596e-07, "loss": 0.0184, "step": 10340 }, { "epoch": 0.46963002455915465, "grad_norm": 0.22839473187923431, "learning_rate": 1.927210611961494e-07, "loss": 0.0169, "step": 10350 }, { "epoch": 0.47008377337515383, "grad_norm": 0.2152249962091446, "learning_rate": 1.870205471638864e-07, "loss": 0.0154, "step": 10360 }, { "epoch": 0.470537522191153, "grad_norm": 0.2347036451101303, "learning_rate": 1.814048158684978e-07, "loss": 0.017, "step": 10370 }, { "epoch": 0.4709912710071522, "grad_norm": 0.24439676105976105, "learning_rate": 1.7587391582909452e-07, "loss": 0.0186, "step": 10380 }, { "epoch": 0.4714450198231514, "grad_norm": 0.2520765960216522, "learning_rate": 1.7042789483186273e-07, "loss": 0.0166, "step": 10390 }, { "epoch": 0.4718987686391506, "grad_norm": 0.19862018525600433, "learning_rate": 1.6506679992964292e-07, "loss": 0.0155, "step": 10400 }, { "epoch": 0.4723525174551498, "grad_norm": 0.2638033628463745, "learning_rate": 1.597906774415281e-07, "loss": 0.0172, "step": 10410 }, { "epoch": 0.47280626627114897, "grad_norm": 0.25144580006599426, "learning_rate": 1.5459957295245965e-07, "loss": 0.0152, "step": 10420 }, { "epoch": 0.47326001508714816, "grad_norm": 0.270696759223938, "learning_rate": 1.494935313128376e-07, "loss": 0.0155, "step": 10430 }, { "epoch": 0.4737137639031473, "grad_norm": 0.2547527253627777, "learning_rate": 1.4447259663812886e-07, "loss": 0.0207, "step": 10440 }, { "epoch": 0.4741675127191465, "grad_norm": 0.202657550573349, "learning_rate": 1.395368123084917e-07, "loss": 0.0162, "step": 10450 }, { "epoch": 0.47462126153514567, "grad_norm": 0.21430754661560059, "learning_rate": 1.3468622096839524e-07, "loss": 0.0183, "step": 10460 }, { "epoch": 0.47507501035114486, "grad_norm": 0.17567235231399536, "learning_rate": 1.2992086452625175e-07, "loss": 0.0139, "step": 10470 }, { "epoch": 0.47552875916714404, "grad_norm": 0.32823416590690613, "learning_rate": 1.252407841540626e-07, "loss": 0.0169, "step": 10480 }, { "epoch": 0.47598250798314323, "grad_norm": 0.24869294464588165, "learning_rate": 1.2064602028704742e-07, "loss": 0.0159, "step": 10490 }, { "epoch": 0.4764362567991424, "grad_norm": 0.2136104553937912, "learning_rate": 1.1613661262331099e-07, "loss": 0.0162, "step": 10500 }, { "epoch": 0.4768900056151416, "grad_norm": 0.27197444438934326, "learning_rate": 1.1171260012348805e-07, "loss": 0.0176, "step": 10510 }, { "epoch": 0.4773437544311408, "grad_norm": 0.1990833878517151, "learning_rate": 1.0737402101041349e-07, "loss": 0.0147, "step": 10520 }, { "epoch": 0.47779750324714, "grad_norm": 0.18487419188022614, "learning_rate": 1.0312091276878821e-07, "loss": 0.0175, "step": 10530 }, { "epoch": 0.4782512520631391, "grad_norm": 0.18671709299087524, "learning_rate": 9.895331214485937e-08, "loss": 0.0171, "step": 10540 }, { "epoch": 0.4787050008791383, "grad_norm": 0.20831847190856934, "learning_rate": 9.487125514610063e-08, "loss": 0.0154, "step": 10550 }, { "epoch": 0.4791587496951375, "grad_norm": 0.24920013546943665, "learning_rate": 9.087477704089686e-08, "loss": 0.0177, "step": 10560 }, { "epoch": 0.4796124985111367, "grad_norm": 0.21350209414958954, "learning_rate": 8.696391235824886e-08, "loss": 0.0189, "step": 10570 }, { "epoch": 