{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 3219, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0, "loss_cot": 1.8923735618591309, "loss_nocot": 0.9232234954833984, "step": 0 }, { "epoch": 0.0009319664492078285, "grad_norm": 17.766110480241327, "learning_rate": 6.211180124223603e-08, "loss": 2.9684, "step": 1 }, { "epoch": 0.0009319664492078285, "loss_cot": 2.094414234161377, "loss_nocot": 0.9723501205444336, "step": 1 }, { "epoch": 0.001863932898415657, "grad_norm": 17.189556903794838, "learning_rate": 1.2422360248447206e-07, "loss": 2.9919, "step": 2 }, { "epoch": 0.001863932898415657, "loss_cot": 2.0499355792999268, "loss_nocot": 0.9470049738883972, "step": 2 }, { "epoch": 0.0027958993476234857, "grad_norm": 16.79892847982626, "learning_rate": 1.863354037267081e-07, "loss": 2.9401, "step": 3 }, { "epoch": 0.0027958993476234857, "loss_cot": 1.812759518623352, "loss_nocot": 0.878680944442749, "step": 3 }, { "epoch": 0.003727865796831314, "grad_norm": 17.32620870017432, "learning_rate": 2.484472049689441e-07, "loss": 2.7182, "step": 4 }, { "epoch": 0.003727865796831314, "loss_cot": 1.8777203559875488, "loss_nocot": 0.8610336184501648, "step": 4 }, { "epoch": 0.004659832246039142, "grad_norm": 17.02869296923448, "learning_rate": 3.1055900621118013e-07, "loss": 2.812, "step": 5 }, { "epoch": 0.004659832246039142, "loss_cot": 1.9700379371643066, "loss_nocot": 1.0224785804748535, "step": 5 }, { "epoch": 0.005591798695246971, "grad_norm": 16.529121982668702, "learning_rate": 3.726708074534162e-07, "loss": 2.931, "step": 6 }, { "epoch": 0.005591798695246971, "loss_cot": 1.8817923069000244, "loss_nocot": 0.9848132133483887, "step": 6 }, { "epoch": 0.0065237651444548, "grad_norm": 17.17535722792952, "learning_rate": 4.347826086956522e-07, "loss": 2.8304, "step": 7 }, { "epoch": 0.0065237651444548, "loss_cot": 2.031240701675415, "loss_nocot": 0.9649577736854553, "step": 7 }, { "epoch": 0.007455731593662628, "grad_norm": 16.956720620575986, "learning_rate": 4.968944099378882e-07, "loss": 2.8073, "step": 8 }, { "epoch": 0.007455731593662628, "loss_cot": 1.8645316362380981, "loss_nocot": 1.023597002029419, "step": 8 }, { "epoch": 0.008387698042870456, "grad_norm": 16.960269745382465, "learning_rate": 5.590062111801243e-07, "loss": 2.8056, "step": 9 }, { "epoch": 0.008387698042870456, "loss_cot": 1.931748867034912, "loss_nocot": 1.026395559310913, "step": 9 }, { "epoch": 0.009319664492078284, "grad_norm": 17.496966589218722, "learning_rate": 6.211180124223603e-07, "loss": 2.9599, "step": 10 }, { "epoch": 0.009319664492078284, "loss_cot": 1.911195158958435, "loss_nocot": 0.7970094084739685, "step": 10 }, { "epoch": 0.010251630941286114, "grad_norm": 16.593807397453084, "learning_rate": 6.832298136645964e-07, "loss": 2.6783, "step": 11 }, { "epoch": 0.010251630941286114, "loss_cot": 2.0346293449401855, "loss_nocot": 0.793146014213562, "step": 11 }, { "epoch": 0.011183597390493943, "grad_norm": 17.35391076692736, "learning_rate": 7.453416149068324e-07, "loss": 2.8279, "step": 12 }, { "epoch": 0.011183597390493943, "loss_cot": 2.028879165649414, "loss_nocot": 0.8466600179672241, "step": 12 }, { "epoch": 0.012115563839701771, "grad_norm": 17.23390956947459, "learning_rate": 8.074534161490684e-07, "loss": 2.7059, "step": 13 }, { "epoch": 0.012115563839701771, "loss_cot": 1.791969656944275, "loss_nocot": 1.1768141984939575, "step": 13 }, { "epoch": 0.0130475302889096, "grad_norm": 16.544586431709142, "learning_rate": 8.695652173913044e-07, "loss": 2.8976, "step": 14 }, { "epoch": 0.0130475302889096, "loss_cot": 1.884734869003296, "loss_nocot": 0.7962949275970459, "step": 14 }, { "epoch": 0.013979496738117428, "grad_norm": 16.842723666860877, "learning_rate": 9.316770186335404e-07, "loss": 2.759, "step": 15 }, { "epoch": 0.013979496738117428, "loss_cot": 1.841055154800415, "loss_nocot": 0.8323764801025391, "step": 15 }, { "epoch": 0.014911463187325256, "grad_norm": 16.480448198974315, "learning_rate": 9.937888198757765e-07, "loss": 2.8512, "step": 16 }, { "epoch": 0.014911463187325256, "loss_cot": 1.7955163717269897, "loss_nocot": 0.8649758696556091, "step": 16 }, { "epoch": 0.015843429636533086, "grad_norm": 16.519409002484117, "learning_rate": 1.0559006211180126e-06, "loss": 2.8316, "step": 17 }, { "epoch": 0.015843429636533086, "loss_cot": 1.922585129737854, "loss_nocot": 0.763505220413208, "step": 17 }, { "epoch": 0.016775396085740912, "grad_norm": 15.126418856316885, "learning_rate": 1.1180124223602485e-06, "loss": 2.6955, "step": 18 }, { "epoch": 0.016775396085740912, "loss_cot": 1.7979284524917603, "loss_nocot": 0.9408049583435059, "step": 18 }, { "epoch": 0.017707362534948742, "grad_norm": 15.020714364396767, "learning_rate": 1.1801242236024846e-06, "loss": 2.6856, "step": 19 }, { "epoch": 0.017707362534948742, "loss_cot": 1.9284067153930664, "loss_nocot": 0.857387125492096, "step": 19 }, { "epoch": 0.01863932898415657, "grad_norm": 15.187544190260933, "learning_rate": 1.2422360248447205e-06, "loss": 2.5523, "step": 20 }, { "epoch": 0.01863932898415657, "loss_cot": 1.8647878170013428, "loss_nocot": 0.6987367868423462, "step": 20 }, { "epoch": 0.0195712954333644, "grad_norm": 14.211068062571178, "learning_rate": 1.3043478260869566e-06, "loss": 2.6772, "step": 21 }, { "epoch": 0.0195712954333644, "loss_cot": 1.7113462686538696, "loss_nocot": 0.8705965876579285, "step": 21 }, { "epoch": 0.02050326188257223, "grad_norm": 14.65346115404784, "learning_rate": 1.3664596273291927e-06, "loss": 2.6044, "step": 22 }, { "epoch": 0.02050326188257223, "loss_cot": 1.8236255645751953, "loss_nocot": 0.9176993370056152, "step": 22 }, { "epoch": 0.021435228331780055, "grad_norm": 14.903959552419623, "learning_rate": 1.4285714285714286e-06, "loss": 2.7072, "step": 23 }, { "epoch": 0.021435228331780055, "loss_cot": 1.7039988040924072, "loss_nocot": 0.7293686866760254, "step": 23 }, { "epoch": 0.022367194780987885, "grad_norm": 11.818991909905444, "learning_rate": 1.4906832298136647e-06, "loss": 2.525, "step": 24 }, { "epoch": 0.022367194780987885, "loss_cot": 1.5034873485565186, "loss_nocot": 0.8427740335464478, "step": 24 }, { "epoch": 0.023299161230195712, "grad_norm": 11.049909547656902, "learning_rate": 1.5527950310559006e-06, "loss": 2.4864, "step": 25 }, { "epoch": 0.023299161230195712, "loss_cot": 1.533676028251648, "loss_nocot": 0.8939008712768555, "step": 25 }, { "epoch": 0.024231127679403542, "grad_norm": 11.226893014505741, "learning_rate": 1.6149068322981367e-06, "loss": 2.4681, "step": 26 }, { "epoch": 0.024231127679403542, "loss_cot": 1.585343360900879, "loss_nocot": 0.8981025218963623, "step": 26 }, { "epoch": 0.02516309412861137, "grad_norm": 10.241965889690277, "learning_rate": 1.6770186335403729e-06, "loss": 2.4679, "step": 27 }, { "epoch": 0.02516309412861137, "loss_cot": 1.581865906715393, "loss_nocot": 0.770372748374939, "step": 27 }, { "epoch": 0.0260950605778192, "grad_norm": 10.526261862476462, "learning_rate": 1.7391304347826088e-06, "loss": 2.3547, "step": 28 }, { "epoch": 0.0260950605778192, "loss_cot": 1.486628770828247, "loss_nocot": 1.1537609100341797, "step": 28 }, { "epoch": 0.02702702702702703, "grad_norm": 9.889560243947065, "learning_rate": 1.8012422360248449e-06, "loss": 2.4054, "step": 29 }, { "epoch": 0.02702702702702703, "loss_cot": 1.3758352994918823, "loss_nocot": 0.8928386569023132, "step": 29 }, { "epoch": 0.027958993476234855, "grad_norm": 9.464400205838686, "learning_rate": 1.8633540372670808e-06, "loss": 2.3108, "step": 30 }, { "epoch": 0.027958993476234855, "loss_cot": 1.4588910341262817, "loss_nocot": 0.9654240012168884, "step": 30 }, { "epoch": 0.028890959925442685, "grad_norm": 9.244531462277758, "learning_rate": 1.925465838509317e-06, "loss": 2.3298, "step": 31 }, { "epoch": 0.028890959925442685, "loss_cot": 1.3677054643630981, "loss_nocot": 0.9614218473434448, "step": 31 }, { "epoch": 0.02982292637465051, "grad_norm": 9.115528062159107, "learning_rate": 1.987577639751553e-06, "loss": 2.2952, "step": 32 }, { "epoch": 0.02982292637465051, "loss_cot": 1.3433549404144287, "loss_nocot": 0.9459013938903809, "step": 32 }, { "epoch": 0.03075489282385834, "grad_norm": 5.774295856984472, "learning_rate": 2.049689440993789e-06, "loss": 2.0262, "step": 33 }, { "epoch": 0.03075489282385834, "loss_cot": 1.1897070407867432, "loss_nocot": 0.8480222821235657, "step": 33 }, { "epoch": 0.03168685927306617, "grad_norm": 4.423169763698922, "learning_rate": 2.111801242236025e-06, "loss": 2.0111, "step": 34 }, { "epoch": 0.03168685927306617, "loss_cot": 1.154961347579956, "loss_nocot": 0.814033031463623, "step": 34 }, { "epoch": 0.032618825722273995, "grad_norm": 4.187269346054797, "learning_rate": 2.173913043478261e-06, "loss": 1.9795, "step": 35 }, { "epoch": 0.032618825722273995, "loss_cot": 1.124685525894165, "loss_nocot": 0.7273523807525635, "step": 35 }, { "epoch": 0.033550792171481825, "grad_norm": 4.1352776254142505, "learning_rate": 2.236024844720497e-06, "loss": 1.9799, "step": 36 }, { "epoch": 0.033550792171481825, "loss_cot": 1.1760149002075195, "loss_nocot": 0.961056113243103, "step": 36 }, { "epoch": 0.034482758620689655, "grad_norm": 3.9012159660089685, "learning_rate": 2.298136645962733e-06, "loss": 1.9535, "step": 37 }, { "epoch": 0.034482758620689655, "loss_cot": 1.1516003608703613, "loss_nocot": 0.8377864360809326, "step": 37 }, { "epoch": 0.035414725069897485, "grad_norm": 4.055938605783251, "learning_rate": 2.3602484472049692e-06, "loss": 2.0831, "step": 38 }, { "epoch": 0.035414725069897485, "loss_cot": 1.0935581922531128, "loss_nocot": 0.894018828868866, "step": 38 }, { "epoch": 0.036346691519105315, "grad_norm": 3.7603658079753473, "learning_rate": 2.422360248447205e-06, "loss": 2.0127, "step": 39 }, { "epoch": 0.036346691519105315, "loss_cot": 1.1338495016098022, "loss_nocot": 0.6907313466072083, "step": 39 }, { "epoch": 0.03727865796831314, "grad_norm": 3.5962392125360974, "learning_rate": 2.484472049689441e-06, "loss": 1.9368, "step": 40 }, { "epoch": 0.03727865796831314, "loss_cot": 1.1261610984802246, "loss_nocot": 0.6937215924263, "step": 40 }, { "epoch": 0.03821062441752097, "grad_norm": 3.4259300059663724, "learning_rate": 2.546583850931677e-06, "loss": 1.8155, "step": 41 }, { "epoch": 0.03821062441752097, "loss_cot": 1.1510069370269775, "loss_nocot": 0.8512140512466431, "step": 41 }, { "epoch": 0.0391425908667288, "grad_norm": 3.3187901479540423, "learning_rate": 2.6086956521739132e-06, "loss": 1.9828, "step": 42 }, { "epoch": 0.0391425908667288, "loss_cot": 1.1087310314178467, "loss_nocot": 0.6657044887542725, "step": 42 }, { "epoch": 0.04007455731593663, "grad_norm": 3.1511950854558965, "learning_rate": 2.670807453416149e-06, "loss": 1.9632, "step": 43 }, { "epoch": 0.04007455731593663, "loss_cot": 1.035422444343567, "loss_nocot": 0.5915104150772095, "step": 43 }, { "epoch": 0.04100652376514446, "grad_norm": 2.57550866930269, "learning_rate": 2.7329192546583855e-06, "loss": 1.7886, "step": 44 }, { "epoch": 0.04100652376514446, "loss_cot": 1.1038804054260254, "loss_nocot": 0.6105912327766418, "step": 44 }, { "epoch": 0.04193849021435228, "grad_norm": 2.320069402601851, "learning_rate": 2.795031055900621e-06, "loss": 1.7294, "step": 45 }, { "epoch": 0.04193849021435228, "loss_cot": 1.000008225440979, "loss_nocot": 0.710453987121582, "step": 45 }, { "epoch": 0.04287045666356011, "grad_norm": 2.149212613094728, "learning_rate": 2.8571428571428573e-06, "loss": 1.7527, "step": 46 }, { "epoch": 0.04287045666356011, "loss_cot": 1.0848525762557983, "loss_nocot": 0.6893993616104126, "step": 46 }, { "epoch": 0.04380242311276794, "grad_norm": 2.0250618148503223, "learning_rate": 2.919254658385093e-06, "loss": 1.7814, "step": 47 }, { "epoch": 0.04380242311276794, "loss_cot": 0.8912276029586792, "loss_nocot": 1.0268404483795166, "step": 47 }, { "epoch": 0.04473438956197577, "grad_norm": 1.8886037014652397, "learning_rate": 2.9813664596273295e-06, "loss": 1.7896, "step": 48 }, { "epoch": 0.04473438956197577, "loss_cot": 1.058471918106079, "loss_nocot": 0.6546507477760315, "step": 48 }, { "epoch": 0.045666356011183594, "grad_norm": 1.7742284372977297, "learning_rate": 3.043478260869566e-06, "loss": 1.6394, "step": 49 }, { "epoch": 0.045666356011183594, "loss_cot": 0.8765228986740112, "loss_nocot": 0.6640743017196655, "step": 49 }, { "epoch": 0.046598322460391424, "grad_norm": 1.5818406491923025, "learning_rate": 3.1055900621118013e-06, "loss": 1.5606, "step": 50 }, { "epoch": 0.046598322460391424, "loss_cot": 0.925304651260376, "loss_nocot": 0.7540417313575745, "step": 50 }, { "epoch": 0.047530288909599254, "grad_norm": 1.8685853489893995, "learning_rate": 3.1677018633540376e-06, "loss": 1.5791, "step": 51 }, { "epoch": 0.047530288909599254, "loss_cot": 0.9773271083831787, "loss_nocot": 0.6273480653762817, "step": 51 }, { "epoch": 0.048462255358807084, "grad_norm": 1.6172304933707513, "learning_rate": 3.2298136645962735e-06, "loss": 1.5898, "step": 52 }, { "epoch": 0.048462255358807084, "loss_cot": 0.9646862745285034, "loss_nocot": 0.6975805759429932, "step": 52 }, { "epoch": 0.049394221808014914, "grad_norm": 1.595734026436158, "learning_rate": 3.29192546583851e-06, "loss": 1.6078, "step": 53 }, { "epoch": 0.049394221808014914, "loss_cot": 0.9073131084442139, "loss_nocot": 0.7408664226531982, "step": 53 }, { "epoch": 0.05032618825722274, "grad_norm": 1.717526346510589, "learning_rate": 3.3540372670807457e-06, "loss": 1.652, "step": 54 }, { "epoch": 0.05032618825722274, "loss_cot": 0.9820903539657593, "loss_nocot": 0.5653016567230225, "step": 54 }, { "epoch": 0.05125815470643057, "grad_norm": 1.4470911688549024, "learning_rate": 3.4161490683229816e-06, "loss": 1.572, "step": 55 }, { "epoch": 0.05125815470643057, "loss_cot": 0.8367831707000732, "loss_nocot": 0.5934205055236816, "step": 55 }, { "epoch": 0.0521901211556384, "grad_norm": 1.4185604578944444, "learning_rate": 3.4782608695652175e-06, "loss": 1.5184, "step": 56 }, { "epoch": 0.0521901211556384, "loss_cot": 0.8655263185501099, "loss_nocot": 0.6296666860580444, "step": 56 }, { "epoch": 0.05312208760484623, "grad_norm": 1.2956913152652152, "learning_rate": 3.540372670807454e-06, "loss": 1.5138, "step": 57 }, { "epoch": 0.05312208760484623, "loss_cot": 0.9023932814598083, "loss_nocot": 0.7732945680618286, "step": 57 }, { "epoch": 0.05405405405405406, "grad_norm": 1.5626166047386476, "learning_rate": 3.6024844720496897e-06, "loss": 1.5925, "step": 58 }, { "epoch": 0.05405405405405406, "loss_cot": 0.8940421938896179, "loss_nocot": 0.5760956406593323, "step": 58 }, { "epoch": 0.05498602050326188, "grad_norm": 1.2178641052770423, "learning_rate": 3.664596273291926e-06, "loss": 1.4088, "step": 59 }, { "epoch": 0.05498602050326188, "loss_cot": 0.8904099464416504, "loss_nocot": 0.4708455204963684, "step": 59 }, { "epoch": 0.05591798695246971, "grad_norm": 1.0698890374874546, "learning_rate": 3.7267080745341615e-06, "loss": 1.3992, "step": 60 }, { "epoch": 0.05591798695246971, "loss_cot": 0.9405477046966553, "loss_nocot": 0.5347287654876709, "step": 60 }, { "epoch": 0.05684995340167754, "grad_norm": 1.470533349468584, "learning_rate": 3.788819875776398e-06, "loss": 1.5336, "step": 61 }, { "epoch": 0.05684995340167754, "loss_cot": 0.871566116809845, "loss_nocot": 0.7418372631072998, "step": 61 }, { "epoch": 0.05778191985088537, "grad_norm": 1.1543740596406016, "learning_rate": 3.850931677018634e-06, "loss": 1.4877, "step": 62 }, { "epoch": 0.05778191985088537, "loss_cot": 0.8075270652770996, "loss_nocot": 0.9012430906295776, "step": 62 }, { "epoch": 0.05871388630009319, "grad_norm": 1.5024195925060473, "learning_rate": 3.91304347826087e-06, "loss": 1.5621, "step": 63 }, { "epoch": 0.05871388630009319, "loss_cot": 0.8118829727172852, "loss_nocot": 0.7675687670707703, "step": 63 }, { "epoch": 0.05964585274930102, "grad_norm": 1.062176449083709, "learning_rate": 3.975155279503106e-06, "loss": 1.4328, "step": 64 }, { "epoch": 0.05964585274930102, "loss_cot": 0.8138152360916138, "loss_nocot": 0.6022648215293884, "step": 64 }, { "epoch": 0.06057781919850885, "grad_norm": 1.0064755422217961, "learning_rate": 4.037267080745342e-06, "loss": 1.3516, "step": 65 }, { "epoch": 0.06057781919850885, "loss_cot": 0.8747197389602661, "loss_nocot": 0.696572482585907, "step": 65 }, { "epoch": 0.06150978564771668, "grad_norm": 0.9846407018928477, "learning_rate": 4.099378881987578e-06, "loss": 1.4692, "step": 66 }, { "epoch": 0.06150978564771668, "loss_cot": 0.8451322317123413, "loss_nocot": 0.6860634088516235, "step": 66 }, { "epoch": 0.06244175209692451, "grad_norm": 1.1646277669777862, "learning_rate": 4.1614906832298145e-06, "loss": 1.4898, "step": 67 }, { "epoch": 0.06244175209692451, "loss_cot": 0.790704607963562, "loss_nocot": 0.47710442543029785, "step": 67 }, { "epoch": 0.06337371854613234, "grad_norm": 0.9410764184572923, "learning_rate": 4.22360248447205e-06, "loss": 1.3426, "step": 68 }, { "epoch": 0.06337371854613234, "loss_cot": 0.8143335580825806, "loss_nocot": 0.6503655910491943, "step": 68 }, { "epoch": 0.06430568499534017, "grad_norm": 1.0899173674785652, "learning_rate": 4.2857142857142855e-06, "loss": 1.3917, "step": 69 }, { "epoch": 0.06430568499534017, "loss_cot": 0.7874933481216431, "loss_nocot": 0.9205915927886963, "step": 69 }, { "epoch": 0.06523765144454799, "grad_norm": 0.9795455426769375, "learning_rate": 4.347826086956522e-06, "loss": 1.3789, "step": 70 }, { "epoch": 0.06523765144454799, "loss_cot": 0.8209361433982849, "loss_nocot": 0.6927160024642944, "step": 70 }, { "epoch": 0.06616961789375582, "grad_norm": 1.0304844281500862, "learning_rate": 4.409937888198758e-06, "loss": 1.4081, "step": 71 }, { "epoch": 0.06616961789375582, "loss_cot": 0.8055527806282043, "loss_nocot": 0.6140692830085754, "step": 71 }, { "epoch": 0.06710158434296365, "grad_norm": 1.0131489210254565, "learning_rate": 4.472049689440994e-06, "loss": 1.4902, "step": 72 }, { "epoch": 0.06710158434296365, "loss_cot": 0.8025979399681091, "loss_nocot": 0.44233715534210205, "step": 72 }, { "epoch": 0.06803355079217148, "grad_norm": 0.8593548631966087, "learning_rate": 4.534161490683231e-06, "loss": 1.2753, "step": 73 }, { "epoch": 0.06803355079217148, "loss_cot": 0.7028517723083496, "loss_nocot": 0.5892951488494873, "step": 73 }, { "epoch": 0.06896551724137931, "grad_norm": 1.0231836505649101, "learning_rate": 4.596273291925466e-06, "loss": 1.3868, "step": 74 }, { "epoch": 0.06896551724137931, "loss_cot": 0.7207517623901367, "loss_nocot": 0.5702530741691589, "step": 74 }, { "epoch": 0.06989748369058714, "grad_norm": 0.8876793088910062, "learning_rate": 4.6583850931677025e-06, "loss": 1.3505, "step": 75 }, { "epoch": 0.06989748369058714, "loss_cot": 0.8415015339851379, "loss_nocot": 0.5601282715797424, "step": 75 }, { "epoch": 0.07082945013979497, "grad_norm": 0.9077661878239123, "learning_rate": 4.7204968944099384e-06, "loss": 1.3616, "step": 76 }, { "epoch": 0.07082945013979497, "loss_cot": 0.8046107292175293, "loss_nocot": 0.584475576877594, "step": 76 }, { "epoch": 0.0717614165890028, "grad_norm": 0.8394949971700003, "learning_rate": 4.782608695652174e-06, "loss": 1.3192, "step": 77 }, { "epoch": 0.0717614165890028, "loss_cot": 0.7742605805397034, "loss_nocot": 0.47337400913238525, "step": 77 }, { "epoch": 0.07269338303821063, "grad_norm": 0.7879122983287538, "learning_rate": 4.84472049689441e-06, "loss": 1.2552, "step": 78 }, { "epoch": 0.07269338303821063, "loss_cot": 0.6853511333465576, "loss_nocot": 0.7166496515274048, "step": 78 }, { "epoch": 0.07362534948741846, "grad_norm": 0.8557166640981717, "learning_rate": 4.906832298136646e-06, "loss": 1.2915, "step": 79 }, { "epoch": 0.07362534948741846, "loss_cot": 0.8087495565414429, "loss_nocot": 0.6231666803359985, "step": 79 }, { "epoch": 0.07455731593662628, "grad_norm": 0.955009431589667, "learning_rate": 4.968944099378882e-06, "loss": 1.4114, "step": 80 }, { "epoch": 0.07455731593662628, "loss_cot": 0.7761220932006836, "loss_nocot": 0.5909121036529541, "step": 80 }, { "epoch": 0.0754892823858341, "grad_norm": 0.8569919957894364, "learning_rate": 5.031055900621118e-06, "loss": 1.3502, "step": 81 }, { "epoch": 0.0754892823858341, "loss_cot": 0.695780873298645, "loss_nocot": 0.48113948106765747, "step": 81 }, { "epoch": 0.07642124883504194, "grad_norm": 1.0218304651285108, "learning_rate": 5.093167701863354e-06, "loss": 1.3838, "step": 82 }, { "epoch": 0.07642124883504194, "loss_cot": 0.7828802466392517, "loss_nocot": 0.6773653030395508, "step": 82 }, { "epoch": 0.07735321528424977, "grad_norm": 0.8299992013525921, "learning_rate": 5.155279503105591e-06, "loss": 1.3482, "step": 83 }, { "epoch": 0.07735321528424977, "loss_cot": 0.8772420883178711, "loss_nocot": 0.5162135362625122, "step": 83 }, { "epoch": 0.0782851817334576, "grad_norm": 0.8309816089738064, "learning_rate": 5.2173913043478265e-06, "loss": 1.276, "step": 84 }, { "epoch": 0.0782851817334576, "loss_cot": 0.7418529391288757, "loss_nocot": 0.6080256700515747, "step": 84 }, { "epoch": 0.07921714818266543, "grad_norm": 0.8742391693177843, "learning_rate": 5.279503105590062e-06, "loss": 1.3122, "step": 85 }, { "epoch": 0.07921714818266543, "loss_cot": 0.7666840553283691, "loss_nocot": 0.6644238829612732, "step": 85 }, { "epoch": 0.08014911463187326, "grad_norm": 0.82796049913303, "learning_rate": 5.341614906832298e-06, "loss": 1.2991, "step": 86 }, { "epoch": 0.08014911463187326, "loss_cot": 0.7236154675483704, "loss_nocot": 0.7179359197616577, "step": 86 }, { "epoch": 0.08108108108108109, "grad_norm": 0.7864734080423235, "learning_rate": 5.403726708074535e-06, "loss": 1.2967, "step": 87 }, { "epoch": 0.08108108108108109, "loss_cot": 0.7455065250396729, "loss_nocot": 0.5599379539489746, "step": 87 }, { "epoch": 0.08201304753028892, "grad_norm": 0.7412923733552803, "learning_rate": 5.465838509316771e-06, "loss": 1.2919, "step": 88 }, { "epoch": 0.08201304753028892, "loss_cot": 0.8520106077194214, "loss_nocot": 0.439400851726532, "step": 88 }, { "epoch": 0.08294501397949673, "grad_norm": 1.0578695342011344, "learning_rate": 5.527950310559007e-06, "loss": 1.2964, "step": 89 }, { "epoch": 0.08294501397949673, "loss_cot": 0.6980115175247192, "loss_nocot": 0.6562376022338867, "step": 89 }, { "epoch": 0.08387698042870456, "grad_norm": 0.9142731808021427, "learning_rate": 5.590062111801242e-06, "loss": 1.3675, "step": 90 }, { "epoch": 0.08387698042870456, "loss_cot": 0.7467353343963623, "loss_nocot": 0.4776882529258728, "step": 90 }, { "epoch": 0.08480894687791239, "grad_norm": 0.7145179892286054, "learning_rate": 5.652173913043479e-06, "loss": 1.239, "step": 91 }, { "epoch": 0.08480894687791239, "loss_cot": 0.7173954248428345, "loss_nocot": 0.5157912373542786, "step": 91 }, { "epoch": 0.08574091332712022, "grad_norm": 0.8105808527546844, "learning_rate": 5.7142857142857145e-06, "loss": 1.2982, "step": 92 }, { "epoch": 0.08574091332712022, "loss_cot": 0.7216081619262695, "loss_nocot": 0.5497541427612305, "step": 92 }, { "epoch": 0.08667287977632805, "grad_norm": 0.8542745621516765, "learning_rate": 5.77639751552795e-06, "loss": 1.3318, "step": 93 }, { "epoch": 0.08667287977632805, "loss_cot": 0.7028072476387024, "loss_nocot": 0.5442987680435181, "step": 93 }, { "epoch": 0.08760484622553588, "grad_norm": 0.7233586576301895, "learning_rate": 5.838509316770186e-06, "loss": 1.2578, "step": 94 }, { "epoch": 0.08760484622553588, "loss_cot": 0.7196884751319885, "loss_nocot": 0.4986764192581177, "step": 94 }, { "epoch": 0.08853681267474371, "grad_norm": 0.8618394328419465, "learning_rate": 5.900621118012423e-06, "loss": 1.3372, "step": 95 }, { "epoch": 0.08853681267474371, "loss_cot": 0.6946591734886169, "loss_nocot": 0.6496953964233398, "step": 95 }, { "epoch": 0.08946877912395154, "grad_norm": 1.0972662484475388, "learning_rate": 5.962732919254659e-06, "loss": 1.3969, "step": 96 }, { "epoch": 0.08946877912395154, "loss_cot": 0.674106240272522, "loss_nocot": 0.5686264038085938, "step": 96 }, { "epoch": 0.09040074557315937, "grad_norm": 0.7572783897031419, "learning_rate": 6.024844720496895e-06, "loss": 1.1887, "step": 97 }, { "epoch": 0.09040074557315937, "loss_cot": 0.6983271241188049, "loss_nocot": 0.46746087074279785, "step": 97 }, { "epoch": 0.09133271202236719, "grad_norm": 0.8448205847230663, "learning_rate": 6.086956521739132e-06, "loss": 1.2278, "step": 98 }, { "epoch": 0.09133271202236719, "loss_cot": 0.7147111892700195, "loss_nocot": 0.6085753440856934, "step": 98 }, { "epoch": 0.09226467847157502, "grad_norm": 0.8411560876809681, "learning_rate": 6.1490683229813675e-06, "loss": 1.3129, "step": 99 }, { "epoch": 0.09226467847157502, "loss_cot": 0.6786739826202393, "loss_nocot": 0.39393937587738037, "step": 99 }, { "epoch": 0.09319664492078285, "grad_norm": 0.8003515075781824, "learning_rate": 6.2111801242236025e-06, "loss": 1.2764, "step": 100 }, { "epoch": 0.09319664492078285, "loss_cot": 0.6802921891212463, "loss_nocot": 0.348594605922699, "step": 100 }, { "epoch": 0.09412861136999068, "grad_norm": 0.8079525906977751, "learning_rate": 6.2732919254658384e-06, "loss": 1.1859, "step": 101 }, { "epoch": 0.09412861136999068, "loss_cot": 0.7103203535079956, "loss_nocot": 0.5124337077140808, "step": 101 }, { "epoch": 0.09506057781919851, "grad_norm": 0.7340788142394558, "learning_rate": 6.335403726708075e-06, "loss": 1.2021, "step": 102 }, { "epoch": 0.09506057781919851, "loss_cot": 0.705657958984375, "loss_nocot": 0.6228861212730408, "step": 102 }, { "epoch": 0.09599254426840634, "grad_norm": 0.7966547353340095, "learning_rate": 6.397515527950311e-06, "loss": 1.2703, "step": 103 }, { "epoch": 0.09599254426840634, "loss_cot": 0.7113581895828247, "loss_nocot": 0.44466161727905273, "step": 103 }, { "epoch": 0.09692451071761417, "grad_norm": 0.7069107627429247, "learning_rate": 6.459627329192547e-06, "loss": 1.1877, "step": 104 }, { "epoch": 0.09692451071761417, "loss_cot": 0.667229413986206, "loss_nocot": 0.7124866247177124, "step": 104 }, { "epoch": 0.097856477166822, "grad_norm": 0.8901257803747425, "learning_rate": 6.521739130434783e-06, "loss": 1.2982, "step": 105 }, { "epoch": 0.097856477166822, "loss_cot": 0.7073123455047607, "loss_nocot": 0.49963244795799255, "step": 105 }, { "epoch": 0.09878844361602983, "grad_norm": 0.6927986699604295, "learning_rate": 6.58385093167702e-06, "loss": 1.2028, "step": 106 }, { "epoch": 0.09878844361602983, "loss_cot": 0.6616072058677673, "loss_nocot": 0.5157642960548401, "step": 106 }, { "epoch": 0.09972041006523766, "grad_norm": 0.7378620082895342, "learning_rate": 6.6459627329192555e-06, "loss": 1.1975, "step": 107 }, { "epoch": 0.09972041006523766, "loss_cot": 0.7413234710693359, "loss_nocot": 0.7724511623382568, "step": 107 }, { "epoch": 0.10065237651444547, "grad_norm": 0.7915810211812045, "learning_rate": 6.7080745341614914e-06, "loss": 1.3864, "step": 108 }, { "epoch": 0.10065237651444547, "loss_cot": 0.6809225082397461, "loss_nocot": 0.4137725830078125, "step": 108 }, { "epoch": 0.1015843429636533, "grad_norm": 0.787307936913373, "learning_rate": 6.7701863354037265e-06, "loss": 1.2048, "step": 109 }, { "epoch": 0.1015843429636533, "loss_cot": 0.7567579746246338, "loss_nocot": 0.6275107264518738, "step": 109 }, { "epoch": 0.10251630941286113, "grad_norm": 0.776485035153563, "learning_rate": 6.832298136645963e-06, "loss": 1.2349, "step": 110 }, { "epoch": 0.10251630941286113, "loss_cot": 0.6956518888473511, "loss_nocot": 0.47011882066726685, "step": 110 }, { "epoch": 0.10344827586206896, "grad_norm": 0.7960739293164103, "learning_rate": 6.894409937888199e-06, "loss": 1.1728, "step": 111 }, { "epoch": 0.10344827586206896, "loss_cot": 0.7427248954772949, "loss_nocot": 0.4337083697319031, "step": 111 }, { "epoch": 0.1043802423112768, "grad_norm": 0.8094501870488209, "learning_rate": 6.956521739130435e-06, "loss": 1.2883, "step": 112 }, { "epoch": 0.1043802423112768, "loss_cot": 0.6588935852050781, "loss_nocot": 0.7686380743980408, "step": 112 }, { "epoch": 0.10531220876048462, "grad_norm": 0.8126486326475459, "learning_rate": 7.018633540372671e-06, "loss": 1.2969, "step": 113 }, { "epoch": 0.10531220876048462, "loss_cot": 0.6156876087188721, "loss_nocot": 0.6255949139595032, "step": 113 }, { "epoch": 0.10624417520969245, "grad_norm": 0.9198720071738504, "learning_rate": 7.080745341614908e-06, "loss": 1.2781, "step": 114 }, { "epoch": 0.10624417520969245, "loss_cot": 0.6247697472572327, "loss_nocot": 0.4535942077636719, "step": 114 }, { "epoch": 0.10717614165890028, "grad_norm": 0.7341909099190833, "learning_rate": 7.1428571428571436e-06, "loss": 1.2042, "step": 115 }, { "epoch": 0.10717614165890028, "loss_cot": 0.6843552589416504, "loss_nocot": 0.4675709903240204, "step": 115 }, { "epoch": 0.10810810810810811, "grad_norm": 0.6509562608998156, "learning_rate": 7.2049689440993795e-06, "loss": 1.101, "step": 116 }, { "epoch": 0.10810810810810811, "loss_cot": 0.6569675803184509, "loss_nocot": 0.5920939445495605, "step": 116 }, { "epoch": 0.10904007455731593, "grad_norm": 0.7917794449728763, "learning_rate": 7.267080745341616e-06, "loss": 1.2537, "step": 117 }, { "epoch": 0.10904007455731593, "loss_cot": 0.7379813194274902, "loss_nocot": 0.554854154586792, "step": 117 }, { "epoch": 0.10997204100652376, "grad_norm": 0.9823427806091617, "learning_rate": 7.329192546583852e-06, "loss": 1.2112, "step": 118 }, { "epoch": 0.10997204100652376, "loss_cot": 0.6848487854003906, "loss_nocot": 0.4412152171134949, "step": 118 }, { "epoch": 0.11090400745573159, "grad_norm": 0.7966576907638379, "learning_rate": 7.391304347826087e-06, "loss": 1.1938, "step": 119 }, { "epoch": 0.11090400745573159, "loss_cot": 0.6530359387397766, "loss_nocot": 0.5055398941040039, "step": 119 }, { "epoch": 0.11183597390493942, "grad_norm": 0.9222050001468828, "learning_rate": 7.453416149068323e-06, "loss": 1.1861, "step": 120 }, { "epoch": 0.11183597390493942, "loss_cot": 0.7570744156837463, "loss_nocot": 0.4967311918735504, "step": 120 }, { "epoch": 0.11276794035414725, "grad_norm": 0.6819968736992258, "learning_rate": 7.515527950310559e-06, "loss": 1.2347, "step": 121 }, { "epoch": 0.11276794035414725, "loss_cot": 0.7330630421638489, "loss_nocot": 0.5889959931373596, "step": 121 }, { "epoch": 0.11369990680335508, "grad_norm": 0.7436197263107096, "learning_rate": 7.577639751552796e-06, "loss": 1.2253, "step": 122 }, { "epoch": 0.11369990680335508, "loss_cot": 0.7037546038627625, "loss_nocot": 0.6157116889953613, "step": 122 }, { "epoch": 0.11463187325256291, "grad_norm": 0.7085470808813079, "learning_rate": 7.639751552795032e-06, "loss": 1.1726, "step": 123 }, { "epoch": 0.11463187325256291, "loss_cot": 0.6762243509292603, "loss_nocot": 0.39059174060821533, "step": 123 }, { "epoch": 0.11556383970177074, "grad_norm": 0.7914314218797052, "learning_rate": 7.701863354037268e-06, "loss": 1.3023, "step": 124 }, { "epoch": 0.11556383970177074, "loss_cot": 0.6055842638015747, "loss_nocot": 0.5583102107048035, "step": 124 }, { "epoch": 0.11649580615097857, "grad_norm": 0.6791830203800265, "learning_rate": 7.763975155279503e-06, "loss": 1.1233, "step": 125 }, { "epoch": 0.11649580615097857, "loss_cot": 0.6690504550933838, "loss_nocot": 0.43991321325302124, "step": 125 }, { "epoch": 0.11742777260018639, "grad_norm": 0.7064245346201267, "learning_rate": 7.82608695652174e-06, "loss": 1.1898, "step": 126 }, { "epoch": 0.11742777260018639, "loss_cot": 0.6995365619659424, "loss_nocot": 0.5073245763778687, "step": 126 }, { "epoch": 0.11835973904939422, "grad_norm": 0.820732883509141, "learning_rate": 7.888198757763977e-06, "loss": 1.3204, "step": 127 }, { "epoch": 0.11835973904939422, "loss_cot": 0.6820406317710876, "loss_nocot": 0.6715729236602783, "step": 127 }, { "epoch": 0.11929170549860205, "grad_norm": 0.7456939676266922, "learning_rate": 7.950310559006212e-06, "loss": 1.219, "step": 128 }, { "epoch": 0.11929170549860205, "loss_cot": 0.72175133228302, "loss_nocot": 0.846758246421814, "step": 128 }, { "epoch": 0.12022367194780988, "grad_norm": 0.7997449559445443, "learning_rate": 8.012422360248447e-06, "loss": 1.2543, "step": 129 }, { "epoch": 0.12022367194780988, "loss_cot": 0.7052532434463501, "loss_nocot": 0.4425358176231384, "step": 129 }, { "epoch": 0.1211556383970177, "grad_norm": 0.7004442378922866, "learning_rate": 8.074534161490684e-06, "loss": 1.1897, "step": 130 }, { "epoch": 0.1211556383970177, "loss_cot": 0.609025776386261, "loss_nocot": 0.5528712272644043, "step": 130 }, { "epoch": 0.12208760484622554, "grad_norm": 0.7589330429232631, "learning_rate": 8.13664596273292e-06, "loss": 1.138, "step": 131 }, { "epoch": 0.12208760484622554, "loss_cot": 0.6290774345397949, "loss_nocot": 0.485796183347702, "step": 131 }, { "epoch": 0.12301957129543337, "grad_norm": 0.7416589914702457, "learning_rate": 8.198757763975156e-06, "loss": 1.2066, "step": 132 }, { "epoch": 0.12301957129543337, "loss_cot": 0.6915582418441772, "loss_nocot": 0.4303431808948517, "step": 132 }, { "epoch": 0.1239515377446412, "grad_norm": 0.7060958409705418, "learning_rate": 8.260869565217392e-06, "loss": 1.1986, "step": 133 }, { "epoch": 0.1239515377446412, "loss_cot": 0.769749104976654, "loss_nocot": 0.4445653259754181, "step": 133 }, { "epoch": 0.12488350419384903, "grad_norm": 1.0062844764744372, "learning_rate": 8.322981366459629e-06, "loss": 1.2586, "step": 134 }, { "epoch": 0.12488350419384903, "loss_cot": 0.6342225074768066, "loss_nocot": 0.5797199010848999, "step": 134 }, { "epoch": 0.12581547064305684, "grad_norm": 0.728250107784773, "learning_rate": 8.385093167701864e-06, "loss": 1.1671, "step": 135 }, { "epoch": 0.12581547064305684, "loss_cot": 0.6359551548957825, "loss_nocot": 0.48858925700187683, "step": 135 }, { "epoch": 0.1267474370922647, "grad_norm": 0.8800785725006687, "learning_rate": 8.4472049689441e-06, "loss": 1.1654, "step": 136 }, { "epoch": 0.1267474370922647, "loss_cot": 0.595723032951355, "loss_nocot": 0.5527037382125854, "step": 136 }, { "epoch": 0.1276794035414725, "grad_norm": 1.486511577146298, "learning_rate": 8.509316770186336e-06, "loss": 1.1733, "step": 137 }, { "epoch": 0.1276794035414725, "loss_cot": 0.6665338277816772, "loss_nocot": 0.5737912654876709, "step": 137 }, { "epoch": 0.12861136999068035, "grad_norm": 0.7056160739119751, "learning_rate": 8.571428571428571e-06, "loss": 1.1908, "step": 138 }, { "epoch": 0.12861136999068035, "loss_cot": 0.6063699722290039, "loss_nocot": 0.8522747755050659, "step": 138 }, { "epoch": 0.12954333643988816, "grad_norm": 1.0466652181643716, "learning_rate": 8.633540372670808e-06, "loss": 1.262, "step": 139 }, { "epoch": 0.12954333643988816, "loss_cot": 0.6809717416763306, "loss_nocot": 0.459656298160553, "step": 139 }, { "epoch": 0.13047530288909598, "grad_norm": 0.6687434536209682, "learning_rate": 8.695652173913044e-06, "loss": 1.1293, "step": 140 }, { "epoch": 0.13047530288909598, "loss_cot": 0.7119914889335632, "loss_nocot": 0.4933791756629944, "step": 140 }, { "epoch": 0.13140726933830382, "grad_norm": 0.7182805012411619, "learning_rate": 8.75776397515528e-06, "loss": 1.2017, "step": 141 }, { "epoch": 0.13140726933830382, "loss_cot": 0.5982465744018555, "loss_nocot": 0.4673933684825897, "step": 141 }, { "epoch": 0.13233923578751164, "grad_norm": 0.7534320060592025, "learning_rate": 8.819875776397516e-06, "loss": 1.204, "step": 142 }, { "epoch": 0.13233923578751164, "loss_cot": 0.6360054612159729, "loss_nocot": 0.5380712747573853, "step": 142 }, { "epoch": 0.13327120223671948, "grad_norm": 0.7201497400079875, "learning_rate": 8.881987577639753e-06, "loss": 1.1695, "step": 143 }, { "epoch": 0.13327120223671948, "loss_cot": 0.6861408948898315, "loss_nocot": 0.5077911019325256, "step": 143 }, { "epoch": 0.1342031686859273, "grad_norm": 0.8461368253787814, "learning_rate": 8.944099378881988e-06, "loss": 1.2171, "step": 144 }, { "epoch": 0.1342031686859273, "loss_cot": 0.6749124526977539, "loss_nocot": 0.4492349922657013, "step": 144 }, { "epoch": 0.13513513513513514, "grad_norm": 