0.4800662473271359, "grad_norm": 0.2606104612350464, "learning_rate": 8.313869488746574e-08, "loss": 0.0144, "step": 10580 }, { "epoch": 0.48051999614313506, "grad_norm": 0.2248334139585495, "learning_rate": 7.939915767787853e-08, "loss": 0.0155, "step": 10590 }, { "epoch": 0.48097374495913425, "grad_norm": 0.21416142582893372, "learning_rate": 7.574533303855491e-08, "loss": 0.0182, "step": 10600 }, { "epoch": 0.48142749377513344, "grad_norm": 0.21379952132701874, "learning_rate": 7.217725253801488e-08, "loss": 0.0188, "step": 10610 }, { "epoch": 0.48188124259113263, "grad_norm": 0.18420834839344025, "learning_rate": 6.869494700396328e-08, "loss": 0.0177, "step": 10620 }, { "epoch": 0.4823349914071318, "grad_norm": 0.19334009289741516, "learning_rate": 6.529844652301997e-08, "loss": 0.0175, "step": 10630 }, { "epoch": 0.482788740223131, "grad_norm": 0.21159031987190247, "learning_rate": 6.19877804404645e-08, "loss": 0.0153, "step": 10640 }, { "epoch": 0.48324248903913014, "grad_norm": 0.1979469507932663, "learning_rate": 5.876297735997738e-08, "loss": 0.0184, "step": 10650 }, { "epoch": 0.48369623785512933, "grad_norm": 0.18674810230731964, "learning_rate": 5.562406514339369e-08, "loss": 0.0179, "step": 10660 }, { "epoch": 0.4841499866711285, "grad_norm": 0.17443569004535675, "learning_rate": 5.257107091046654e-08, "loss": 0.0152, "step": 10670 }, { "epoch": 0.4846037354871277, "grad_norm": 0.20907823741436005, "learning_rate": 4.9604021038628384e-08, "loss": 0.0168, "step": 10680 }, { "epoch": 0.4850574843031269, "grad_norm": 0.22139771282672882, "learning_rate": 4.6722941162764546e-08, "loss": 0.0165, "step": 10690 }, { "epoch": 0.4855112331191261, "grad_norm": 0.31164970993995667, "learning_rate": 4.392785617499451e-08, "loss": 0.0166, "step": 10700 }, { "epoch": 0.4859649819351253, "grad_norm": 0.22600050270557404, "learning_rate": 4.1218790224450965e-08, "loss": 0.018, "step": 10710 }, { "epoch": 0.48641873075112446, "grad_norm": 0.1871599704027176, "learning_rate": 3.859576671707554e-08, "loss": 0.0146, "step": 10720 }, { "epoch": 0.48687247956712365, "grad_norm": 0.31369152665138245, "learning_rate": 3.605880831541564e-08, "loss": 0.02, "step": 10730 }, { "epoch": 0.48732622838312284, "grad_norm": 0.22444361448287964, "learning_rate": 3.36079369384279e-08, "loss": 0.019, "step": 10740 }, { "epoch": 0.487779977199122, "grad_norm": 0.19071801006793976, "learning_rate": 3.124317376129171e-08, "loss": 0.0138, "step": 10750 }, { "epoch": 0.48823372601512116, "grad_norm": 0.2862185835838318, "learning_rate": 2.8964539215220468e-08, "loss": 0.0163, "step": 10760 }, { "epoch": 0.48868747483112035, "grad_norm": 0.22695022821426392, "learning_rate": 2.6772052987290575e-08, "loss": 0.0172, "step": 10770 }, { "epoch": 0.48914122364711954, "grad_norm": 0.13512293994426727, "learning_rate": 2.4665734020270503e-08, "loss": 0.0155, "step": 10780 }, { "epoch": 0.4895949724631187, "grad_norm": 0.1680724173784256, "learning_rate": 2.2645600512452016e-08, "loss": 0.0171, "step": 10790 }, { "epoch": 0.4900487212791179, "grad_norm": 0.21303394436836243, "learning_rate": 2.0711669917501398e-08, "loss": 0.0137, "step": 10800 }, { "epoch": 0.4905024700951171, "grad_norm": 0.2663159668445587, "learning_rate": 1.8863958944300708e-08, "loss": 0.0171, "step": 10810 }, { "epoch": 0.4909562189111163, "grad_norm": 0.2092321366071701, "learning_rate": 1.710248355680788e-08, "loss": 0.0175, "step": 10820 }, { "epoch": 0.4914099677271155, "grad_norm": 0.17886793613433838, "learning_rate": 1.5427258973919058e-08, "loss": 0.0152, "step": 10830 }, { "epoch": 0.49186371654311467, "grad_norm": 0.27888569235801697, "learning_rate": 1.3838299669334255e-08, "loss": 0.0182, "step": 10840 }, { "epoch": 0.4923174653591138, "grad_norm": 0.20388205349445343, "learning_rate": 1.2335619371434126e-08, "loss": 0.0156, "step": 10850 }, { "epoch": 0.492771214175113, "grad_norm": 0.18075647950172424, "learning_rate": 1.0919231063161173e-08, "loss": 0.0192, "step": 10860 }, { "epoch": 0.4932249629911122, "grad_norm": 0.22544729709625244, "learning_rate": 9.589146981907604e-09, "loss": 0.016, "step": 10870 }, { "epoch": 0.49367871180711137, "grad_norm": 0.21136526763439178, "learning_rate": 8.345378619408762e-09, "loss": 0.0149, "step": 10880 }, { "epoch": 0.49413246062311056, "grad_norm": 0.22266151010990143, "learning_rate": 7.187936721646527e-09, "loss": 0.0185, "step": 10890 }, { "epoch": 0.49458620943910975, "grad_norm": 0.16044868528842926, "learning_rate": 6.116831288751624e-09, "loss": 0.0164, "step": 10900 }, { "epoch": 0.49503995825510894, "grad_norm": 0.1872600018978119, "learning_rate": 5.13207157492257e-09, "loss": 0.0188, "step": 10910 }, { "epoch": 0.4954937070711081, "grad_norm": 0.2220599204301834, "learning_rate": 4.233666088341304e-09, "loss": 0.0165, "step": 10920 }, { "epoch": 0.4959474558871073, "grad_norm": 0.22442923486232758, "learning_rate": 3.4216225911032354e-09, "loss": 0.0178, "step": 10930 }, { "epoch": 0.4964012047031065, "grad_norm": 0.22961091995239258, "learning_rate": 2.6959480991484157e-09, "loss": 0.0197, "step": 10940 }, { "epoch": 0.49685495351910564, "grad_norm": 0.23307688534259796, "learning_rate": 2.0566488821993635e-09, "loss": 0.0182, "step": 10950 }, { "epoch": 0.4973087023351048, "grad_norm": 0.2578476667404175, "learning_rate": 1.503730463709996e-09, "loss": 0.0153, "step": 10960 }, { "epoch": 0.497762451151104, "grad_norm": 0.27216029167175293, "learning_rate": 1.0371976208167766e-09, "loss": 0.0192, "step": 10970 }, { "epoch": 0.4982161999671032, "grad_norm": 0.2106863409280777, "learning_rate": 6.570543842965293e-10, "loss": 0.0183, "step": 10980 }, { "epoch": 0.4986699487831024, "grad_norm": 0.15630310773849487, "learning_rate": 3.6330403853201966e-10, "loss": 0.0148, "step": 10990 }, { "epoch": 0.4991236975991016, "grad_norm": 0.20467230677604675, "learning_rate": 1.5594912148420017e-10, "loss": 0.0198, "step": 11000 }, { "epoch": 0.49957744641510077, "grad_norm": 0.27265435457229614, "learning_rate": 3.49914246700056e-11, "loss": 0.0202, "step": 11010 }, { "epoch": 0.4999858203495, "step": 11019, "total_flos": 1.5507177612131697e+18, "train_loss": 0.026509896606377287, "train_runtime": 48214.3501, "train_samples_per_second": 1.828, "train_steps_per_second": 0.229 } ], "logging_steps": 10, "max_steps": 11019, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.5507177612131697e+18, "train_batch_size": 1, "trial_name": null, "trial_params": null }