0.6896203092870571, "learning_rate": 9.006211180124225e-06, "loss": 1.1759, "step": 145 }, { "epoch": 0.13513513513513514, "loss_cot": 0.6355440020561218, "loss_nocot": 0.5397538542747498, "step": 145 }, { "epoch": 0.13606710158434296, "grad_norm": 0.7485746416637489, "learning_rate": 9.068322981366461e-06, "loss": 1.1862, "step": 146 }, { "epoch": 0.13606710158434296, "loss_cot": 0.6767895221710205, "loss_nocot": 0.5801115036010742, "step": 146 }, { "epoch": 0.1369990680335508, "grad_norm": 0.7331008821288781, "learning_rate": 9.130434782608697e-06, "loss": 1.1843, "step": 147 }, { "epoch": 0.1369990680335508, "loss_cot": 0.6073203086853027, "loss_nocot": 0.4923625588417053, "step": 147 }, { "epoch": 0.13793103448275862, "grad_norm": 0.8045590939330816, "learning_rate": 9.192546583850932e-06, "loss": 1.1491, "step": 148 }, { "epoch": 0.13793103448275862, "loss_cot": 0.5994528532028198, "loss_nocot": 0.4526660740375519, "step": 148 }, { "epoch": 0.13886300093196646, "grad_norm": 0.8546201037426588, "learning_rate": 9.254658385093168e-06, "loss": 1.1634, "step": 149 }, { "epoch": 0.13886300093196646, "loss_cot": 0.6598418354988098, "loss_nocot": 0.5673488974571228, "step": 149 }, { "epoch": 0.13979496738117428, "grad_norm": 0.8219070820894792, "learning_rate": 9.316770186335405e-06, "loss": 1.1901, "step": 150 }, { "epoch": 0.13979496738117428, "loss_cot": 0.6959781646728516, "loss_nocot": 0.46376264095306396, "step": 150 }, { "epoch": 0.1407269338303821, "grad_norm": 0.7812174008656457, "learning_rate": 9.37888198757764e-06, "loss": 1.1862, "step": 151 }, { "epoch": 0.1407269338303821, "loss_cot": 0.6483443975448608, "loss_nocot": 0.5181110501289368, "step": 151 }, { "epoch": 0.14165890027958994, "grad_norm": 0.7226351132973383, "learning_rate": 9.440993788819877e-06, "loss": 1.2051, "step": 152 }, { "epoch": 0.14165890027958994, "loss_cot": 0.7131832242012024, "loss_nocot": 0.504234790802002, "step": 152 }, { "epoch": 0.14259086672879775, "grad_norm": 0.7253570204197838, "learning_rate": 9.503105590062112e-06, "loss": 1.1672, "step": 153 }, { "epoch": 0.14259086672879775, "loss_cot": 0.7300309538841248, "loss_nocot": 0.5464959144592285, "step": 153 }, { "epoch": 0.1435228331780056, "grad_norm": 0.7681124244760521, "learning_rate": 9.565217391304349e-06, "loss": 1.1829, "step": 154 }, { "epoch": 0.1435228331780056, "loss_cot": 0.7064125537872314, "loss_nocot": 0.44177520275115967, "step": 154 }, { "epoch": 0.14445479962721341, "grad_norm": 0.7375000705736291, "learning_rate": 9.627329192546585e-06, "loss": 1.1656, "step": 155 }, { "epoch": 0.14445479962721341, "loss_cot": 0.6620402336120605, "loss_nocot": 0.8133618235588074, "step": 155 }, { "epoch": 0.14538676607642126, "grad_norm": 0.7620868386118294, "learning_rate": 9.68944099378882e-06, "loss": 1.2447, "step": 156 }, { "epoch": 0.14538676607642126, "loss_cot": 0.5868980884552002, "loss_nocot": 0.4825012683868408, "step": 156 }, { "epoch": 0.14631873252562907, "grad_norm": 0.7391116834528904, "learning_rate": 9.751552795031056e-06, "loss": 1.167, "step": 157 }, { "epoch": 0.14631873252562907, "loss_cot": 0.6702220439910889, "loss_nocot": 0.47749608755111694, "step": 157 }, { "epoch": 0.14725069897483692, "grad_norm": 0.8330483328710497, "learning_rate": 9.813664596273292e-06, "loss": 1.2834, "step": 158 }, { "epoch": 0.14725069897483692, "loss_cot": 0.6233461499214172, "loss_nocot": 0.4588722586631775, "step": 158 }, { "epoch": 0.14818266542404473, "grad_norm": 0.8311863512094795, "learning_rate": 9.875776397515529e-06, "loss": 1.1878, "step": 159 }, { "epoch": 0.14818266542404473, "loss_cot": 0.6068678498268127, "loss_nocot": 0.48286908864974976, "step": 159 }, { "epoch": 0.14911463187325255, "grad_norm": 0.7753100831260723, "learning_rate": 9.937888198757764e-06, "loss": 1.1892, "step": 160 }, { "epoch": 0.14911463187325255, "loss_cot": 0.6242489814758301, "loss_nocot": 0.5376546382904053, "step": 160 }, { "epoch": 0.1500465983224604, "grad_norm": 0.7845618445237553, "learning_rate": 1e-05, "loss": 1.1206, "step": 161 }, { "epoch": 0.1500465983224604, "loss_cot": 0.6413248777389526, "loss_nocot": 0.41792699694633484, "step": 161 }, { "epoch": 0.1509785647716682, "grad_norm": 0.7634195540543002, "learning_rate": 1.0062111801242236e-05, "loss": 1.1555, "step": 162 }, { "epoch": 0.1509785647716682, "loss_cot": 0.6083952188491821, "loss_nocot": 0.6356023550033569, "step": 162 }, { "epoch": 0.15191053122087605, "grad_norm": 0.8028054448340856, "learning_rate": 1.0124223602484473e-05, "loss": 1.2466, "step": 163 }, { "epoch": 0.15191053122087605, "loss_cot": 0.7504128217697144, "loss_nocot": 0.5099287629127502, "step": 163 }, { "epoch": 0.15284249767008387, "grad_norm": 0.773127301218745, "learning_rate": 1.0186335403726708e-05, "loss": 1.2642, "step": 164 }, { "epoch": 0.15284249767008387, "loss_cot": 0.6528803110122681, "loss_nocot": 0.45601415634155273, "step": 164 }, { "epoch": 0.15377446411929171, "grad_norm": 1.0276121079572227, "learning_rate": 1.0248447204968946e-05, "loss": 1.1172, "step": 165 }, { "epoch": 0.15377446411929171, "loss_cot": 0.6329808235168457, "loss_nocot": 0.706676721572876, "step": 165 }, { "epoch": 0.15470643056849953, "grad_norm": 0.6876271179082105, "learning_rate": 1.0310559006211181e-05, "loss": 1.1696, "step": 166 }, { "epoch": 0.15470643056849953, "loss_cot": 0.635745644569397, "loss_nocot": 0.4300963282585144, "step": 166 }, { "epoch": 0.15563839701770738, "grad_norm": 0.678568730235985, "learning_rate": 1.0372670807453418e-05, "loss": 1.0766, "step": 167 }, { "epoch": 0.15563839701770738, "loss_cot": 0.6668745279312134, "loss_nocot": 0.5862067341804504, "step": 167 }, { "epoch": 0.1565703634669152, "grad_norm": 0.7167180529659654, "learning_rate": 1.0434782608695653e-05, "loss": 1.18, "step": 168 }, { "epoch": 0.1565703634669152, "loss_cot": 0.5677046179771423, "loss_nocot": 0.4630996882915497, "step": 168 }, { "epoch": 0.157502329916123, "grad_norm": 0.7266904193510457, "learning_rate": 1.049689440993789e-05, "loss": 1.1299, "step": 169 }, { "epoch": 0.157502329916123, "loss_cot": 0.6751296520233154, "loss_nocot": 0.5662996768951416, "step": 169 }, { "epoch": 0.15843429636533085, "grad_norm": 0.6988753704501938, "learning_rate": 1.0559006211180125e-05, "loss": 1.1166, "step": 170 }, { "epoch": 0.15843429636533085, "loss_cot": 0.615484356880188, "loss_nocot": 0.3776780962944031, "step": 170 }, { "epoch": 0.15936626281453867, "grad_norm": 0.7004286049212242, "learning_rate": 1.062111801242236e-05, "loss": 1.0934, "step": 171 }, { "epoch": 0.15936626281453867, "loss_cot": 0.6511818170547485, "loss_nocot": 0.48351407051086426, "step": 171 }, { "epoch": 0.1602982292637465, "grad_norm": 0.6576477804789855, "learning_rate": 1.0683229813664597e-05, "loss": 1.0857, "step": 172 }, { "epoch": 0.1602982292637465, "loss_cot": 0.6611406207084656, "loss_nocot": 0.48527956008911133, "step": 172 }, { "epoch": 0.16123019571295433, "grad_norm": 0.7968516853278346, "learning_rate": 1.0745341614906832e-05, "loss": 1.19, "step": 173 }, { "epoch": 0.16123019571295433, "loss_cot": 0.5997411608695984, "loss_nocot": 0.4223073124885559, "step": 173 }, { "epoch": 0.16216216216216217, "grad_norm": 0.6558371078722036, "learning_rate": 1.080745341614907e-05, "loss": 1.0856, "step": 174 }, { "epoch": 0.16216216216216217, "loss_cot": 0.6175566911697388, "loss_nocot": 0.49436256289482117, "step": 174 }, { "epoch": 0.16309412861137, "grad_norm": 0.7333325847225151, "learning_rate": 1.0869565217391305e-05, "loss": 1.0828, "step": 175 }, { "epoch": 0.16309412861137, "loss_cot": 0.6001670956611633, "loss_nocot": 0.3636420965194702, "step": 175 }, { "epoch": 0.16402609506057783, "grad_norm": 0.6945082696359051, "learning_rate": 1.0931677018633542e-05, "loss": 1.065, "step": 176 }, { "epoch": 0.16402609506057783, "loss_cot": 0.6457768678665161, "loss_nocot": 0.4882368743419647, "step": 176 }, { "epoch": 0.16495806150978565, "grad_norm": 0.8337756358918811, "learning_rate": 1.0993788819875777e-05, "loss": 1.1737, "step": 177 }, { "epoch": 0.16495806150978565, "loss_cot": 0.6655874252319336, "loss_nocot": 0.5367054343223572, "step": 177 }, { "epoch": 0.16589002795899346, "grad_norm": 0.6784985047515316, "learning_rate": 1.1055900621118014e-05, "loss": 1.0962, "step": 178 }, { "epoch": 0.16589002795899346, "loss_cot": 0.6782284379005432, "loss_nocot": 0.6644495725631714, "step": 178 }, { "epoch": 0.1668219944082013, "grad_norm": 0.7492637536173585, "learning_rate": 1.1118012422360249e-05, "loss": 1.1906, "step": 179 }, { "epoch": 0.1668219944082013, "loss_cot": 0.6292970180511475, "loss_nocot": 0.4012303948402405, "step": 179 }, { "epoch": 0.16775396085740912, "grad_norm": 0.6829001732632162, "learning_rate": 1.1180124223602484e-05, "loss": 1.0854, "step": 180 }, { "epoch": 0.16775396085740912, "loss_cot": 0.6043727397918701, "loss_nocot": 0.42222341895103455, "step": 180 }, { "epoch": 0.16868592730661697, "grad_norm": 0.8120226566075693, "learning_rate": 1.1242236024844722e-05, "loss": 1.1316, "step": 181 }, { "epoch": 0.16868592730661697, "loss_cot": 0.6094085574150085, "loss_nocot": 0.44284743070602417, "step": 181 }, { "epoch": 0.16961789375582478, "grad_norm": 0.6851483823883485, "learning_rate": 1.1304347826086957e-05, "loss": 1.1366, "step": 182 }, { "epoch": 0.16961789375582478, "loss_cot": 0.6082867980003357, "loss_nocot": 0.4980284869670868, "step": 182 }, { "epoch": 0.17054986020503263, "grad_norm": 0.6619484255663358, "learning_rate": 1.1366459627329194e-05, "loss": 1.0556, "step": 183 }, { "epoch": 0.17054986020503263, "loss_cot": 0.6691023707389832, "loss_nocot": 0.6555956602096558, "step": 183 }, { "epoch": 0.17148182665424044, "grad_norm": 0.7063779073161183, "learning_rate": 1.1428571428571429e-05, "loss": 1.1416, "step": 184 }, { "epoch": 0.17148182665424044, "loss_cot": 0.6047367453575134, "loss_nocot": 0.4952542185783386, "step": 184 }, { "epoch": 0.1724137931034483, "grad_norm": 0.7032567210411254, "learning_rate": 1.1490683229813666e-05, "loss": 1.1159, "step": 185 }, { "epoch": 0.1724137931034483, "loss_cot": 0.6321551203727722, "loss_nocot": 0.3992549777030945, "step": 185 }, { "epoch": 0.1733457595526561, "grad_norm": 0.6132161797222421, "learning_rate": 1.15527950310559e-05, "loss": 1.0493, "step": 186 }, { "epoch": 0.1733457595526561, "loss_cot": 0.6117006540298462, "loss_nocot": 0.5215492844581604, "step": 186 }, { "epoch": 0.17427772600186392, "grad_norm": 0.7597666934898023, "learning_rate": 1.161490683229814e-05, "loss": 1.1546, "step": 187 }, { "epoch": 0.17427772600186392, "loss_cot": 0.5272868871688843, "loss_nocot": 0.6146036982536316, "step": 187 }, { "epoch": 0.17520969245107176, "grad_norm": 0.6754899778478513, "learning_rate": 1.1677018633540373e-05, "loss": 1.1164, "step": 188 }, { "epoch": 0.17520969245107176, "loss_cot": 0.7537875175476074, "loss_nocot": 0.41248998045921326, "step": 188 }, { "epoch": 0.17614165890027958, "grad_norm": 0.6403160925480412, "learning_rate": 1.1739130434782611e-05, "loss": 1.1219, "step": 189 }, { "epoch": 0.17614165890027958, "loss_cot": 0.6079091429710388, "loss_nocot": 0.564183235168457, "step": 189 }, { "epoch": 0.17707362534948742, "grad_norm": 0.7342604603041808, "learning_rate": 1.1801242236024846e-05, "loss": 1.1885, "step": 190 }, { "epoch": 0.17707362534948742, "loss_cot": 0.6364481449127197, "loss_nocot": 0.5179814100265503, "step": 190 }, { "epoch": 0.17800559179869524, "grad_norm": 0.8853216252541759, "learning_rate": 1.1863354037267081e-05, "loss": 1.2214, "step": 191 }, { "epoch": 0.17800559179869524, "loss_cot": 0.6115385293960571, "loss_nocot": 0.3938530683517456, "step": 191 }, { "epoch": 0.17893755824790308, "grad_norm": 0.7135578276103738, "learning_rate": 1.1925465838509318e-05, "loss": 1.1519, "step": 192 }, { "epoch": 0.17893755824790308, "loss_cot": 0.620561957359314, "loss_nocot": 0.6947695016860962, "step": 192 }, { "epoch": 0.1798695246971109, "grad_norm": 0.7532797006204407, "learning_rate": 1.1987577639751553e-05, "loss": 1.2489, "step": 193 }, { "epoch": 0.1798695246971109, "loss_cot": 0.6239883899688721, "loss_nocot": 0.5807971954345703, "step": 193 }, { "epoch": 0.18080149114631874, "grad_norm": 0.7080975040874616, "learning_rate": 1.204968944099379e-05, "loss": 1.1543, "step": 194 }, { "epoch": 0.18080149114631874, "loss_cot": 0.6174724698066711, "loss_nocot": 0.5826753377914429, "step": 194 }, { "epoch": 0.18173345759552656, "grad_norm": 0.7792451809045462, "learning_rate": 1.2111801242236025e-05, "loss": 1.1944, "step": 195 }, { "epoch": 0.18173345759552656, "loss_cot": 0.6106735467910767, "loss_nocot": 0.6087216734886169, "step": 195 }, { "epoch": 0.18266542404473438, "grad_norm": 0.677198781411723, "learning_rate": 1.2173913043478263e-05, "loss": 1.1521, "step": 196 }, { "epoch": 0.18266542404473438, "loss_cot": 0.6138521432876587, "loss_nocot": 0.6388240456581116, "step": 196 }, { "epoch": 0.18359739049394222, "grad_norm": 0.7308227116511128, "learning_rate": 1.2236024844720498e-05, "loss": 1.1345, "step": 197 }, { "epoch": 0.18359739049394222, "loss_cot": 0.6388584971427917, "loss_nocot": 0.4755370616912842, "step": 197 }, { "epoch": 0.18452935694315004, "grad_norm": 0.6645507368023452, "learning_rate": 1.2298136645962735e-05, "loss": 1.0419, "step": 198 }, { "epoch": 0.18452935694315004, "loss_cot": 0.6924009919166565, "loss_nocot": 0.42748749256134033, "step": 198 }, { "epoch": 0.18546132339235788, "grad_norm": 0.6668701823717593, "learning_rate": 1.236024844720497e-05, "loss": 1.1461, "step": 199 }, { "epoch": 0.18546132339235788, "loss_cot": 0.5490299463272095, "loss_nocot": 0.4415239989757538, "step": 199 }, { "epoch": 0.1863932898415657, "grad_norm": 0.6732319516001545, "learning_rate": 1.2422360248447205e-05, "loss": 1.0227, "step": 200 }, { "epoch": 0.1863932898415657, "loss_cot": 0.6246012449264526, "loss_nocot": 0.554567277431488, "step": 200 }, { "epoch": 0.18732525629077354, "grad_norm": 0.8054985085347, "learning_rate": 1.2484472049689442e-05, "loss": 1.1272, "step": 201 }, { "epoch": 0.18732525629077354, "loss_cot": 0.6161444187164307, "loss_nocot": 0.611241340637207, "step": 201 }, { "epoch": 0.18825722273998136, "grad_norm": 0.6462471554066688, "learning_rate": 1.2546583850931677e-05, "loss": 1.0682, "step": 202 }, { "epoch": 0.18825722273998136, "loss_cot": 0.5816634893417358, "loss_nocot": 0.4227678179740906, "step": 202 }, { "epoch": 0.1891891891891892, "grad_norm": 0.6856780399098062, "learning_rate": 1.2608695652173915e-05, "loss": 1.0914, "step": 203 }, { "epoch": 0.1891891891891892, "loss_cot": 0.6495304107666016, "loss_nocot": 0.9938982725143433, "step": 203 }, { "epoch": 0.19012115563839702, "grad_norm": 0.7821602470969502, "learning_rate": 1.267080745341615e-05, "loss": 1.2929, "step": 204 }, { "epoch": 0.19012115563839702, "loss_cot": 0.6140915155410767, "loss_nocot": 0.5134720206260681, "step": 204 }, { "epoch": 0.19105312208760486, "grad_norm": 0.6918298644779325, "learning_rate": 1.2732919254658387e-05, "loss": 1.1225, "step": 205 }, { "epoch": 0.19105312208760486, "loss_cot": 0.7013094425201416, "loss_nocot": 0.6423965096473694, "step": 205 }, { "epoch": 0.19198508853681268, "grad_norm": 0.7801008628485326, "learning_rate": 1.2795031055900622e-05, "loss": 1.2296, "step": 206 }, { "epoch": 0.19198508853681268, "loss_cot": 0.6461310386657715, "loss_nocot": 0.49154168367385864, "step": 206 }, { "epoch": 0.1929170549860205, "grad_norm": 1.2635154245306872, "learning_rate": 1.2857142857142859e-05, "loss": 1.1255, "step": 207 }, { "epoch": 0.1929170549860205, "loss_cot": 0.6130734086036682, "loss_nocot": 0.443855881690979, "step": 207 }, { "epoch": 0.19384902143522834, "grad_norm": 0.6879886963887082, "learning_rate": 1.2919254658385094e-05, "loss": 1.122, "step": 208 }, { "epoch": 0.19384902143522834, "loss_cot": 0.6057791113853455, "loss_nocot": 0.4603012800216675, "step": 208 }, { "epoch": 0.19478098788443615, "grad_norm": 0.6765017914174447, "learning_rate": 1.2981366459627329e-05, "loss": 1.0868, "step": 209 }, { "epoch": 0.19478098788443615, "loss_cot": 0.6640405654907227, "loss_nocot": 0.6220258474349976, "step": 209 }, { "epoch": 0.195712954333644, "grad_norm": 0.6903324154803742, "learning_rate": 1.3043478260869566e-05, "loss": 1.1105, "step": 210 }, { "epoch": 0.195712954333644, "loss_cot": 0.6726062297821045, "loss_nocot": 0.5585152506828308, "step": 210 }, { "epoch": 0.1966449207828518, "grad_norm": 0.7265707470661816, "learning_rate": 1.31055900621118e-05, "loss": 1.1866, "step": 211 }, { "epoch": 0.1966449207828518, "loss_cot": 0.6208266019821167, "loss_nocot": 0.5822149515151978, "step": 211 }, { "epoch": 0.19757688723205966, "grad_norm": 0.7014384780461377, "learning_rate": 1.316770186335404e-05, "loss": 1.1061, "step": 212 }, { "epoch": 0.19757688723205966, "loss_cot": 0.6332534551620483, "loss_nocot": 0.6620657444000244, "step": 212 }, { "epoch": 0.19850885368126747, "grad_norm": 0.8686470295654657, "learning_rate": 1.3229813664596274e-05, "loss": 1.2712, "step": 213 }, { "epoch": 0.19850885368126747, "loss_cot": 0.6319789886474609, "loss_nocot": 0.5281420350074768, "step": 213 }, { "epoch": 0.19944082013047532, "grad_norm": 0.7088845563133558, "learning_rate": 1.3291925465838511e-05, "loss": 1.1138, "step": 214 }, { "epoch": 0.19944082013047532, "loss_cot": 0.6151564121246338, "loss_nocot": 0.45228031277656555, "step": 214 }, { "epoch": 0.20037278657968313, "grad_norm": 0.7440889609973891, "learning_rate": 1.3354037267080746e-05, "loss": 1.0721, "step": 215 }, { "epoch": 0.20037278657968313, "loss_cot": 0.6518409252166748, "loss_nocot": 0.3980031907558441, "step": 215 }, { "epoch": 0.20130475302889095, "grad_norm": 1.4607029178300823, "learning_rate": 1.3416149068322983e-05, "loss": 1.0349, "step": 216 }, { "epoch": 0.20130475302889095, "loss_cot": 0.6059936285018921, "loss_nocot": 0.48796704411506653, "step": 216 }, { "epoch": 0.2022367194780988, "grad_norm": 0.7612678864125353, "learning_rate": 1.3478260869565218e-05, "loss": 1.0656, "step": 217 }, { "epoch": 0.2022367194780988, "loss_cot": 0.6511025428771973, "loss_nocot": 0.5447966456413269, "step": 217 }, { "epoch": 0.2031686859273066, "grad_norm": 0.6231852272051511, "learning_rate": 1.3540372670807453e-05, "loss": 1.0798, "step": 218 }, { "epoch": 0.2031686859273066, "loss_cot": 0.6346331834793091, "loss_nocot": 0.4554853141307831, "step": 218 }, { "epoch": 0.20410065237651445, "grad_norm": 0.722273828213536, "learning_rate": 1.3602484472049691e-05, "loss": 1.1161, "step": 219 }, { "epoch": 0.20410065237651445, "loss_cot": 0.5722639560699463, "loss_nocot": 0.48593032360076904, "step": 219 }, { "epoch": 0.20503261882572227, "grad_norm": 0.742059436721159, "learning_rate": 1.3664596273291926e-05, "loss": 1.153, "step": 220 }, { "epoch": 0.20503261882572227, "loss_cot": 0.5771195888519287, "loss_nocot": 0.3729369044303894, "step": 220 }, { "epoch": 0.2059645852749301, "grad_norm": 0.6732920700406393, "learning_rate": 1.3726708074534163e-05, "loss": 1.0988, "step": 221 }, { "epoch": 0.2059645852749301, "loss_cot": 0.6231944561004639, "loss_nocot": 0.5922213792800903, "step": 221 }, { "epoch": 0.20689655172413793, "grad_norm": 0.7521535236860519, "learning_rate": 1.3788819875776398e-05, "loss": 1.1134, "step": 222 }, { "epoch": 0.20689655172413793, "loss_cot": 0.6315449476242065, "loss_nocot": 0.4583328366279602, "step": 222 }, { "epoch": 0.20782851817334577, "grad_norm": 0.6835556626310475, "learning_rate": 1.3850931677018635e-05, "loss": 1.098, "step": 223 }, { "epoch": 0.20782851817334577, "loss_cot": 0.6172322630882263, "loss_nocot": 0.4465647041797638, "step": 223 }, { "epoch": 0.2087604846225536, "grad_norm": 0.7093714271163222, "learning_rate": 1.391304347826087e-05, "loss": 1.0751, "step": 224 }, { "epoch": 0.2087604846225536, "loss_cot": 0.6214926242828369, "loss_nocot": 0.43479570746421814, "step": 224 }, { "epoch": 0.2096924510717614, "grad_norm": 0.700148652101937, "learning_rate": 1.3975155279503107e-05, "loss": 1.116, "step": 225 }, { "epoch": 0.2096924510717614, "loss_cot": 0.5380982160568237, "loss_nocot": 0.6982182264328003, "step": 225 }, { "epoch": 0.21062441752096925, "grad_norm": 0.6691119704778269, "learning_rate": 1.4037267080745342e-05, "loss": 1.0817, "step": 226 }, { "epoch": 0.21062441752096925, "loss_cot": 0.6301432847976685, "loss_nocot": 0.5876816511154175, "step": 226 }, { "epoch": 0.21155638397017706, "grad_norm": 0.772135200203018, "learning_rate": 1.409937888198758e-05, "loss": 1.1571, "step": 227 }, { "epoch": 0.21155638397017706, "loss_cot": 0.6219503879547119, "loss_nocot": 0.5031936168670654, "step": 227 }, { "epoch": 0.2124883504193849, "grad_norm": 0.8163936751074752, "learning_rate": 1.4161490683229815e-05, "loss": 1.1516, "step": 228 }, { "epoch": 0.2124883504193849, "loss_cot": 0.6463695168495178, "loss_nocot": 0.41586530208587646, "step": 228 }, { "epoch": 0.21342031686859272, "grad_norm": 0.65963288183252, "learning_rate": 1.422360248447205e-05, "loss": 1.1023, "step": 229 }, { "epoch": 0.21342031686859272, "loss_cot": 0.6218523979187012, "loss_nocot": 0.39927953481674194, "step": 229 }, { "epoch": 0.21435228331780057, "grad_norm": 0.7180205619091273, "learning_rate": 1.4285714285714287e-05, "loss": 1.0905, "step": 230 }, { "epoch": 0.21435228331780057, "loss_cot": 0.584065318107605, "loss_nocot": 0.438500314950943, "step": 230 }, { "epoch": 0.21528424976700838, "grad_norm": 0.6088566803056461, "learning_rate": 1.4347826086956522e-05, "loss": 1.0435, "step": 231 }, { "epoch": 0.21528424976700838, "loss_cot": 0.6238535642623901, "loss_nocot": 0.41387635469436646, "step": 231 }, { "epoch": 0.21621621621621623, "grad_norm": 0.6905763671178666, "learning_rate": 1.4409937888198759e-05, "loss": 1.079, "step": 232 }, { "epoch": 0.21621621621621623, "loss_cot": 0.7285051345825195, "loss_nocot": 0.4625026285648346, "step": 232 }, { "epoch": 0.21714818266542404, "grad_norm": 0.8542980564426194, "learning_rate": 1.4472049689440994e-05, "loss": 1.1753, "step": 233 }, { "epoch": 0.21714818266542404, "loss_cot": 0.5811556577682495, "loss_nocot": 0.5300537347793579, "step": 233 }, { "epoch": 0.21808014911463186, "grad_norm": 0.6298695877637693, "learning_rate": 1.4534161490683232e-05, "loss": 1.0724, "step": 234 }, { "epoch": 0.21808014911463186, "loss_cot": 0.5971666574478149, "loss_nocot": 0.5264700651168823, "step": 234 }, { "epoch": 0.2190121155638397, "grad_norm": 0.7099723172346497, "learning_rate": 1.4596273291925467e-05, "loss": 1.0576, "step": 235 }, { "epoch": 0.2190121155638397, "loss_cot": 0.603142499923706, "loss_nocot": 0.4184395968914032, "step": 235 }, { "epoch": 0.21994408201304752, "grad_norm": 0.7190467913103317, "learning_rate": 1.4658385093167704e-05, "loss": 1.1558, "step": 236 }, { "epoch": 0.21994408201304752, "loss_cot": 0.6168382167816162, "loss_nocot": 0.4949399530887604, "step": 236 }, { "epoch": 0.22087604846225536, "grad_norm": 0.6961000503195647, "learning_rate": 1.472049689440994e-05, "loss": 1.1312, "step": 237 }, { "epoch": 0.22087604846225536, "loss_cot": 0.6076015830039978, "loss_nocot": 0.4647408425807953, "step": 237 }, { "epoch": 0.22180801491146318, "grad_norm": 0.6609073082587592, "learning_rate": 1.4782608695652174e-05, "loss": 1.0873, "step": 238 }, { "epoch": 0.22180801491146318, "loss_cot": 0.569318950176239, "loss_nocot": 0.867267906665802, "step": 238 }, { "epoch": 0.22273998136067102, "grad_norm": 0.7875300126210655, "learning_rate": 1.4844720496894411e-05, "loss": 1.1947, "step": 239 }, { "epoch": 0.22273998136067102, "loss_cot": 0.6194082498550415, "loss_nocot": 0.5835227966308594, "step": 239 }, { "epoch": 0.22367194780987884, "grad_norm": 0.8272604893258474, "learning_rate": 1.4906832298136646e-05, "loss": 1.1154, "step": 240 }, { "epoch": 0.22367194780987884, "loss_cot": 0.5737695693969727, "loss_nocot": 0.4508478045463562, "step": 240 }, { "epoch": 0.22460391425908668, "grad_norm": 0.8146789169424118, "learning_rate": 1.4968944099378885e-05, "loss": 1.1203, "step": 241 }, { "epoch": 0.22460391425908668, "loss_cot": 0.6000455021858215, "loss_nocot": 0.4568960964679718, "step": 241 }, { "epoch": 0.2255358807082945, "grad_norm": 0.6872295664388238, "learning_rate": 1.5031055900621118e-05, "loss": 1.0851, "step": 242 }, { "epoch": 0.2255358807082945, "loss_cot": 0.7123602628707886, "loss_nocot": 0.4142554700374603, "step": 242 }, { "epoch": 0.22646784715750232, "grad_norm": 0.7960617893768465, "learning_rate": 1.5093167701863356e-05, "loss": 1.1359, "step": 243 }, { "epoch": 0.22646784715750232, "loss_cot": 0.592166543006897, "loss_nocot": 0.6494652032852173, "step": 243 }, { "epoch": 0.22739981360671016, "grad_norm": 0.8110042536771588, "learning_rate": 1.5155279503105591e-05, "loss": 1.1343, "step": 244 }, { "epoch": 0.22739981360671016, "loss_cot": 0.601658821105957, "loss_nocot": 0.48911231756210327, "step": 244 }, { "epoch": 0.22833178005591798, "grad_norm": 0.8471385128704498, "learning_rate": 1.5217391304347828e-05, "loss": 1.1138, "step": 245 }, { "epoch": 0.22833178005591798, "loss_cot": 0.5470917224884033, "loss_nocot": 0.39978712797164917, "step": 245 }, { "epoch": 0.22926374650512582, "grad_norm": 0.743755677080498, "learning_rate": 1.5279503105590063e-05, "loss": 1.0571, "step": 246 }, { "epoch": 0.22926374650512582, "loss_cot": 0.4881841540336609, "loss_nocot": 0.46996086835861206, "step": 246 }, { "epoch": 0.23019571295433364, "grad_norm": 0.6470485265541336, "learning_rate": 1.5341614906832298e-05, "loss": 1.0344, "step": 247 }, { "epoch": 0.23019571295433364, "loss_cot": 0.606418788433075, "loss_nocot": 0.7681374549865723, "step": 247 }, { "epoch": 0.23112767940354148, "grad_norm": 0.7614665141495375, "learning_rate": 1.5403726708074537e-05, "loss": 1.195, "step": 248 }, { "epoch": 0.23112767940354148, "loss_cot": 0.5724070072174072, "loss_nocot": 0.4332415461540222, "step": 248 }, { "epoch": 0.2320596458527493, "grad_norm": 0.6158395465726255, "learning_rate": 1.5465838509316772e-05, "loss": 1.0454, "step": 249 }, { "epoch": 0.2320596458527493, "loss_cot": 0.598156213760376, "loss_nocot": 0.43189215660095215, "step": 249 }, { "epoch": 0.23299161230195714, "grad_norm": 0.7595365669202322, "learning_rate": 1.5527950310559007e-05, "loss": 1.0824, "step": 250 }, { "epoch": 0.23299161230195714, "loss_cot": 0.6798398494720459, "loss_nocot": 0.414772629737854, "step": 250 }, { "epoch": 0.23392357875116496, "grad_norm": 0.6956567043297965, "learning_rate": 1.5590062111801242e-05, "loss": 1.1336, "step": 251 }, { "epoch": 0.23392357875116496, "loss_cot": 0.6146822571754456, "loss_nocot": 0.44349732995033264, "step": 251 }, { "epoch": 0.23485554520037277, "grad_norm": 0.8644061660230243, "learning_rate": 1.565217391304348e-05, "loss": 1.1119, "step": 252 }, { "epoch": 0.23485554520037277, "loss_cot": 0.5694839954376221, "loss_nocot": 0.4773327112197876, "step": 252 }, { "epoch": 0.23578751164958062, "grad_norm": 0.7601339831559506, "learning_rate": 1.5714285714285715e-05, "loss": 1.1227, "step": 253 }, { "epoch": 0.23578751164958062, "loss_cot": 0.6104736924171448, "loss_nocot": 0.4289238750934601, "step": 253 }, { "epoch": 0.23671947809878843, "grad_norm": 0.9696119583232002, "learning_rate": 1.5776397515527954e-05, "loss": 1.1389, "step": 254 }, { "epoch": 0.23671947809878843, "loss_cot": 0.6250410676002502, "loss_nocot": 0.2850145399570465, "step": 254 }, { "epoch": 0.23765144454799628, "grad_norm": 0.6329406981073996, "learning_rate": 1.583850931677019e-05, "loss": 1.0217, "step": 255 }, { "epoch": 0.23765144454799628, "loss_cot": 0.5840396881103516, "loss_nocot": 0.7087559700012207, "step": 255 }, { "epoch": 0.2385834109972041, "grad_norm": 0.6994990911383698, "learning_rate": 1.5900621118012424e-05, "loss": 1.1323, "step": 256 }, { "epoch": 0.2385834109972041, "loss_cot": 0.5992868542671204, "loss_nocot": 0.45539766550064087, "step": 256 }, { "epoch": 0.23951537744641194, "grad_norm": 0.6848093828100369, "learning_rate": 1.596273291925466e-05, "loss": 1.0743, "step": 257 }, { "epoch": 0.23951537744641194, "loss_cot": 0.5972615480422974, "loss_nocot": 0.6255854368209839, "step": 257 }, { "epoch": 0.24044734389561975, "grad_norm": 0.726483095004753, "learning_rate": 1.6024844720496894e-05, "loss": 1.1147, "step": 258 }, { "epoch": 0.24044734389561975, "loss_cot": 0.6835112571716309, "loss_nocot": 0.5351482629776001, "step": 258 }, { "epoch": 0.2413793103448276, "grad_norm": 0.6540449715401635, "learning_rate": 1.6086956521739132e-05, "loss": 1.0986, "step": 259 }, { "epoch": 0.2413793103448276, "loss_cot": 0.5832176804542542, "loss_nocot": 0.4232088625431061, "step": 259 }, { "epoch": 0.2423112767940354, "grad_norm": 0.7501624499707806, "learning_rate": 1.6149068322981367e-05, "loss": 1.1694, "step": 260 }, { "epoch": 0.2423112767940354, "loss_cot": 0.5536887049674988, "loss_nocot": 0.5755178928375244, "step": 260 }, { "epoch": 0.24324324324324326, "grad_norm": 0.7299160186895466, "learning_rate": 1.6211180124223606e-05, "loss": 1.1505, "step": 261 }, { "epoch": 0.24324324324324326, "loss_cot": 0.5463538765907288, "loss_nocot": 0.3876972198486328, "step": 261 }, { "epoch": 0.24417520969245107, "grad_norm": 0.7604324054120747, "learning_rate": 1.627329192546584e-05, "loss": 1.1669, "step": 262 }, { "epoch": 0.24417520969245107, "loss_cot": 0.6113790273666382, "loss_nocot": 0.6637871265411377, "step": 262 }, { "epoch": 0.2451071761416589, "grad_norm": 0.7442352944058866, "learning_rate": 1.6335403726708076e-05, "loss": 1.1233, "step": 263 }, { "epoch": 0.2451071761416589, "loss_cot": 0.5551185607910156, "loss_nocot": 0.4800494611263275, "step": 263 }, { "epoch": 0.24603914259086673, "grad_norm": 0.7869017612352736, "learning_rate": 1.639751552795031e-05, "loss": 1.0292, "step": 264 }, { "epoch": 0.24603914259086673, "loss_cot": 0.5759170055389404, "loss_nocot": 0.4524957239627838, "step": 264 }, { "epoch": 0.24697110904007455, "grad_norm": 0.6921605836796744, "learning_rate": 1.645962732919255e-05, "loss": 1.0418, "step": 265 }, { "epoch": 0.24697110904007455, "loss_cot": 0.5452185273170471, "loss_nocot": 0.431199312210083, "step": 265 }, { "epoch": 0.2479030754892824, "grad_norm": 0.6979001242981134, "learning_rate": 1.6521739130434785e-05, "loss": 1.0509, "step": 266 }, { "epoch": 0.2479030754892824, "loss_cot": 0.5092286467552185, "loss_nocot": 0.4302326440811157, "step": 266 }, { "epoch": 0.2488350419384902, "grad_norm": 0.6896945414714449, "learning_rate": 1.658385093167702e-05, "loss": 1.0733, "step": 267 }, { "epoch": 0.2488350419384902, "loss_cot": 0.652651309967041, "loss_nocot": 0.47227999567985535, "step": 267 }, { "epoch": 0.24976700838769805, "grad_norm": 0.7363563559876178, "learning_rate": 1.6645962732919258e-05, "loss": 1.1261, "step": 268 }, { "epoch": 0.24976700838769805, "loss_cot": 0.5637537240982056, "loss_nocot": 0.5201998949050903, "step": 268 }, { "epoch": 0.2506989748369059, "grad_norm": 0.8649516336209031, "learning_rate": 1.670807453416149e-05, "loss": 1.0901, "step": 269 }, { "epoch": 0.2506989748369059, "loss_cot": 0.5802245736122131, "loss_nocot": 0.6160457134246826, "step": 269 }, { "epoch": 0.2516309412861137, "grad_norm": 0.7346128862275524, "learning_rate": 1.6770186335403728e-05, "loss": 1.0752, "step": 270 }, { "epoch": 0.2516309412861137, "loss_cot": 0.5822553634643555, "loss_nocot": 0.5234347581863403, "step": 270 }, { "epoch": 0.25256290773532153, "grad_norm": 0.7165083302256463, "learning_rate": 1.6832298136645963e-05, "loss": 1.1057, "step": 271 }, { "epoch": 0.25256290773532153, "loss_cot": 0.7001940011978149, "loss_nocot": 0.485546350479126, "step": 271 }, { "epoch": 0.2534948741845294, "grad_norm": 0.7436692854580536, "learning_rate": 1.68944099378882e-05, "loss": 1.1008, "step": 272 }, { "epoch": 0.2534948741845294, "loss_cot": 0.6279588937759399, "loss_nocot": 0.4916031062602997, "step": 272 }, { "epoch": 0.25442684063373716, "grad_norm": 0.6476625229603454, "learning_rate": 1.6956521739130437e-05, "loss": 1.0845, "step": 273 }, { "epoch": 0.25442684063373716, "loss_cot": 0.6158952713012695, "loss_nocot": 0.547599196434021, "step": 273 }, { "epoch": 0.255358807082945, "grad_norm": 0.7584265820534717, "learning_rate": 1.7018633540372672e-05, "loss": 1.1058, "step": 274 }, { "epoch": 0.255358807082945, "loss_cot": 0.6697469353675842, "loss_nocot": 0.6137550473213196, "step": 274 }, { "epoch": 0.25629077353215285, "grad_norm": 0.7581984049048509, "learning_rate": 1.7080745341614907e-05, "loss": 1.1581, "step": 275 }, { "epoch": 0.25629077353215285, "loss_cot": 0.6465067267417908, "loss_nocot": 0.7135007381439209, "step": 275 }, { "epoch": 0.2572227399813607, "grad_norm": 0.7306009320542967, "learning_rate": 1.7142857142857142e-05, "loss": 1.111, "step": 276 }, { "epoch": 0.2572227399813607, "loss_cot": 0.5963895320892334, "loss_nocot": 0.40008270740509033, "step": 276 }, { "epoch": 0.2581547064305685, "grad_norm": 0.5900150446327344, "learning_rate": 1.720496894409938e-05, "loss": 0.9645, "step": 277 }, { "epoch": 0.2581547064305685, "loss_cot": 0.5560274124145508, "loss_nocot": 0.4596090316772461, "step": 277 }, { "epoch": 0.2590866728797763, "grad_norm": 0.642845534592707, "learning_rate": 1.7267080745341615e-05, "loss": 1.0309, "step": 278 }, { "epoch": 0.2590866728797763, "loss_cot": 0.5250738859176636, "loss_nocot": 0.4889541268348694, "step": 278 }, { "epoch": 0.26001863932898417, "grad_norm": 0.8235640120107642, "learning_rate": 1.7329192546583854e-05, "loss": 1.111, "step": 279 }, { "epoch": 0.26001863932898417, "loss_cot": 0.5462762117385864, "loss_nocot": 0.4654357433319092, "step": 279 }, { "epoch": 0.26095060577819196, "grad_norm": 0.7628097509037944, "learning_rate": 1.739130434782609e-05, "loss": 1.1165, "step": 280 }, { "epoch": 0.26095060577819196, "loss_cot": 0.6277706623077393, "loss_nocot": 0.5579551458358765, "step": 280 }, { "epoch": 0.2618825722273998, "grad_norm": 0.6972346443904524, "learning_rate": 1.7453416149068324e-05, "loss": 1.0944, "step": 281 }, { "epoch": 0.2618825722273998, "loss_cot": 0.6581377983093262, "loss_nocot": 0.812847375869751, "step": 281 }, { "epoch": 0.26281453867660765, "grad_norm": 0.9020759207426129, "learning_rate": 1.751552795031056e-05, "loss": 1.2771, "step": 282 }, { "epoch": 0.26281453867660765, "loss_cot": 0.6053471565246582, "loss_nocot": 0.4765598773956299, "step": 282 }, { "epoch": 0.2637465051258155, "grad_norm": 0.7430969819641965, "learning_rate": 1.7577639751552797e-05, "loss": 1.051, "step": 283 }, { "epoch": 0.2637465051258155, "loss_cot": 0.5975424647331238, "loss_nocot": 0.3728427290916443, "step": 283 }, { "epoch": 0.2646784715750233, "grad_norm": 0.604457251487808, "learning_rate": 1.7639751552795032e-05, "loss": 0.9516, "step": 284 }, { "epoch": 0.2646784715750233, "loss_cot": 0.612080454826355, "loss_nocot": 0.5715537667274475, "step": 284 }, { "epoch": 0.2656104380242311, "grad_norm": 0.686993716206929, "learning_rate": 1.7701863354037267e-05, "loss": 1.034, "step": 285 }, { "epoch": 0.2656104380242311, "loss_cot": 0.6728270053863525, "loss_nocot": 0.5665817260742188, "step": 285 }, { "epoch": 0.26654240447343897, "grad_norm": 0.6632874928665746, "learning_rate": 1.7763975155279506e-05, "loss": 1.1227, "step": 286 }, { "epoch": 0.26654240447343897, "loss_cot": 0.5650104880332947, "loss_nocot": 0.5898211598396301, "step": 286 }, { "epoch": 0.2674743709226468, "grad_norm": 0.8214598666552938, "learning_rate": 1.782608695652174e-05, "loss": 1.1186, "step": 287 }, { "epoch": 0.2674743709226468, "loss_cot": 0.6145656704902649, "loss_nocot": 0.4519171714782715, "step": 287 }, { "epoch": 0.2684063373718546, "grad_norm": 0.8876290671168698, "learning_rate": 1.7888198757763976e-05, "loss": 1.1953, "step": 288 }, { "epoch": 0.2684063373718546, "loss_cot": 0.5573554039001465, "loss_nocot": 0.5187745094299316, "step": 288 }, { "epoch": 0.26933830382106244, "grad_norm": 0.7778172006292443, "learning_rate": 1.795031055900621e-05, "loss": 1.0977, "step": 289 }, { "epoch": 0.26933830382106244, "loss_cot": 0.5802196264266968, "loss_nocot": 0.4568411111831665, "step": 289 }, { "epoch": 0.2702702702702703, "grad_norm": 0.6629667903159091, "learning_rate": 1.801242236024845e-05, "loss": 1.0264, "step": 290 }, { "epoch": 0.2702702702702703, "loss_cot": 0.6584134101867676, "loss_nocot": 0.6870370507240295, "step": 290 }, { "epoch": 0.2712022367194781, "grad_norm": 0.6716123660945583, "learning_rate": 1.8074534161490685e-05, "loss": 1.1155, "step": 291 }, { "epoch": 0.2712022367194781, "loss_cot": 0.6086136102676392, "loss_nocot": 0.482075572013855, "step": 291 }, { "epoch": 0.2721342031686859, "grad_norm": 0.7077487267798297, "learning_rate": 1.8136645962732923e-05, "loss": 1.1078, "step": 292 }, { "epoch": 0.2721342031686859, "loss_cot": 0.5743558406829834, "loss_nocot": 0.5493192672729492, "step": 292 }, { "epoch": 0.27306616961789376, "grad_norm": 1.5510928158835173, "learning_rate": 1.8198757763975158e-05, "loss": 1.1096, "step": 293 }, { "epoch": 0.27306616961789376, "loss_cot": 0.5746216773986816, "loss_nocot": 0.42925170063972473, "step": 293 }, { "epoch": 0.2739981360671016, "grad_norm": 0.6556217617273578, "learning_rate": 1.8260869565217393e-05, "loss": 1.0509, "step": 294 }, { "epoch": 0.2739981360671016, "loss_cot": 0.623308002948761, "loss_nocot": 0.5380405187606812, "step": 294 }, { "epoch": 0.2749301025163094, "grad_norm": 0.7970917284239047, "learning_rate": 1.8322981366459628e-05, "loss": 1.1618, "step": 295 }, { "epoch": 0.2749301025163094, "loss_cot": 0.5665611624717712, "loss_nocot": 0.4439443349838257, "step": 295 }, { "epoch": 0.27586206896551724, "grad_norm": 0.7294074095278292, "learning_rate": 1.8385093167701863e-05, "loss": 1.0121, "step": 296 }, { "epoch": 0.27586206896551724, "loss_cot": 0.6429389119148254, "loss_nocot": 0.2902117371559143, "step": 296 }, { "epoch": 0.2767940354147251, "grad_norm": 0.6634579861105143, "learning_rate": 1.84472049689441e-05, "loss": 1.0733, "step": 297 }, { "epoch": 0.2767940354147251, "loss_cot": 0.6223878860473633, "loss_nocot": 2.7164080142974854, "step": 297 }, { "epoch": 0.2777260018639329, "grad_norm": 28.505206901877784, "learning_rate": 1.8509316770186337e-05, "loss": 1.6207, "step": 298 }, { "epoch": 0.2777260018639329, "loss_cot": 0.5539063215255737, "loss_nocot": 0.436716228723526, "step": 298 }, { "epoch": 0.2786579683131407, "grad_norm": 0.6796996838358673, "learning_rate": 1.8571428571428575e-05, "loss": 1.0402, "step": 299 }, { "epoch": 0.2786579683131407, "loss_cot": 0.6648465394973755, "loss_nocot": 0.5541929006576538, "step": 299 }, { "epoch": 0.27958993476234856, "grad_norm": 0.8464889550540687, "learning_rate": 1.863354037267081e-05, "loss": 1.1064, "step": 300 }, { "epoch": 0.27958993476234856, "loss_cot": 0.5999451875686646, "loss_nocot": 0.4943528473377228, "step": 300 }, { "epoch": 0.2805219012115564, "grad_norm": 0.6684848136566263, "learning_rate": 1.8695652173913045e-05, "loss": 1.0508, "step": 301 }, { "epoch": 0.2805219012115564, "loss_cot": 0.5987526774406433, "loss_nocot": 0.41722235083580017, "step": 301 }, { "epoch": 0.2814538676607642, "grad_norm": 0.7251890016495675, "learning_rate": 1.875776397515528e-05, "loss": 1.1505, "step": 302 }, { "epoch": 0.2814538676607642, "loss_cot": 0.5361956357955933, "loss_nocot": 0.6283316016197205, "step": 302 }, { "epoch": 0.28238583410997203, "grad_norm": 0.8355594294103045, "learning_rate": 1.881987577639752e-05, "loss": 1.1104, "step": 303 }, { "epoch": 0.28238583410997203, "loss_cot": 0.6601375341415405, "loss_nocot": 0.5150175094604492, "step": 303 }, { "epoch": 0.2833178005591799, "grad_norm": 0.6870218732227588, "learning_rate": 1.8881987577639754e-05, "loss": 1.1497, "step": 304 }, { "epoch": 0.2833178005591799, "loss_cot": 0.5989819765090942, "loss_nocot": 0.416589617729187, "step": 304 }, { "epoch": 0.2842497670083877, "grad_norm": 0.6388504696796049, "learning_rate": 1.894409937888199e-05, "loss": 1.0328, "step": 305 }, { "epoch": 0.2842497670083877, "loss_cot": 0.5908269286155701, "loss_nocot": 0.48905375599861145, "step": 305 }, { "epoch": 0.2851817334575955, "grad_norm": 0.6906403392044176, "learning_rate": 1.9006211180124224e-05, "loss": 0.9782, "step": 306 }, { "epoch": 0.2851817334575955, "loss_cot": 0.6101381182670593, "loss_nocot": 0.5739023685455322, "step": 306 }, { "epoch": 0.28611369990680335, "grad_norm": 0.7266152246890858, "learning_rate": 1.906832298136646e-05, "loss": 1.1326, "step": 307 }, { "epoch": 0.28611369990680335, "loss_cot": 0.5335378646850586, "loss_nocot": 0.462820827960968, "step": 307 }, { "epoch": 0.2870456663560112, "grad_norm": 0.5923706726641015, "learning_rate": 1.9130434782608697e-05, "loss": 0.9976, "step": 308 }, { "epoch": 0.2870456663560112, "loss_cot": 0.6623530387878418, "loss_nocot": 0.44996073842048645, "step": 308 }, { "epoch": 0.287977632805219, "grad_norm": 0.7953064261857534, "learning_rate": 1.9192546583850932e-05, "loss": 1.0663, "step": 309 }, { "epoch": 0.287977632805219, "loss_cot": 0.6392213106155396, "loss_nocot": 0.5132942795753479, "step": 309 }, { "epoch": 0.28890959925442683, "grad_norm": 0.715863682589443, "learning_rate": 1.925465838509317e-05, "loss": 1.0924, "step": 310 }, { "epoch": 0.28890959925442683, "loss_cot": 0.6065669059753418, "loss_nocot": 0.6037058234214783, "step": 310 }, { "epoch": 0.2898415657036347, "grad_norm": 0.8111118014028954, "learning_rate": 1.9316770186335406e-05, "loss": 1.2006, "step": 311 }, { "epoch": 0.2898415657036347, "loss_cot": 0.5414538383483887, "loss_nocot": 0.395720899105072, "step": 311 }, { "epoch": 0.2907735321528425, "grad_norm": 0.696208338410846, "learning_rate": 1.937888198757764e-05, "loss": 1.0439, "step": 312 }, { "epoch": 0.2907735321528425, "loss_cot": 0.5877740383148193, "loss_nocot": 0.5961290597915649, "step": 312 }, { "epoch": 0.2917054986020503, "grad_norm": 0.70475019687625, "learning_rate": 1.9440993788819876e-05, "loss": 1.149, "step": 313 }, { "epoch": 0.2917054986020503, "loss_cot": 0.5710998773574829, "loss_nocot": 0.5460205078125, "step": 313 }, { "epoch": 0.29263746505125815, "grad_norm": 0.722311795591492, "learning_rate": 1.950310559006211e-05, "loss": 1.0515, "step": 314 }, { "epoch": 0.29263746505125815, "loss_cot": 0.5891591310501099, "loss_nocot": 0.34979555010795593, "step": 314 }, { "epoch": 0.293569431500466, "grad_norm": 0.817449228673877, "learning_rate": 1.956521739130435e-05, "loss": 1.1125, "step": 315 }, { "epoch": 0.293569431500466, "loss_cot": 0.5453968644142151, "loss_nocot": 0.47743886709213257, "step": 315 }, { "epoch": 0.29450139794967384, "grad_norm": 0.6597155489229738, "learning_rate": 1.9627329192546585e-05, "loss": 1.067, "step": 316 }, { "epoch": 0.29450139794967384, "loss_cot": 0.5632179975509644, "loss_nocot": 0.6481726169586182, "step": 316 }, { "epoch": 0.2954333643988816, "grad_norm": 0.7719961942481631, "learning_rate": 1.9689440993788823e-05, "loss": 1.0654, "step": 317 }, { "epoch": 0.2954333643988816, "loss_cot": 0.5673841238021851, "loss_nocot": 0.5112293362617493, "step": 317 }, { "epoch": 0.29636533084808947, "grad_norm": 0.6505025629552319, "learning_rate": 1.9751552795031058e-05, "loss": 1.0345, "step": 318 }, { "epoch": 0.29636533084808947, "loss_cot": 0.5265287160873413, "loss_nocot": 0.3770858943462372, "step": 318 }, { "epoch": 0.2972972972972973, "grad_norm": 0.665811236117511, "learning_rate": 1.9813664596273293e-05, "loss": 1.0742, "step": 319 }, { "epoch": 0.2972972972972973, "loss_cot": 0.5846214294433594, "loss_nocot": 0.5114637613296509, "step": 319 }, { "epoch": 0.2982292637465051, "grad_norm": 0.7363701542230411, "learning_rate": 1.9875776397515528e-05, "loss": 1.1056, "step": 320 }, { "epoch": 0.2982292637465051, "loss_cot": 0.5649977922439575, "loss_nocot": 0.3370095491409302, "step": 320 }, { "epoch": 0.29916123019571295, "grad_norm": 0.7024653884840099, "learning_rate": 1.9937888198757767e-05, "loss": 1.0654, "step": 321 }, { "epoch": 0.29916123019571295, "loss_cot": 0.5936656594276428, "loss_nocot": 0.29925960302352905, "step": 321 }, { "epoch": 0.3000931966449208, "grad_norm": 0.8441499324920929, "learning_rate": 2e-05, "loss": 1.0519, "step": 322 }, { "epoch": 0.3000931966449208, "loss_cot": 0.5746537446975708, "loss_nocot": 0.4335782825946808, "step": 322 }, { "epoch": 0.30102516309412863, "grad_norm": 0.79836514981323, "learning_rate": 1.999309630652399e-05, "loss": 1.0538, "step": 323 }, { "epoch": 0.30102516309412863, "loss_cot": 0.5768923163414001, "loss_nocot": 0.49121958017349243, "step": 323 }, { "epoch": 0.3019571295433364, "grad_norm": 0.6792222886466517, "learning_rate": 1.9986192613047983e-05, "loss": 1.0326, "step": 324 }, { "epoch": 0.3019571295433364, "loss_cot": 0.5973414182662964, "loss_nocot": 0.4723036289215088, "step": 324 }, { "epoch": 0.30288909599254427, "grad_norm": 0.6763849631741261, "learning_rate": 1.9979288919571972e-05, "loss": 1.0588, "step": 325 }, { "epoch": 0.30288909599254427, "loss_cot": 0.6644694805145264, "loss_nocot": 0.3493711054325104, "step": 325 }, { "epoch": 0.3038210624417521, "grad_norm": 0.6517865256932276, "learning_rate": 1.997238522609596e-05, "loss": 1.0497, "step": 326 }, { "epoch": 0.3038210624417521, "loss_cot": 0.5834453701972961, "loss_nocot": 0.6516546010971069, "step": 326 }, { "epoch": 0.3047530288909599, "grad_norm": 0.8367685561709479, "learning_rate": 1.9965481532619954e-05, "loss": 1.1168, "step": 327 }, { "epoch": 0.3047530288909599, "loss_cot": 0.5478999614715576, "loss_nocot": 0.555001974105835, "step": 327 }, { "epoch": 0.30568499534016774, "grad_norm": 0.6796166228062454, "learning_rate": 1.9958577839143946e-05, "loss": 1.0802, "step": 328 }, { "epoch": 0.30568499534016774, "loss_cot": 0.5831949710845947, "loss_nocot": 0.4475668668746948, "step": 328 }, { "epoch": 0.3066169617893756, "grad_norm": 0.8486503457612445, "learning_rate": 1.9951674145667935e-05, "loss": 1.0966, "step": 329 }, { "epoch": 0.3066169617893756, "loss_cot": 0.5882941484451294, "loss_nocot": 0.5530401468276978, "step": 329 }, { "epoch": 0.30754892823858343, "grad_norm": 0.6790318986382337, "learning_rate": 1.9944770452191924e-05, "loss": 1.0777, "step": 330 }, { "epoch": 0.30754892823858343, "loss_cot": 0.5467467308044434, "loss_nocot": 0.49682068824768066, "step": 330 }, { "epoch": 0.3084808946877912, "grad_norm": 0.6974855062340363, "learning_rate": 1.9937866758715913e-05, "loss": 1.0808, "step": 331 }, { "epoch": 0.3084808946877912, "loss_cot": 0.5349782705307007, "loss_nocot": 0.43394577503204346, "step": 331 }, { "epoch": 0.30941286113699906, "grad_norm": 0.6827501405358855, "learning_rate": 1.9930963065239906e-05, "loss": 1.0591, "step": 332 }, { "epoch": 0.30941286113699906, "loss_cot": 0.5724664330482483, "loss_nocot": 0.28892797231674194, "step": 332 }, { "epoch": 0.3103448275862069, "grad_norm": 0.6636551159192894, "learning_rate": 1.9924059371763895e-05, "loss": 1.0495, "step": 333 }, { "epoch": 0.3103448275862069, "loss_cot": 0.6268256306648254, "loss_nocot": 0.5368311405181885, "step": 333 }, { "epoch": 0.31127679403541475, "grad_norm": 0.6542810924059189, "learning_rate": 1.9917155678287884e-05, "loss": 1.091, "step": 334 }, { "epoch": 0.31127679403541475, "loss_cot": 0.5917558670043945, "loss_nocot": 0.45855486392974854, "step": 334 }, { "epoch": 0.31220876048462254, "grad_norm": 0.7519364140623627, "learning_rate": 1.9910251984811876e-05, "loss": 1.055, "step": 335 }, { "epoch": 0.31220876048462254, "loss_cot": 0.585034966468811, "loss_nocot": 0.48182931542396545, "step": 335 }, { "epoch": 0.3131407269338304, "grad_norm": 0.694398953760891, "learning_rate": 1.9903348291335865e-05, "loss": 1.0967, "step": 336 }, { "epoch": 0.3131407269338304, "loss_cot": 0.5545620322227478, "loss_nocot": 0.6345438361167908, "step": 336 }, { "epoch": 0.3140726933830382, "grad_norm": 0.8230256704858366, "learning_rate": 1.9896444597859858e-05, "loss": 1.115, "step": 337 }, { "epoch": 0.3140726933830382, "loss_cot": 0.49870651960372925, "loss_nocot": 0.6526142358779907, "step": 337 }, { "epoch": 0.315004659832246, "grad_norm": 0.6862677224035615, "learning_rate": 1.9889540904383847e-05, "loss": 1.083, "step": 338 }, { "epoch": 0.315004659832246, "loss_cot": 0.5726734399795532, "loss_nocot": 0.4462927579879761, "step": 338 }, { "epoch": 0.31593662628145386, "grad_norm": 0.6427315977843803, "learning_rate": 1.988263721090784e-05, "loss": 1.0349, "step": 339 }, { "epoch": 0.31593662628145386, "loss_cot": 0.5742329955101013, "loss_nocot": 0.5387732982635498, "step": 339 }, { "epoch": 0.3168685927306617, "grad_norm": 0.6824753189130681, "learning_rate": 1.9875733517431828e-05, "loss": 1.0932, "step": 340 }, { "epoch": 0.3168685927306617, "loss_cot": 0.5621895790100098, "loss_nocot": 0.43568354845046997, "step": 340 }, { "epoch": 0.31780055917986955, "grad_norm": 0.6340549441298003, "learning_rate": 1.9868829823955817e-05, "loss": 1.0648, "step": 341 }, { "epoch": 0.31780055917986955, "loss_cot": 0.5988958477973938, "loss_nocot": 0.4381638169288635, "step": 341 }, { "epoch": 0.31873252562907733, "grad_norm": 0.6318886323074252, "learning_rate": 1.9861926130479806e-05, "loss": 1.0498, "step": 342 }, { "epoch": 0.31873252562907733, "loss_cot": 0.6098800897598267, "loss_nocot": 0.42603275179862976, "step": 342 }, { "epoch": 0.3196644920782852, "grad_norm": 0.7972448926448236, "learning_rate": 1.98550224370038e-05, "loss": 1.0511, "step": 343 }, { "epoch": 0.3196644920782852, "loss_cot": 0.6186063289642334, "loss_nocot": 0.5686526298522949, "step": 343 }, { "epoch": 0.320596458527493, "grad_norm": 0.8422818554892797, "learning_rate": 1.9848118743527788e-05, "loss": 1.1459, "step": 344 }, { "epoch": 0.320596458527493, "loss_cot": 0.49218687415122986, "loss_nocot": 0.5208251476287842, "step": 344 }, { "epoch": 0.32152842497670087, "grad_norm": 0.6776422736971361, "learning_rate": 1.984121505005178e-05, "loss": 1.0277, "step": 345 }, { "epoch": 0.32152842497670087, "loss_cot": 0.5843741297721863, "loss_nocot": 0.6835174560546875, "step": 345 }, { "epoch": 0.32246039142590865, "grad_norm": 0.6524756773147141, "learning_rate": 1.983431135657577e-05, "loss": 1.0583, "step": 346 }, { "epoch": 0.32246039142590865, "loss_cot": 0.6397352814674377, "loss_nocot": 0.36832642555236816, "step": 346 }, { "epoch": 0.3233923578751165, "grad_norm": 0.6678999407833331, "learning_rate": 1.982740766309976e-05, "loss": 1.0826, "step": 347 }, { "epoch": 0.3233923578751165, "loss_cot": 0.6443203687667847, "loss_nocot": 0.49588721990585327, "step": 347 }, { "epoch": 0.32432432432432434, "grad_norm": 0.6408812004109331, "learning_rate": 1.982050396962375e-05, "loss": 1.0727, "step": 348 }, { "epoch": 0.32432432432432434, "loss_cot": 0.5192399024963379, "loss_nocot": 0.47412243485450745, "step": 348 }, { "epoch": 0.32525629077353213, "grad_norm": 0.6786559019389148, "learning_rate": 1.981360027614774e-05, "loss": 1.0562, "step": 349 }, { "epoch": 0.32525629077353213, "loss_cot": 0.5555649995803833, "loss_nocot": 0.4672958552837372, "step": 349 }, { "epoch": 0.32618825722274, "grad_norm": 0.6173502949251296, "learning_rate": 1.9806696582671732e-05, "loss": 1.0221, "step": 350 }, { "epoch": 0.32618825722274, "loss_cot": 0.5801630616188049, "loss_nocot": 0.679271936416626, "step": 350 }, { "epoch": 0.3271202236719478, "grad_norm": 0.7241075929459727, "learning_rate": 1.979979288919572e-05, "loss": 1.1526, "step": 351 }, { "epoch": 0.3271202236719478, "loss_cot": 0.5517939925193787, "loss_nocot": 0.3650301694869995, "step": 351 }, { "epoch": 0.32805219012115566, "grad_norm": 7.265490564238156, "learning_rate": 1.979288919571971e-05, "loss": 1.1342, "step": 352 }, { "epoch": 0.32805219012115566, "loss_cot": 0.5390347838401794, "loss_nocot": 0.39969754219055176, "step": 352 }, { "epoch": 0.32898415657036345, "grad_norm": 0.6485436936133888, "learning_rate": 1.9785985502243702e-05, "loss": 1.0451, "step": 353 }, { "epoch": 0.32898415657036345, "loss_cot": 0.591434121131897, "loss_nocot": 0.6208484768867493, "step": 353 }, { "epoch": 0.3299161230195713, "grad_norm": 0.7744751501945493, "learning_rate": 1.977908180876769e-05, "loss": 1.0999, "step": 354 }, { "epoch": 0.3299161230195713, "loss_cot": 0.5320420265197754, "loss_nocot": 0.5271145701408386, "step": 354 }, { "epoch": 0.33084808946877914, "grad_norm": 0.7204788128347889, "learning_rate": 1.9772178115291684e-05, "loss": 1.1479, "step": 355 }, { "epoch": 0.33084808946877914, "loss_cot": 0.5311765670776367, "loss_nocot": 0.45962393283843994, "step": 355 }, { "epoch": 0.3317800559179869, "grad_norm": 0.6413743767158959, "learning_rate": 1.9765274421815673e-05, "loss": 0.9728, "step": 356 }, { "epoch": 0.3317800559179869, "loss_cot": 0.6020807027816772, "loss_nocot": 0.4595928192138672, "step": 356 }, { "epoch": 0.33271202236719477, "grad_norm": 0.6555034507404884, "learning_rate": 1.9758370728339665e-05, "loss": 1.0501, "step": 357 }, { "epoch": 0.33271202236719477, "loss_cot": 0.6014455556869507, "loss_nocot": 0.6631703972816467, "step": 357 }, { "epoch": 0.3336439888164026, "grad_norm": 0.7835022327790307, "learning_rate": 1.9751467034863654e-05, "loss": 1.2271, "step": 358 }, { "epoch": 0.3336439888164026, "loss_cot": 0.6015011072158813, "loss_nocot": 0.6937581300735474, "step": 358 }, { "epoch": 0.33457595526561046, "grad_norm": 0.7777679547932826, "learning_rate": 1.9744563341387643e-05, "loss": 1.1474, "step": 359 }, { "epoch": 0.33457595526561046, "loss_cot": 0.5750195980072021, "loss_nocot": 0.34142664074897766, "step": 359 }, { "epoch": 0.33550792171481825, "grad_norm": 0.7754499461377463, "learning_rate": 1.9737659647911633e-05, "loss": 1.0688, "step": 360 }, { "epoch": 0.33550792171481825, "loss_cot": 0.5190398693084717, "loss_nocot": 0.45677074790000916, "step": 360 }, { "epoch": 0.3364398881640261, "grad_norm": 0.6602501351345257, "learning_rate": 1.9730755954435625e-05, "loss": 1.0442, "step": 361 }, { "epoch": 0.3364398881640261, "loss_cot": 0.5503088235855103, "loss_nocot": 0.4217316508293152, "step": 361 }, { "epoch": 0.33737185461323393, "grad_norm": 0.6086566085483922, "learning_rate": 1.9723852260959614e-05, "loss": 0.9584, "step": 362 }, { "epoch": 0.33737185461323393, "loss_cot": 0.5758987665176392, "loss_nocot": 0.4583321511745453, "step": 362 }, { "epoch": 0.3383038210624418, "grad_norm": 0.6651128635565181, "learning_rate": 1.9716948567483606e-05, "loss": 1.058, "step": 363 }, { "epoch": 0.3383038210624418, "loss_cot": 0.5371959805488586, "loss_nocot": 0.42002493143081665, "step": 363 }, { "epoch": 0.33923578751164957, "grad_norm": 0.6845499183871174, "learning_rate": 1.9710044874007595e-05, "loss": 1.1138, "step": 364 }, { "epoch": 0.33923578751164957, "loss_cot": 0.5745118260383606, "loss_nocot": 0.7321501970291138, "step": 364 }, { "epoch": 0.3401677539608574, "grad_norm": 0.8300675147514183, "learning_rate": 1.9703141180531588e-05, "loss": 1.1602, "step": 365 }, { "epoch": 0.3401677539608574, "loss_cot": 0.5749101638793945, "loss_nocot": 0.43204450607299805, "step": 365 }, { "epoch": 0.34109972041006525, "grad_norm": 0.7192447658984344, "learning_rate": 1.9696237487055577e-05, "loss": 1.1019, "step": 366 }, { "epoch": 0.34109972041006525, "loss_cot": 0.6398497819900513, "loss_nocot": 0.4978741407394409, "step": 366 }, { "epoch": 0.34203168685927304, "grad_norm": 0.6507027960439365, "learning_rate": 1.9689333793579566e-05, "loss": 1.0634, "step": 367 }, { "epoch": 0.34203168685927304, "loss_cot": 0.5462619066238403, "loss_nocot": 0.3851626515388489, "step": 367 }, { "epoch": 0.3429636533084809, "grad_norm": 0.5975258685046537, "learning_rate": 1.968243010010356e-05, "loss": 0.9947, "step": 368 }, { "epoch": 0.3429636533084809, "loss_cot": 0.517857551574707, "loss_nocot": 0.3800123333930969, "step": 368 }, { "epoch": 0.34389561975768873, "grad_norm": 0.6403279546588679, "learning_rate": 1.9675526406627547e-05, "loss": 0.9974, "step": 369 }, { "epoch": 0.34389561975768873, "loss_cot": 0.5299266576766968, "loss_nocot": 0.5328345894813538, "step": 369 }, { "epoch": 0.3448275862068966, "grad_norm": 0.7417094228533414, "learning_rate": 1.9668622713151536e-05, "loss": 1.0906, "step": 370 }, { "epoch": 0.3448275862068966, "loss_cot": 0.547173023223877, "loss_nocot": 0.5262021422386169, "step": 370 }, { "epoch": 0.34575955265610436, "grad_norm": 0.6660513132300264, "learning_rate": 1.9661719019675526e-05, "loss": 0.9814, "step": 371 }, { "epoch": 0.34575955265610436, "loss_cot": 0.5486048460006714, "loss_nocot": 0.6799715161323547, "step": 371 }, { "epoch": 0.3466915191053122, "grad_norm": 0.7236514509172581, "learning_rate": 1.9654815326199518e-05, "loss": 1.1035, "step": 372 }, { "epoch": 0.3466915191053122, "loss_cot": 0.5737224817276001, "loss_nocot": 0.59737229347229, "step": 372 }, { "epoch": 0.34762348555452005, "grad_norm": 32.21476913384252, "learning_rate": 1.9647911632723507e-05, "loss": 1.3898, "step": 373 }, { "epoch": 0.34762348555452005, "loss_cot": 0.5218517184257507, "loss_nocot": 0.5307422280311584, "step": 373 }, { "epoch": 0.34855545200372784, "grad_norm": 0.6408269490294877, "learning_rate": 1.96410079392475e-05, "loss": 1.0242, "step": 374 }, { "epoch": 0.34855545200372784, "loss_cot": 0.6077382564544678, "loss_nocot": 0.4584420323371887, "step": 374 }, { "epoch": 0.3494874184529357, "grad_norm": 0.633739713388402, "learning_rate": 1.9634104245771492e-05, "loss": 1.0038, "step": 375 }, { "epoch": 0.3494874184529357, "loss_cot": 0.5905505418777466, "loss_nocot": 0.49360695481300354, "step": 375 }, { "epoch": 0.3504193849021435, "grad_norm": 0.6843830615756338, "learning_rate": 1.962720055229548e-05, "loss": 1.0782, "step": 376 }, { "epoch": 0.3504193849021435, "loss_cot": 0.6116503477096558, "loss_nocot": 0.36954638361930847, "step": 376 }, { "epoch": 0.35135135135135137, "grad_norm": 0.7866761085921573, "learning_rate": 1.962029685881947e-05, "loss": 1.095, "step": 377 }, { "epoch": 0.35135135135135137, "loss_cot": 0.5844241380691528, "loss_nocot": 0.4766101539134979, "step": 377 }, { "epoch": 0.35228331780055916, "grad_norm": 0.5968288296115213, "learning_rate": 1.961339316534346e-05, "loss": 0.9763, "step": 378 }, { "epoch": 0.35228331780055916, "loss_cot": 0.5916619300842285, "loss_nocot": 0.5383001565933228, "step": 378 }, { "epoch": 0.353215284249767, "grad_norm": 0.6985531510296006, "learning_rate": 1.960648947186745e-05, "loss": 1.079, "step": 379 }, { "epoch": 0.353215284249767, "loss_cot": 0.4937915503978729, "loss_nocot": 0.4442325234413147, "step": 379 }, { "epoch": 0.35414725069897485, "grad_norm": 0.6580890234567919, "learning_rate": 1.959958577839144e-05, "loss": 1.0461, "step": 380 }, { "epoch": 0.35414725069897485, "loss_cot": 0.5809780359268188, "loss_nocot": 0.5008988380432129, "step": 380 }, { "epoch": 0.3550792171481827, "grad_norm": 0.6490760308186663, "learning_rate": 1.959268208491543e-05, "loss": 1.0474, "step": 381 }, { "epoch": 0.3550792171481827, "loss_cot": 0.6135519742965698, "loss_nocot": 0.5432662963867188, "step": 381 }, { "epoch": 0.3560111835973905, "grad_norm": 0.7024227103400582, "learning_rate": 1.9585778391439422e-05, "loss": 1.0405, "step": 382 }, { "epoch": 0.3560111835973905, "loss_cot": 0.6072396636009216, "loss_nocot": 0.5522023439407349, "step": 382 }, { "epoch": 0.3569431500465983, "grad_norm": 0.742080316713272, "learning_rate": 1.957887469796341e-05, "loss": 1.1337, "step": 383 }, { "epoch": 0.3569431500465983, "loss_cot": 0.504491925239563, "loss_nocot": 0.49686625599861145, "step": 383 }, { "epoch": 0.35787511649580617, "grad_norm": 0.6376877101089293, "learning_rate": 1.9571971004487403e-05, "loss": 1.0311, "step": 384 }, { "epoch": 0.35787511649580617, "loss_cot": 0.5535157918930054, "loss_nocot": 0.3367512822151184, "step": 384 }, { "epoch": 0.35880708294501396, "grad_norm": 0.6487410038551067, "learning_rate": 1.9565067311011392e-05, "loss": 1.0157, "step": 385 }, { "epoch": 0.35880708294501396, "loss_cot": 0.5432296991348267, "loss_nocot": 0.47800981998443604, "step": 385 }, { "epoch": 0.3597390493942218, "grad_norm": 0.6649418804064579, "learning_rate": 1.9558163617535385e-05, "loss": 1.0439, "step": 386 }, { "epoch": 0.3597390493942218, "loss_cot": 0.5479096174240112, "loss_nocot": 0.4152758717536926, "step": 386 }, { "epoch": 0.36067101584342964, "grad_norm": 0.6678918516580479, "learning_rate": 1.9551259924059374e-05, "loss": 1.0624, "step": 387 }, { "epoch": 0.36067101584342964, "loss_cot": 0.5698502659797668, "loss_nocot": 0.34039703011512756, "step": 387 }, { "epoch": 0.3616029822926375, "grad_norm": 0.611361638460127, "learning_rate": 1.9544356230583363e-05, "loss": 0.9901, "step": 388 }, { "epoch": 0.3616029822926375, "loss_cot": 0.5765388011932373, "loss_nocot": 0.5005046129226685, "step": 388 }, { "epoch": 0.3625349487418453, "grad_norm": 0.700792302846591, "learning_rate": 1.9537452537107352e-05, "loss": 1.0415, "step": 389 }, { "epoch": 0.3625349487418453, "loss_cot": 0.5382907390594482, "loss_nocot": 0.7777643799781799, "step": 389 }, { "epoch": 0.3634669151910531, "grad_norm": 0.8833256995349352, "learning_rate": 1.9530548843631344e-05, "loss": 1.1289, "step": 390 }, { "epoch": 0.3634669151910531, "loss_cot": 0.6050356030464172, "loss_nocot": 0.5513265132904053, "step": 390 }, { "epoch": 0.36439888164026096, "grad_norm": 0.641488566363856, "learning_rate": 1.9523645150155333e-05, "loss": 1.0803, "step": 391 }, { "epoch": 0.36439888164026096, "loss_cot": 0.5256467461585999, "loss_nocot": 0.3868277668952942, "step": 391 }, { "epoch": 0.36533084808946875, "grad_norm": 0.6509294378189246, "learning_rate": 1.9516741456679326e-05, "loss": 0.9748, "step": 392 }, { "epoch": 0.36533084808946875, "loss_cot": 0.5570458769798279, "loss_nocot": 0.3984455466270447, "step": 392 }, { "epoch": 0.3662628145386766, "grad_norm": 0.7007064718121546, "learning_rate": 1.9509837763203315e-05, "loss": 0.9817, "step": 393 }, { "epoch": 0.3662628145386766, "loss_cot": 0.6010556221008301, "loss_nocot": 0.44371432065963745, "step": 393 }, { "epoch": 0.36719478098788444, "grad_norm": 0.6397618591099437, "learning_rate": 1.9502934069727307e-05, "loss": 1.0157, "step": 394 }, { "epoch": 0.36719478098788444, "loss_cot": 0.5035985112190247, "loss_nocot": 0.46349552273750305, "step": 394 }, { "epoch": 0.3681267474370923, "grad_norm": 0.6374631945833338, "learning_rate": 1.9496030376251296e-05, "loss": 1.061, "step": 395 }, { "epoch": 0.3681267474370923, "loss_cot": 0.514579176902771, "loss_nocot": 0.5110875368118286, "step": 395 }, { "epoch": 0.36905871388630007, "grad_norm": 0.62982725637383, "learning_rate": 1.9489126682775285e-05, "loss": 1.0096, "step": 396 }, { "epoch": 0.36905871388630007, "loss_cot": 0.5051480531692505, "loss_nocot": 0.44551166892051697, "step": 396 }, { "epoch": 0.3699906803355079, "grad_norm": 0.6343917670983638, "learning_rate": 1.9482222989299278e-05, "loss": 0.973, "step": 397 }, { "epoch": 0.3699906803355079, "loss_cot": 0.562098503112793, "loss_nocot": 0.33717530965805054, "step": 397 }, { "epoch": 0.37092264678471576, "grad_norm": 0.6479444229963034, "learning_rate": 1.9475319295823267e-05, "loss": 1.0388, "step": 398 }, { "epoch": 0.37092264678471576, "loss_cot": 0.6060038805007935, "loss_nocot": 0.38387012481689453, "step": 398 }, { "epoch": 0.3718546132339236, "grad_norm": 0.6774961870194083, "learning_rate": 1.9468415602347256e-05, "loss": 1.0324, "step": 399 }, { "epoch": 0.3718546132339236, "loss_cot": 0.5018987655639648, "loss_nocot": 0.6012822985649109, "step": 399 }, { "epoch": 0.3727865796831314, "grad_norm": 0.6850907390064297, "learning_rate": 1.9461511908871248e-05, "loss": 1.0458, "step": 400 }, { "epoch": 0.3727865796831314, "loss_cot": 0.5355463624000549, "loss_nocot": 0.4579300880432129, "step": 400 }, { "epoch": 0.37371854613233924, "grad_norm": 0.6725863264685641, "learning_rate": 1.9454608215395237e-05, "loss": 1.0803, "step": 401 }, { "epoch": 0.37371854613233924, "loss_cot": 0.6093152761459351, "loss_nocot": 0.37101173400878906, "step": 401 }, { "epoch": 0.3746505125815471, "grad_norm": 0.6204038586182021, "learning_rate": 1.944770452191923e-05, "loss": 0.9848, "step": 402 }, { "epoch": 0.3746505125815471, "loss_cot": 0.566320538520813, "loss_nocot": 0.5501458644866943, "step": 402 }, { "epoch": 0.37558247903075487, "grad_norm": 0.7421571501810734, "learning_rate": 1.944080082844322e-05, "loss": 1.0928, "step": 403 }, { "epoch": 0.37558247903075487, "loss_cot": 0.5657442212104797, "loss_nocot": 0.6485046148300171, "step": 403 }, { "epoch": 0.3765144454799627, "grad_norm": 0.7403976132631476, "learning_rate": 1.943389713496721e-05, "loss": 1.0777, "step": 404 }, { "epoch": 0.3765144454799627, "loss_cot": 0.5777563452720642, "loss_nocot": 0.41576236486434937, "step": 404 }, { "epoch": 0.37744641192917056, "grad_norm": 0.683137340005845, "learning_rate": 1.94269934414912e-05, "loss": 1.0595, "step": 405 }, { "epoch": 0.37744641192917056, "loss_cot": 0.574272096157074, "loss_nocot": 0.5391466617584229, "step": 405 }, { "epoch": 0.3783783783783784, "grad_norm": 0.7426836379701878, "learning_rate": 1.942008974801519e-05, "loss": 1.034, "step": 406 }, { "epoch": 0.3783783783783784, "loss_cot": 0.5810824632644653, "loss_nocot": 0.3369154930114746, "step": 406 }, { "epoch": 0.3793103448275862, "grad_norm": 0.7910239187976655, "learning_rate": 1.941318605453918e-05, "loss": 1.0178, "step": 407 }, { "epoch": 0.3793103448275862, "loss_cot": 0.5540333986282349, "loss_nocot": 0.5425444841384888, "step": 407 }, { "epoch": 0.38024231127679403, "grad_norm": 0.6626095025953662, "learning_rate": 1.940628236106317e-05, "loss": 1.0417, "step": 408 }, { "epoch": 0.38024231127679403, "loss_cot": 0.6143311858177185, "loss_nocot": 0.6043874621391296, "step": 408 }, { "epoch": 0.3811742777260019, "grad_norm": 0.7583830172724093, "learning_rate": 1.939937866758716e-05, "loss": 1.0887, "step": 409 }, { "epoch": 0.3811742777260019, "loss_cot": 0.5662150382995605, "loss_nocot": 0.49785667657852173, "step": 409 }, { "epoch": 0.3821062441752097, "grad_norm": 0.7346069765293198, "learning_rate": 1.9392474974111152e-05, "loss": 1.1073, "step": 410 }, { "epoch": 0.3821062441752097, "loss_cot": 0.5861252546310425, "loss_nocot": 0.4150822162628174, "step": 410 }, { "epoch": 0.3830382106244175, "grad_norm": 0.6750743153505709, "learning_rate": 1.938557128063514e-05, "loss": 1.029, "step": 411 }, { "epoch": 0.3830382106244175, "loss_cot": 0.6422778367996216, "loss_nocot": 0.4736456573009491, "step": 411 }, { "epoch": 0.38397017707362535, "grad_norm": 0.672681853939802, "learning_rate": 1.9378667587159134e-05, "loss": 1.1012, "step": 412 }, { "epoch": 0.38397017707362535, "loss_cot": 0.4927200973033905, "loss_nocot": 0.4055599570274353, "step": 412 }, { "epoch": 0.3849021435228332, "grad_norm": 0.7719494575309791, "learning_rate": 1.9371763893683123e-05, "loss": 0.9595, "step": 413 }, { "epoch": 0.3849021435228332, "loss_cot": 0.5277903079986572, "loss_nocot": 0.4832519590854645, "step": 413 }, { "epoch": 0.385834109972041, "grad_norm": 0.6265712126118307, "learning_rate": 1.9364860200207112e-05, "loss": 0.9696, "step": 414 }, { "epoch": 0.385834109972041, "loss_cot": 0.6139301657676697, "loss_nocot": 0.42313581705093384, "step": 414 }, { "epoch": 0.38676607642124883, "grad_norm": 0.674678991642941, "learning_rate": 1.9357956506731104e-05, "loss": 1.0733, "step": 415 }, { "epoch": 0.38676607642124883, "loss_cot": 0.5525542497634888, "loss_nocot": 0.4660050570964813, "step": 415 }, { "epoch": 0.38769804287045667, "grad_norm": 0.6503413974054362, "learning_rate": 1.9351052813255093e-05, "loss": 1.0968, "step": 416 }, { "epoch": 0.38769804287045667, "loss_cot": 0.5250723361968994, "loss_nocot": 0.39867204427719116, "step": 416 }, { "epoch": 0.3886300093196645, "grad_norm": 0.6383951595622247, "learning_rate": 1.9344149119779082e-05, "loss": 0.9926, "step": 417 }, { "epoch": 0.3886300093196645, "loss_cot": 0.6245573163032532, "loss_nocot": 0.6169633865356445, "step": 417 }, { "epoch": 0.3895619757688723, "grad_norm": 0.6630846431789983, "learning_rate": 1.933724542630307e-05, "loss": 1.0413, "step": 418 }, { "epoch": 0.3895619757688723, "loss_cot": 0.5502790808677673, "loss_nocot": 0.443250834941864, "step": 418 }, { "epoch": 0.39049394221808015, "grad_norm": 0.7659737526883643, "learning_rate": 1.9330341732827064e-05, "loss": 1.09, "step": 419 }, { "epoch": 0.39049394221808015, "loss_cot": 0.506550133228302, "loss_nocot": 0.45569056272506714, "step": 419 }, { "epoch": 0.391425908667288, "grad_norm": 0.6333755675408584, "learning_rate": 1.9323438039351056e-05, "loss": 0.9967, "step": 420 }, { "epoch": 0.391425908667288, "loss_cot": 0.5828301310539246, "loss_nocot": 0.6549180746078491, "step": 420 }, { "epoch": 0.3923578751164958, "grad_norm": 0.7575083593338956, "learning_rate": 1.9316534345875045e-05, "loss": 1.1605, "step": 421 }, { "epoch": 0.3923578751164958, "loss_cot": 0.5975593328475952, "loss_nocot": 0.47831934690475464, "step": 421 }, { "epoch": 0.3932898415657036, "grad_norm": 0.6632535971414257, "learning_rate": 1.9309630652399034e-05, "loss": 1.0637, "step": 422 }, { "epoch": 0.3932898415657036, "loss_cot": 0.5753180384635925, "loss_nocot": 0.5311611294746399, "step": 422 }, { "epoch": 0.39422180801491147, "grad_norm": 0.7549686093511446, "learning_rate": 1.9302726958923027e-05, "loss": 1.1046, "step": 423 }, { "epoch": 0.39422180801491147, "loss_cot": 0.5337231159210205, "loss_nocot": 0.5053136348724365, "step": 423 }, { "epoch": 0.3951537744641193, "grad_norm": 0.6815726316482659, "learning_rate": 1.9295823265447016e-05, "loss": 1.0802, "step": 424 }, { "epoch": 0.3951537744641193, "loss_cot": 0.5432838201522827, "loss_nocot": 0.42247113585472107, "step": 424 }, { "epoch": 0.3960857409133271, "grad_norm": 0.7021181790931946, "learning_rate": 1.9288919571971005e-05, "loss": 1.0108, "step": 425 }, { "epoch": 0.3960857409133271, "loss_cot": 0.6182104349136353, "loss_nocot": 0.41456887125968933, "step": 425 }, { "epoch": 0.39701770736253494, "grad_norm": 0.6716799360818079, "learning_rate": 1.9282015878494997e-05, "loss": 1.0462, "step": 426 }, { "epoch": 0.39701770736253494, "loss_cot": 0.5532072186470032, "loss_nocot": 0.4271758198738098, "step": 426 }, { "epoch": 0.3979496738117428, "grad_norm": 0.6448798135982575, "learning_rate": 1.9275112185018986e-05, "loss": 0.9817, "step": 427 }, { "epoch": 0.3979496738117428, "loss_cot": 0.548058032989502, "loss_nocot": 0.6160704493522644, "step": 427 }, { "epoch": 0.39888164026095063, "grad_norm": 0.6762178377558461, "learning_rate": 1.9268208491542975e-05, "loss": 1.0584, "step": 428 }, { "epoch": 0.39888164026095063, "loss_cot": 0.5992042422294617, "loss_nocot": 0.3834255337715149, "step": 428 }, { "epoch": 0.3998136067101584, "grad_norm": 0.8021979960538839, "learning_rate": 1.9261304798066968e-05, "loss": 0.9887, "step": 429 }, { "epoch": 0.3998136067101584, "loss_cot": 0.52435302734375, "loss_nocot": 0.4603980481624603, "step": 429 }, { "epoch": 0.40074557315936626, "grad_norm": 0.6915988717517465, "learning_rate": 1.925440110459096e-05, "loss": 1.0593, "step": 430 }, { "epoch": 0.40074557315936626, "loss_cot": 0.5320976972579956, "loss_nocot": 0.5805166959762573, "step": 430 }, { "epoch": 0.4016775396085741, "grad_norm": 0.8329544306994251, "learning_rate": 1.924749741111495e-05, "loss": 1.1734, "step": 431 }, { "epoch": 0.4016775396085741, "loss_cot": 0.6065605282783508, "loss_nocot": 0.4571148157119751, "step": 431 }, { "epoch": 0.4026095060577819, "grad_norm": 0.7019588346823813, "learning_rate": 1.9240593717638938e-05, "loss": 1.1076, "step": 432 }, { "epoch": 0.4026095060577819, "loss_cot": 0.6076522469520569, "loss_nocot": 0.4758365750312805, "step": 432 }, { "epoch": 0.40354147250698974, "grad_norm": 0.6681085441336229, "learning_rate": 1.9233690024162927e-05, "loss": 1.0512, "step": 433 }, { "epoch": 0.40354147250698974, "loss_cot": 0.6173204183578491, "loss_nocot": 0.47116756439208984, "step": 433 }, { "epoch": 0.4044734389561976, "grad_norm": 0.7362796060012389, "learning_rate": 1.922678633068692e-05, "loss": 1.0678, "step": 434 }, { "epoch": 0.4044734389561976, "loss_cot": 0.5860982537269592, "loss_nocot": 0.46969732642173767, "step": 434 }, { "epoch": 0.40540540540540543, "grad_norm": 0.659903170533572, "learning_rate": 1.921988263721091e-05, "loss": 1.0308, "step": 435 }, { "epoch": 0.40540540540540543, "loss_cot": 0.5829790234565735, "loss_nocot": 0.4400536119937897, "step": 435 }, { "epoch": 0.4063373718546132, "grad_norm": 0.7010666011197193, "learning_rate": 1.9212978943734898e-05, "loss": 1.0426, "step": 436 }, { "epoch": 0.4063373718546132, "loss_cot": 0.6133280396461487, "loss_nocot": 0.6849981546401978, "step": 436 }, { "epoch": 0.40726933830382106, "grad_norm": 0.7239764630295149, "learning_rate": 1.920607525025889e-05, "loss": 1.1409, "step": 437 }, { "epoch": 0.40726933830382106, "loss_cot": 0.5850489735603333, "loss_nocot": 0.3643433749675751, "step": 437 }, { "epoch": 0.4082013047530289, "grad_norm": 0.6529770574806769, "learning_rate": 1.919917155678288e-05, "loss": 1.0092, "step": 438 }, { "epoch": 0.4082013047530289, "loss_cot": 0.5046075582504272, "loss_nocot": 0.45108455419540405, "step": 438 }, { "epoch": 0.4091332712022367, "grad_norm": 0.6611638618114076, "learning_rate": 1.919226786330687e-05, "loss": 1.0389, "step": 439 }, { "epoch": 0.4091332712022367, "loss_cot": 0.5827428102493286, "loss_nocot": 0.46046799421310425, "step": 439 }, { "epoch": 0.41006523765144454, "grad_norm": 0.6956581902228445, "learning_rate": 1.918536416983086e-05, "loss": 1.0386, "step": 440 }, { "epoch": 0.41006523765144454, "loss_cot": 0.5842732787132263, "loss_nocot": 0.5215663909912109, "step": 440 }, { "epoch": 0.4109972041006524, "grad_norm": 0.6466833551217173, "learning_rate": 1.9178460476354853e-05, "loss": 0.9703, "step": 441 }, { "epoch": 0.4109972041006524, "loss_cot": 0.60099196434021, "loss_nocot": 0.45063966512680054, "step": 441 }, { "epoch": 0.4119291705498602, "grad_norm": 0.6172189192136857, "learning_rate": 1.9171556782878842e-05, "loss": 0.9913, "step": 442 }, { "epoch": 0.4119291705498602, "loss_cot": 0.5422381162643433, "loss_nocot": 0.4314693212509155, "step": 442 }, { "epoch": 0.412861136999068, "grad_norm": 0.6725710716788702, "learning_rate": 1.916465308940283e-05, "loss": 1.0578, "step": 443 }, { "epoch": 0.412861136999068, "loss_cot": 0.5251117944717407, "loss_nocot": 0.3992169201374054, "step": 443 }, { "epoch": 0.41379310344827586, "grad_norm": 0.683475372342207, "learning_rate": 1.9157749395926824e-05, "loss": 0.992, "step": 444 }, { "epoch": 0.41379310344827586, "loss_cot": 0.5977989435195923, "loss_nocot": 0.43586981296539307, "step": 444 }, { "epoch": 0.4147250698974837, "grad_norm": 0.7162116782408893, "learning_rate": 1.9150845702450813e-05, "loss": 1.0402, "step": 445 }, { "epoch": 0.4147250698974837, "loss_cot": 0.6340588331222534, "loss_nocot": 0.7015682458877563, "step": 445 }, { "epoch": 0.41565703634669154, "grad_norm": 0.7686614076463928, "learning_rate": 1.91439420089748e-05, "loss": 1.0908, "step": 446 }, { "epoch": 0.41565703634669154, "loss_cot": 0.5796846151351929, "loss_nocot": 0.40609776973724365, "step": 446 }, { "epoch": 0.41658900279589933, "grad_norm": 0.5826957813797072, "learning_rate": 1.9137038315498794e-05, "loss": 0.943, "step": 447 }, { "epoch": 0.41658900279589933, "loss_cot": 0.5842987298965454, "loss_nocot": 0.4612368643283844, "step": 447 }, { "epoch": 0.4175209692451072, "grad_norm": 0.7387262759345927, "learning_rate": 1.9130134622022783e-05, "loss": 1.0212, "step": 448 }, { "epoch": 0.4175209692451072, "loss_cot": 0.5660642385482788, "loss_nocot": 0.5051107406616211, "step": 448 }, { "epoch": 0.418452935694315, "grad_norm": 0.6680235128237929, "learning_rate": 1.9123230928546776e-05, "loss": 1.0407, "step": 449 }, { "epoch": 0.418452935694315, "loss_cot": 0.5393254160881042, "loss_nocot": 0.5237394571304321, "step": 449 }, { "epoch": 0.4193849021435228, "grad_norm": 0.6330085946562163, "learning_rate": 1.9116327235070765e-05, "loss": 1.0052, "step": 450 }, { "epoch": 0.4193849021435228, "loss_cot": 0.5472511053085327, "loss_nocot": 0.5468941926956177, "step": 450 }, { "epoch": 0.42031686859273065, "grad_norm": 0.6584788032965431, "learning_rate": 1.9109423541594754e-05, "loss": 1.0299, "step": 451 }, { "epoch": 0.42031686859273065, "loss_cot": 0.5664205551147461, "loss_nocot": 0.5637482404708862, "step": 451 }, { "epoch": 0.4212488350419385, "grad_norm": 0.7478326893412015, "learning_rate": 1.9102519848118746e-05, "loss": 1.0334, "step": 452 }, { "epoch": 0.4212488350419385, "loss_cot": 0.5998755693435669, "loss_nocot": 0.36770063638687134, "step": 452 }, { "epoch": 0.42218080149114634, "grad_norm": 0.6333543720917713, "learning_rate": 1.9095616154642735e-05, "loss": 0.9593, "step": 453 }, { "epoch": 0.42218080149114634, "loss_cot": 0.5462993383407593, "loss_nocot": 0.4486323595046997, "step": 453 }, { "epoch": 0.42311276794035413, "grad_norm": 0.7047875629720108, "learning_rate": 1.9088712461166724e-05, "loss": 1.0069, "step": 454 }, { "epoch": 0.42311276794035413, "loss_cot": 0.5962455868721008, "loss_nocot": 0.3963424265384674, "step": 454 }, { "epoch": 0.424044734389562, "grad_norm": 0.6286699397402954, "learning_rate": 1.9081808767690717e-05, "loss": 0.992, "step": 455 }, { "epoch": 0.424044734389562, "loss_cot": 0.5613746047019958, "loss_nocot": 0.5670101642608643, "step": 455 }, { "epoch": 0.4249767008387698, "grad_norm": 0.647916104949995, "learning_rate": 1.9074905074214706e-05, "loss": 0.9938, "step": 456 }, { "epoch": 0.4249767008387698, "loss_cot": 0.5639286041259766, "loss_nocot": 0.42382875084877014, "step": 456 }, { "epoch": 0.42590866728797766, "grad_norm": 0.6475957578463424, "learning_rate": 1.9068001380738698e-05, "loss": 1.0266, "step": 457 }, { "epoch": 0.42590866728797766, "loss_cot": 0.706607460975647, "loss_nocot": 0.3964606821537018, "step": 457 }, { "epoch": 0.42684063373718545, "grad_norm": 0.6705614558331714, "learning_rate": 1.9061097687262687e-05, "loss": 1.0508, "step": 458 }, { "epoch": 0.42684063373718545, "loss_cot": 0.5912491679191589, "loss_nocot": 0.6543200016021729, "step": 458 }, { "epoch": 0.4277726001863933, "grad_norm": 0.6778668430481821, "learning_rate": 1.905419399378668e-05, "loss": 1.0666, "step": 459 }, { "epoch": 0.4277726001863933, "loss_cot": 0.5502548217773438, "loss_nocot": 0.3749282658100128, "step": 459 }, { "epoch": 0.42870456663560114, "grad_norm": 0.6249444291272168, "learning_rate": 1.904729030031067e-05, "loss": 0.9946, "step": 460 }, { "epoch": 0.42870456663560114, "loss_cot": 0.5821716785430908, "loss_nocot": 0.5909280776977539, "step": 460 }, { "epoch": 0.4296365330848089, "grad_norm": 0.6448859836280062, "learning_rate": 1.9040386606834658e-05, "loss": 1.0253, "step": 461 }, { "epoch": 0.4296365330848089, "loss_cot": 0.5521560907363892, "loss_nocot": 0.39358675479888916, "step": 461 }, { "epoch": 0.43056849953401677, "grad_norm": 0.6516978556972198, "learning_rate": 1.9033482913358647e-05, "loss": 0.9909, "step": 462 }, { "epoch": 0.43056849953401677, "loss_cot": 0.5110374689102173, "loss_nocot": 0.46804478764533997, "step": 462 }, { "epoch": 0.4315004659832246, "grad_norm": 0.7686119525582814, "learning_rate": 1.902657921988264e-05, "loss": 1.0274, "step": 463 }, { "epoch": 0.4315004659832246, "loss_cot": 0.5387184619903564, "loss_nocot": 0.40656423568725586, "step": 463 }, { "epoch": 0.43243243243243246, "grad_norm": 0.6807479684886788, "learning_rate": 1.9019675526406628e-05, "loss": 0.9476, "step": 464 }, { "epoch": 0.43243243243243246, "loss_cot": 0.5994023084640503, "loss_nocot": 0.4292737543582916, "step": 464 }, { "epoch": 0.43336439888164024, "grad_norm": 0.8781342780573715, "learning_rate": 1.901277183293062e-05, "loss": 1.1574, "step": 465 }, { "epoch": 0.43336439888164024, "loss_cot": 0.5830110907554626, "loss_nocot": 0.630247950553894, "step": 465 }, { "epoch": 0.4342963653308481, "grad_norm": 0.6674517280302724, "learning_rate": 1.900586813945461e-05, "loss": 0.9947, "step": 466 }, { "epoch": 0.4342963653308481, "loss_cot": 0.5575019121170044, "loss_nocot": 0.37005171179771423, "step": 466 }, { "epoch": 0.43522833178005593, "grad_norm": 0.6356803696950233, "learning_rate": 1.8998964445978602e-05, "loss": 1.0454, "step": 467 }, { "epoch": 0.43522833178005593, "loss_cot": 0.5326055288314819, "loss_nocot": 0.37616100907325745, "step": 467 }, { "epoch": 0.4361602982292637, "grad_norm": 0.6349279924688405, "learning_rate": 1.899206075250259e-05, "loss": 0.9858, "step": 468 }, { "epoch": 0.4361602982292637, "loss_cot": 0.5814511775970459, "loss_nocot": 0.49791795015335083, "step": 468 }, { "epoch": 0.43709226467847156, "grad_norm": 0.7386785437860817, "learning_rate": 1.898515705902658e-05, "loss": 1.0575, "step": 469 }, { "epoch": 0.43709226467847156, "loss_cot": 0.5545132160186768, "loss_nocot": 0.6561908721923828, "step": 469 }, { "epoch": 0.4380242311276794, "grad_norm": 0.7069214348910146, "learning_rate": 1.8978253365550572e-05, "loss": 1.0602, "step": 470 }, { "epoch": 0.4380242311276794, "loss_cot": 0.5125982165336609, "loss_nocot": 0.5560677647590637, "step": 470 }, { "epoch": 0.43895619757688725, "grad_norm": 0.7563961634690706, "learning_rate": 1.897134967207456e-05, "loss": 1.116, "step": 471 }, { "epoch": 0.43895619757688725, "loss_cot": 0.6143314838409424, "loss_nocot": 0.469318151473999, "step": 471 }, { "epoch": 0.43988816402609504, "grad_norm": 0.6723696011569414, "learning_rate": 1.896444597859855e-05, "loss": 1.0913, "step": 472 }, { "epoch": 0.43988816402609504, "loss_cot": 0.5287169218063354, "loss_nocot": 0.41012057662010193, "step": 472 }, { "epoch": 0.4408201304753029, "grad_norm": 0.6057902733305025, "learning_rate": 1.895754228512254e-05, "loss": 0.9775, "step": 473 }, { "epoch": 0.4408201304753029, "loss_cot": 0.5257737040519714, "loss_nocot": 0.5908749103546143, "step": 473 }, { "epoch": 0.44175209692451073, "grad_norm": 0.7122823779207635, "learning_rate": 1.8950638591646532e-05, "loss": 1.1011, "step": 474 }, { "epoch": 0.44175209692451073, "loss_cot": 0.5028562545776367, "loss_nocot": 0.5855607986450195, "step": 474 }, { "epoch": 0.4426840633737186, "grad_norm": 0.6710334776203005, "learning_rate": 1.894373489817052e-05, "loss": 1.0258, "step": 475 }, { "epoch": 0.4426840633737186, "loss_cot": 0.5727980136871338, "loss_nocot": 0.4682830572128296, "step": 475 }, { "epoch": 0.44361602982292636, "grad_norm": 0.6734461557884767, "learning_rate": 1.8936831204694513e-05, "loss": 1.0608, "step": 476 }, { "epoch": 0.44361602982292636, "loss_cot": 0.6018854379653931, "loss_nocot": 0.3982946574687958, "step": 476 }, { "epoch": 0.4445479962721342, "grad_norm": 0.6455659991544269, "learning_rate": 1.8929927511218506e-05, "loss": 1.0542, "step": 477 }, { "epoch": 0.4445479962721342, "loss_cot": 0.5599216222763062, "loss_nocot": 0.5392163991928101, "step": 477 }, { "epoch": 0.44547996272134205, "grad_norm": 0.6605537937920143, "learning_rate": 1.8923023817742495e-05, "loss": 1.0997, "step": 478 }, { "epoch": 0.44547996272134205, "loss_cot": 0.5469855070114136, "loss_nocot": 0.5542036294937134, "step": 478 }, { "epoch": 0.44641192917054984, "grad_norm": 0.676299420084341, "learning_rate": 1.8916120124266484e-05, "loss": 1.0659, "step": 479 }, { "epoch": 0.44641192917054984, "loss_cot": 0.540774941444397, "loss_nocot": 0.6390047073364258, "step": 479 }, { "epoch": 0.4473438956197577, "grad_norm": 0.8048410850465709, "learning_rate": 1.8909216430790473e-05, "loss": 1.1501, "step": 480 }, { "epoch": 0.4473438956197577, "loss_cot": 0.5823453664779663, "loss_nocot": 0.4740501642227173, "step": 480 }, { "epoch": 0.4482758620689655, "grad_norm": 0.6936379248332863, "learning_rate": 1.8902312737314465e-05, "loss": 1.1143, "step": 481 }, { "epoch": 0.4482758620689655, "loss_cot": 0.573432445526123, "loss_nocot": 0.37773337960243225, "step": 481 }, { "epoch": 0.44920782851817337, "grad_norm": 0.6355612208155328, "learning_rate": 1.8895409043838454e-05, "loss": 1.0285, "step": 482 }, { "epoch": 0.44920782851817337, "loss_cot": 0.5700480937957764, "loss_nocot": 0.4668610394001007, "step": 482 }, { "epoch": 0.45013979496738116, "grad_norm": 0.6852472475919839, "learning_rate": 1.8888505350362443e-05, "loss": 0.9796, "step": 483 }, { "epoch": 0.45013979496738116, "loss_cot": 0.5500595569610596, "loss_nocot": 0.4684199094772339, "step": 483 }, { "epoch": 0.451071761416589, "grad_norm": 0.6674875927274124, "learning_rate": 1.8881601656886436e-05, "loss": 0.9904, "step": 484 }, { "epoch": 0.451071761416589, "loss_cot": 0.5800882577896118, "loss_nocot": 0.3679109513759613, "step": 484 }, { "epoch": 0.45200372786579684, "grad_norm": 0.6916585914883884, "learning_rate": 1.8874697963410425e-05, "loss": 0.9562, "step": 485 }, { "epoch": 0.45200372786579684, "loss_cot": 0.5378942489624023, "loss_nocot": 0.44326937198638916, "step": 485 }, { "epoch": 0.45293569431500463, "grad_norm": 0.7248618877955862, "learning_rate": 1.8867794269934417e-05, "loss": 1.1133, "step": 486 }, { "epoch": 0.45293569431500463, "loss_cot": 0.5958273410797119, "loss_nocot": 0.3547251224517822, "step": 486 }, { "epoch": 0.4538676607642125, "grad_norm": 0.6870333244054301, "learning_rate": 1.8860890576458406e-05, "loss": 1.0777, "step": 487 }, { "epoch": 0.4538676607642125, "loss_cot": 0.5446828007698059, "loss_nocot": 0.3251212537288666, "step": 487 }, { "epoch": 0.4547996272134203, "grad_norm": 0.5872536183396567, "learning_rate": 1.88539868829824e-05, "loss": 0.9803, "step": 488 }, { "epoch": 0.4547996272134203, "loss_cot": 0.5659098029136658, "loss_nocot": 0.46068570017814636, "step": 488 }, { "epoch": 0.45573159366262816, "grad_norm": 0.6916025258488293, "learning_rate": 1.8847083189506388e-05, "loss": 1.0763, "step": 489 }, { "epoch": 0.45573159366262816, "loss_cot": 0.49553805589675903, "loss_nocot": 0.38510802388191223, "step": 489 }, { "epoch": 0.45666356011183595, "grad_norm": 0.647310494775797, "learning_rate": 1.8840179496030377e-05, "loss": 1.0214, "step": 490 }, { "epoch": 0.45666356011183595, "loss_cot": 0.5406575202941895, "loss_nocot": 0.4227454662322998, "step": 490 }, { "epoch": 0.4575955265610438, "grad_norm": 0.6450568987453774, "learning_rate": 1.8833275802554366e-05, "loss": 0.9737, "step": 491 }, { "epoch": 0.4575955265610438, "loss_cot": 0.5275534391403198, "loss_nocot": 0.4738766849040985, "step": 491 }, { "epoch": 0.45852749301025164, "grad_norm": 0.6902879003560581, "learning_rate": 1.882637210907836e-05, "loss": 1.0752, "step": 492 }, { "epoch": 0.45852749301025164, "loss_cot": 0.5215421915054321, "loss_nocot": 0.505312442779541, "step": 492 }, { "epoch": 0.4594594594594595, "grad_norm": 0.5916472501021764, "learning_rate": 1.8819468415602347e-05, "loss": 0.9626, "step": 493 }, { "epoch": 0.4594594594594595, "loss_cot": 0.5621761679649353, "loss_nocot": 0.4253597855567932, "step": 493 }, { "epoch": 0.4603914259086673, "grad_norm": 0.6068795592363898, "learning_rate": 1.881256472212634e-05, "loss": 1.008, "step": 494 }, { "epoch": 0.4603914259086673, "loss_cot": 0.5403579473495483, "loss_nocot": 0.39491426944732666, "step": 494 }, { "epoch": 0.4613233923578751, "grad_norm": 0.6668878482401618, "learning_rate": 1.880566102865033e-05, "loss": 0.9797, "step": 495 }, { "epoch": 0.4613233923578751, "loss_cot": 0.507014811038971, "loss_nocot": 0.4450863301753998, "step": 495 }, { "epoch": 0.46225535880708296, "grad_norm": 0.5989127934356783, "learning_rate": 1.879875733517432e-05, "loss": 0.9529, "step": 496 }, { "epoch": 0.46225535880708296, "loss_cot": 0.5823175311088562, "loss_nocot": 0.3551011085510254, "step": 496 }, { "epoch": 0.46318732525629075, "grad_norm": 0.617628984674071, "learning_rate": 1.879185364169831e-05, "loss": 1.0211, "step": 497 }, { "epoch": 0.46318732525629075, "loss_cot": 0.5532141923904419, "loss_nocot": 0.488719642162323, "step": 497 }, { "epoch": 0.4641192917054986, "grad_norm": 0.6138032038147405, "learning_rate": 1.87849499482223e-05, "loss": 1.0095, "step": 498 }, { "epoch": 0.4641192917054986, "loss_cot": 0.5552414655685425, "loss_nocot": 0.360487699508667, "step": 498 }, { "epoch": 0.46505125815470644, "grad_norm": 0.6291732350629757, "learning_rate": 1.8778046254746292e-05, "loss": 0.9413, "step": 499 }, { "epoch": 0.46505125815470644, "loss_cot": 0.5230647921562195, "loss_nocot": 0.6518762111663818, "step": 499 }, { "epoch": 0.4659832246039143, "grad_norm": 0.8095327814817854, "learning_rate": 1.877114256127028e-05, "loss": 1.0969, "step": 500 }, { "epoch": 0.4659832246039143, "loss_cot": 0.5229116678237915, "loss_nocot": 0.45104870200157166, "step": 500 }, { "epoch": 0.46691519105312207, "grad_norm": 0.6080652562240797, "learning_rate": 1.876423886779427e-05, "loss": 1.0044, "step": 501 }, { "epoch": 0.46691519105312207, "loss_cot": 0.5848287343978882, "loss_nocot": 0.5706957578659058, "step": 501 }, { "epoch": 0.4678471575023299, "grad_norm": 0.6897073720817503, "learning_rate": 1.8757335174318262e-05, "loss": 1.0567, "step": 502 }, { "epoch": 0.4678471575023299, "loss_cot": 0.5026415586471558, "loss_nocot": 0.49588075280189514, "step": 502 }, { "epoch": 0.46877912395153776, "grad_norm": 0.7201301071486217, "learning_rate": 1.875043148084225e-05, "loss": 0.9941, "step": 503 }, { "epoch": 0.46877912395153776, "loss_cot": 0.5292466878890991, "loss_nocot": 0.41207683086395264, "step": 503 }, { "epoch": 0.46971109040074555, "grad_norm": 0.5669337588566556, "learning_rate": 1.8743527787366244e-05, "loss": 0.9123, "step": 504 }, { "epoch": 0.46971109040074555, "loss_cot": 0.5022305846214294, "loss_nocot": 0.37898963689804077, "step": 504 }, { "epoch": 0.4706430568499534, "grad_norm": 0.6962042224080707, "learning_rate": 1.8736624093890233e-05, "loss": 1.0277, "step": 505 }, { "epoch": 0.4706430568499534, "loss_cot": 0.6298894286155701, "loss_nocot": 0.5018436908721924, "step": 505 }, { "epoch": 0.47157502329916123, "grad_norm": 0.7388511798576188, "learning_rate": 1.8729720400414225e-05, "loss": 1.0873, "step": 506 }, { "epoch": 0.47157502329916123, "loss_cot": 0.5376641154289246, "loss_nocot": 0.6820564866065979, "step": 506 }, { "epoch": 0.4725069897483691, "grad_norm": 0.6784212433802792, "learning_rate": 1.8722816706938214e-05, "loss": 1.0472, "step": 507 }, { "epoch": 0.4725069897483691, "loss_cot": 0.5346184968948364, "loss_nocot": 0.5058826208114624, "step": 507 }, { "epoch": 0.47343895619757687, "grad_norm": 0.7380499984717893, "learning_rate": 1.8715913013462203e-05, "loss": 1.0812, "step": 508 }, { "epoch": 0.47343895619757687, "loss_cot": 0.62205970287323, "loss_nocot": 0.44692620635032654, "step": 508 }, { "epoch": 0.4743709226467847, "grad_norm": 0.6530359456022198, "learning_rate": 1.8709009319986192e-05, "loss": 1.0383, "step": 509 }, { "epoch": 0.4743709226467847, "loss_cot": 0.5228177309036255, "loss_nocot": 0.47918206453323364, "step": 509 }, { "epoch": 0.47530288909599255, "grad_norm": 0.6471849617017421, "learning_rate": 1.8702105626510185e-05, "loss": 0.966, "step": 510 }, { "epoch": 0.47530288909599255, "loss_cot": 0.4841274917125702, "loss_nocot": 0.4069589078426361, "step": 510 }, { "epoch": 0.4762348555452004, "grad_norm": 0.7259674892312455, "learning_rate": 1.8695201933034174e-05, "loss": 0.9794, "step": 511 }, { "epoch": 0.4762348555452004, "loss_cot": 0.5257054567337036, "loss_nocot": 0.6038024425506592, "step": 511 }, { "epoch": 0.4771668219944082, "grad_norm": 0.6064793843702453, "learning_rate": 1.8688298239558166e-05, "loss": 0.987, "step": 512 }, { "epoch": 0.4771668219944082, "loss_cot": 0.5664989352226257, "loss_nocot": 0.4302302896976471, "step": 512 }, { "epoch": 0.47809878844361603, "grad_norm": 0.6752180963662586, "learning_rate": 1.8681394546082155e-05, "loss": 1.0507, "step": 513 }, { "epoch": 0.47809878844361603, "loss_cot": 0.5075703859329224, "loss_nocot": 0.6112692356109619, "step": 513 }, { "epoch": 0.4790307548928239, "grad_norm": 0.715452364469079, "learning_rate": 1.8674490852606148e-05, "loss": 1.05, "step": 514 }, { "epoch": 0.4790307548928239, "loss_cot": 0.5604947209358215, "loss_nocot": 0.4226890206336975, "step": 514 }, { "epoch": 0.47996272134203166, "grad_norm": 0.8397149697224546, "learning_rate": 1.8667587159130137e-05, "loss": 1.1082, "step": 515 }, { "epoch": 0.47996272134203166, "loss_cot": 0.5475306510925293, "loss_nocot": 0.39932847023010254, "step": 515 }, { "epoch": 0.4808946877912395, "grad_norm": 0.6601828584329404, "learning_rate": 1.8660683465654126e-05, "loss": 1.0009, "step": 516 }, { "epoch": 0.4808946877912395, "loss_cot": 0.5698971152305603, "loss_nocot": 0.3665863573551178, "step": 516 }, { "epoch": 0.48182665424044735, "grad_norm": 0.7124004420925346, "learning_rate": 1.8653779772178118e-05, "loss": 1.0308, "step": 517 }, { "epoch": 0.48182665424044735, "loss_cot": 0.504848837852478, "loss_nocot": 0.4048410654067993, "step": 517 }, { "epoch": 0.4827586206896552, "grad_norm": 0.6695891661770054, "learning_rate": 1.8646876078702107e-05, "loss": 1.0274, "step": 518 }, { "epoch": 0.4827586206896552, "loss_cot": 0.5444629192352295, "loss_nocot": 0.5573863387107849, "step": 518 }, { "epoch": 0.483690587138863, "grad_norm": 0.6327460014022237, "learning_rate": 1.8639972385226096e-05, "loss": 1.0348, "step": 519 }, { "epoch": 0.483690587138863, "loss_cot": 0.5398765802383423, "loss_nocot": 0.4202582836151123, "step": 519 }, { "epoch": 0.4846225535880708, "grad_norm": 0.6504636968234635, "learning_rate": 1.8633068691750085e-05, "loss": 1.0307, "step": 520 }, { "epoch": 0.4846225535880708, "loss_cot": 0.5673307180404663, "loss_nocot": 0.39550626277923584, "step": 520 }, { "epoch": 0.48555452003727867, "grad_norm": 0.6135798589520528, "learning_rate": 1.8626164998274078e-05, "loss": 0.9505, "step": 521 }, { "epoch": 0.48555452003727867, "loss_cot": 0.5223336219787598, "loss_nocot": 0.4199368953704834, "step": 521 }, { "epoch": 0.4864864864864865, "grad_norm": 0.9302163276214247, "learning_rate": 1.861926130479807e-05, "loss": 1.0646, "step": 522 }, { "epoch": 0.4864864864864865, "loss_cot": 0.49083057045936584, "loss_nocot": 0.6096141338348389, "step": 522 }, { "epoch": 0.4874184529356943, "grad_norm": 0.6622310209783234, "learning_rate": 1.861235761132206e-05, "loss": 1.0841, "step": 523 }, { "epoch": 0.4874184529356943, "loss_cot": 0.6425889730453491, "loss_nocot": 0.49686646461486816, "step": 523 }, { "epoch": 0.48835041938490215, "grad_norm": 0.7284526368338446, "learning_rate": 1.860545391784605e-05, "loss": 1.0547, "step": 524 }, { "epoch": 0.48835041938490215, "loss_cot": 0.5314943790435791, "loss_nocot": 0.5645893812179565, "step": 524 }, { "epoch": 0.48928238583411, "grad_norm": 0.7157252439210171, "learning_rate": 1.859855022437004e-05, "loss": 1.1355, "step": 525 }, { "epoch": 0.48928238583411, "loss_cot": 0.5626823902130127, "loss_nocot": 0.4230518937110901, "step": 525 }, { "epoch": 0.4902143522833178, "grad_norm": 0.6477314286691802, "learning_rate": 1.859164653089403e-05, "loss": 1.0529, "step": 526 }, { "epoch": 0.4902143522833178, "loss_cot": 0.5529187917709351, "loss_nocot": 0.4191989600658417, "step": 526 }, { "epoch": 0.4911463187325256, "grad_norm": 0.7436526405667242, "learning_rate": 1.858474283741802e-05, "loss": 1.0489, "step": 527 }, { "epoch": 0.4911463187325256, "loss_cot": 0.5071412324905396, "loss_nocot": 0.31966209411621094, "step": 527 }, { "epoch": 0.49207828518173347, "grad_norm": 0.6343286809235393, "learning_rate": 1.857783914394201e-05, "loss": 0.9525, "step": 528 }, { "epoch": 0.49207828518173347, "loss_cot": 0.5943031311035156, "loss_nocot": 0.41882407665252686, "step": 528 }, { "epoch": 0.4930102516309413, "grad_norm": 0.678282694626757, "learning_rate": 1.8570935450466e-05, "loss": 1.0043, "step": 529 }, { "epoch": 0.4930102516309413, "loss_cot": 0.5387057065963745, "loss_nocot": 0.42117834091186523, "step": 529 }, { "epoch": 0.4939422180801491, "grad_norm": 0.6733008491511476, "learning_rate": 1.856403175698999e-05, "loss": 1.0202, "step": 530 }, { "epoch": 0.4939422180801491, "loss_cot": 0.5268243551254272, "loss_nocot": 0.3804790675640106, "step": 530 }, { "epoch": 0.49487418452935694, "grad_norm": 0.6509655718819546, "learning_rate": 1.8557128063513982e-05, "loss": 1.0388, "step": 531 }, { "epoch": 0.49487418452935694, "loss_cot": 0.53360515832901, "loss_nocot": 0.40724796056747437, "step": 531 }, { "epoch": 0.4958061509785648, "grad_norm": 0.7286627381228162, "learning_rate": 1.8550224370037974e-05, "loss": 1.0292, "step": 532 }, { "epoch": 0.4958061509785648, "loss_cot": 0.6613810658454895, "loss_nocot": 0.5439943075180054, "step": 532 }, { "epoch": 0.4967381174277726, "grad_norm": 0.6627837981287863, "learning_rate": 1.8543320676561963e-05, "loss": 1.014, "step": 533 }, { "epoch": 0.4967381174277726, "loss_cot": 0.6902511119842529, "loss_nocot": 0.45703548192977905, "step": 533 }, { "epoch": 0.4976700838769804, "grad_norm": 0.7121875532604649, "learning_rate": 1.8536416983085952e-05, "loss": 1.0668, "step": 534 }, { "epoch": 0.4976700838769804, "loss_cot": 0.5419156551361084, "loss_nocot": 0.5689988136291504, "step": 534 }, { "epoch": 0.49860205032618826, "grad_norm": 0.6525656732757998, "learning_rate": 1.8529513289609945e-05, "loss": 0.9711, "step": 535 }, { "epoch": 0.49860205032618826, "loss_cot": 0.527985155582428, "loss_nocot": 0.4375717043876648, "step": 535 }, { "epoch": 0.4995340167753961, "grad_norm": 0.6585980438914049, "learning_rate": 1.8522609596133934e-05, "loss": 1.0067, "step": 536 }, { "epoch": 0.4995340167753961, "loss_cot": 0.5292693376541138, "loss_nocot": 0.4970743656158447, "step": 536 }, { "epoch": 0.5004659832246039, "grad_norm": 0.6284789837397837, "learning_rate": 1.8515705902657923e-05, "loss": 0.9578, "step": 537 }, { "epoch": 0.5004659832246039, "loss_cot": 0.6380079984664917, "loss_nocot": 0.5600184202194214, "step": 537 }, { "epoch": 0.5013979496738118, "grad_norm": 0.6201382747490399, "learning_rate": 1.8508802209181912e-05, "loss": 0.9899, "step": 538 }, { "epoch": 0.5013979496738118, "loss_cot": 0.546416163444519, "loss_nocot": 0.4937698245048523, "step": 538 }, { "epoch": 0.5023299161230196, "grad_norm": 0.6763316000037661, "learning_rate": 1.8501898515705904e-05, "loss": 1.0022, "step": 539 }, { "epoch": 0.5023299161230196, "loss_cot": 0.5297403335571289, "loss_nocot": 0.4154938757419586, "step": 539 }, { "epoch": 0.5032618825722274, "grad_norm": 0.7236805414939171, "learning_rate": 1.8494994822229893e-05, "loss": 1.0139, "step": 540 }, { "epoch": 0.5032618825722274, "loss_cot": 0.5476950407028198, "loss_nocot": 0.36798644065856934, "step": 540 }, { "epoch": 0.5041938490214353, "grad_norm": 0.6265495633820818, "learning_rate": 1.8488091128753886e-05, "loss": 0.9603, "step": 541 }, { "epoch": 0.5041938490214353, "loss_cot": 0.5638449192047119, "loss_nocot": 0.43727147579193115, "step": 541 }, { "epoch": 0.5051258154706431, "grad_norm": 0.6320465676791598, "learning_rate": 1.8481187435277875e-05, "loss": 0.9811, "step": 542 }, { "epoch": 0.5051258154706431, "loss_cot": 0.5252792835235596, "loss_nocot": 0.5227903127670288, "step": 542 }, { "epoch": 0.5060577819198508, "grad_norm": 0.6708085070730637, "learning_rate": 1.8474283741801867e-05, "loss": 0.9925, "step": 543 }, { "epoch": 0.5060577819198508, "loss_cot": 0.5193213820457458, "loss_nocot": 0.4240433871746063, "step": 543 }, { "epoch": 0.5069897483690587, "grad_norm": 0.7458992742955319, "learning_rate": 1.8467380048325856e-05, "loss": 1.005, "step": 544 }, { "epoch": 0.5069897483690587, "loss_cot": 0.512911319732666, "loss_nocot": 0.6595102548599243, "step": 544 }, { "epoch": 0.5079217148182665, "grad_norm": 0.7665190336678851, "learning_rate": 1.8460476354849845e-05, "loss": 1.1205, "step": 545 }, { "epoch": 0.5079217148182665, "loss_cot": 0.5355280637741089, "loss_nocot": 0.4534204602241516, "step": 545 }, { "epoch": 0.5088536812674743, "grad_norm": 0.6965833252497327, "learning_rate": 1.8453572661373838e-05, "loss": 1.0431, "step": 546 }, { "epoch": 0.5088536812674743, "loss_cot": 0.5542032718658447, "loss_nocot": 0.4478801488876343, "step": 546 }, { "epoch": 0.5097856477166822, "grad_norm": 0.6869765369713222, "learning_rate": 1.8446668967897827e-05, "loss": 1.0479, "step": 547 }, { "epoch": 0.5097856477166822, "loss_cot": 0.5105582475662231, "loss_nocot": 0.5079638361930847, "step": 547 }, { "epoch": 0.51071761416589, "grad_norm": 0.6720691690998706, "learning_rate": 1.8439765274421816e-05, "loss": 1.023, "step": 548 }, { "epoch": 0.51071761416589, "loss_cot": 0.5259487628936768, "loss_nocot": 0.3900431990623474, "step": 548 }, { "epoch": 0.5116495806150979, "grad_norm": 0.62017510483177, "learning_rate": 1.8432861580945808e-05, "loss": 0.9997, "step": 549 }, { "epoch": 0.5116495806150979, "loss_cot": 0.5431987047195435, "loss_nocot": 0.5302583575248718, "step": 549 }, { "epoch": 0.5125815470643057, "grad_norm": 0.6844685076141144, "learning_rate": 1.8425957887469797e-05, "loss": 1.034, "step": 550 }, { "epoch": 0.5125815470643057, "loss_cot": 0.5769487023353577, "loss_nocot": 0.4753327965736389, "step": 550 }, { "epoch": 0.5135135135135135, "grad_norm": 0.7257589980607968, "learning_rate": 1.841905419399379e-05, "loss": 1.1042, "step": 551 }, { "epoch": 0.5135135135135135, "loss_cot": 0.4914747178554535, "loss_nocot": 0.4102146625518799, "step": 551 }, { "epoch": 0.5144454799627214, "grad_norm": 0.6431900609963772, "learning_rate": 1.841215050051778e-05, "loss": 0.9638, "step": 552 }, { "epoch": 0.5144454799627214, "loss_cot": 0.4970560669898987, "loss_nocot": 0.3571234345436096, "step": 552 }, { "epoch": 0.5153774464119292, "grad_norm": 0.6273127610389908, "learning_rate": 1.8405246807041768e-05, "loss": 0.9612, "step": 553 }, { "epoch": 0.5153774464119292, "loss_cot": 0.522986888885498, "loss_nocot": 0.5517292618751526, "step": 553 }, { "epoch": 0.516309412861137, "grad_norm": 0.6121945741519276, "learning_rate": 1.839834311356576e-05, "loss": 0.9969, "step": 554 }, { "epoch": 0.516309412861137, "loss_cot": 0.5723692178726196, "loss_nocot": 0.43029630184173584, "step": 554 }, { "epoch": 0.5172413793103449, "grad_norm": 0.6875787404543134, "learning_rate": 1.839143942008975e-05, "loss": 1.0264, "step": 555 }, { "epoch": 0.5172413793103449, "loss_cot": 0.647733747959137, "loss_nocot": 0.372139036655426, "step": 555 }, { "epoch": 0.5181733457595527, "grad_norm": 0.6163131033175487, "learning_rate": 1.8384535726613738e-05, "loss": 1.0111, "step": 556 }, { "epoch": 0.5181733457595527, "loss_cot": 0.5608993768692017, "loss_nocot": 0.3721127510070801, "step": 556 }, { "epoch": 0.5191053122087604, "grad_norm": 0.616737747053428, "learning_rate": 1.837763203313773e-05, "loss": 0.9492, "step": 557 }, { "epoch": 0.5191053122087604, "loss_cot": 0.6562941670417786, "loss_nocot": 0.5137409567832947, "step": 557 }, { "epoch": 0.5200372786579683, "grad_norm": 0.654336536433288, "learning_rate": 1.837072833966172e-05, "loss": 1.0675, "step": 558 }, { "epoch": 0.5200372786579683, "loss_cot": 0.5784489512443542, "loss_nocot": 0.5378357768058777, "step": 558 }, { "epoch": 0.5209692451071761, "grad_norm": 0.7651646379281606, "learning_rate": 1.8363824646185712e-05, "loss": 1.0983, "step": 559 }, { "epoch": 0.5209692451071761, "loss_cot": 0.5622825026512146, "loss_nocot": 0.46415889263153076, "step": 559 }, { "epoch": 0.5219012115563839, "grad_norm": 0.689250011133991, "learning_rate": 1.83569209527097e-05, "loss": 0.9298, "step": 560 }, { "epoch": 0.5219012115563839, "loss_cot": 0.5218905210494995, "loss_nocot": 0.39144599437713623, "step": 560 }, { "epoch": 0.5228331780055918, "grad_norm": 0.6192361143412095, "learning_rate": 1.8350017259233694e-05, "loss": 0.9849, "step": 561 }, { "epoch": 0.5228331780055918, "loss_cot": 0.5240402221679688, "loss_nocot": 0.5342406034469604, "step": 561 }, { "epoch": 0.5237651444547996, "grad_norm": 0.6495281530254425, "learning_rate": 1.8343113565757683e-05, "loss": 1.0315, "step": 562 }, { "epoch": 0.5237651444547996, "loss_cot": 0.5687705874443054, "loss_nocot": 0.4568161368370056, "step": 562 }, { "epoch": 0.5246971109040075, "grad_norm": 0.676639876094301, "learning_rate": 1.833620987228167e-05, "loss": 1.0573, "step": 563 }, { "epoch": 0.5246971109040075, "loss_cot": 0.49226486682891846, "loss_nocot": 0.5001744031906128, "step": 563 }, { "epoch": 0.5256290773532153, "grad_norm": 0.67648455985463, "learning_rate": 1.832930617880566e-05, "loss": 1.0194, "step": 564 }, { "epoch": 0.5256290773532153, "loss_cot": 0.5316097140312195, "loss_nocot": 0.44885390996932983, "step": 564 }, { "epoch": 0.5265610438024231, "grad_norm": 0.6261736501449567, "learning_rate": 1.8322402485329653e-05, "loss": 0.9613, "step": 565 }, { "epoch": 0.5265610438024231, "loss_cot": 0.5943840146064758, "loss_nocot": 0.4085738956928253, "step": 565 }, { "epoch": 0.527493010251631, "grad_norm": 0.6477633429034602, "learning_rate": 1.8315498791853642e-05, "loss": 1.0179, "step": 566 }, { "epoch": 0.527493010251631, "loss_cot": 0.5842931866645813, "loss_nocot": 0.473693311214447, "step": 566 }, { "epoch": 0.5284249767008388, "grad_norm": 0.6734935526696872, "learning_rate": 1.830859509837763e-05, "loss": 1.0665, "step": 567 }, { "epoch": 0.5284249767008388, "loss_cot": 0.551474928855896, "loss_nocot": 0.29826489090919495, "step": 567 }, { "epoch": 0.5293569431500466, "grad_norm": 0.6148625796356935, "learning_rate": 1.8301691404901624e-05, "loss": 0.9432, "step": 568 }, { "epoch": 0.5293569431500466, "loss_cot": 0.457633912563324, "loss_nocot": 1.0271058082580566, "step": 568 }, { "epoch": 0.5302889095992545, "grad_norm": 6.239442270481924, "learning_rate": 1.8294787711425616e-05, "loss": 1.1223, "step": 569 }, { "epoch": 0.5302889095992545, "loss_cot": 0.5416535139083862, "loss_nocot": 0.5508741140365601, "step": 569 }, { "epoch": 0.5312208760484622, "grad_norm": 0.7356011651021435, "learning_rate": 1.8287884017949605e-05, "loss": 1.0655, "step": 570 }, { "epoch": 0.5312208760484622, "loss_cot": 0.5204954147338867, "loss_nocot": 0.3511045277118683, "step": 570 }, { "epoch": 0.53215284249767, "grad_norm": 0.6659403018454149, "learning_rate": 1.8280980324473594e-05, "loss": 0.9706, "step": 571 }, { "epoch": 0.53215284249767, "loss_cot": 0.5735528469085693, "loss_nocot": 0.4985261559486389, "step": 571 }, { "epoch": 0.5330848089468779, "grad_norm": 0.7550379144972852, "learning_rate": 1.8274076630997587e-05, "loss": 1.0434, "step": 572 }, { "epoch": 0.5330848089468779, "loss_cot": 0.6060850620269775, "loss_nocot": 0.4530554413795471, "step": 572 }, { "epoch": 0.5340167753960857, "grad_norm": 0.6402379327828325, "learning_rate": 1.8267172937521576e-05, "loss": 1.0149, "step": 573 }, { "epoch": 0.5340167753960857, "loss_cot": 0.5086386799812317, "loss_nocot": 0.47634077072143555, "step": 573 }, { "epoch": 0.5349487418452936, "grad_norm": 0.8130641750248042, "learning_rate": 1.8260269244045565e-05, "loss": 1.1017, "step": 574 }, { "epoch": 0.5349487418452936, "loss_cot": 0.4976082444190979, "loss_nocot": 0.3855517506599426, "step": 574 }, { "epoch": 0.5358807082945014, "grad_norm": 0.6442052243053392, "learning_rate": 1.8253365550569557e-05, "loss": 1.025, "step": 575 }, { "epoch": 0.5358807082945014, "loss_cot": 0.5187210440635681, "loss_nocot": 0.5899454355239868, "step": 575 }, { "epoch": 0.5368126747437092, "grad_norm": 1.147000020167267, "learning_rate": 1.8246461857093546e-05, "loss": 1.0255, "step": 576 }, { "epoch": 0.5368126747437092, "loss_cot": 0.5387892127037048, "loss_nocot": 0.40586310625076294, "step": 576 }, { "epoch": 0.5377446411929171, "grad_norm": 0.5569441444287991, "learning_rate": 1.8239558163617535e-05, "loss": 0.9137, "step": 577 }, { "epoch": 0.5377446411929171, "loss_cot": 0.5257259607315063, "loss_nocot": 0.5157747268676758, "step": 577 }, { "epoch": 0.5386766076421249, "grad_norm": 0.8619816642678052, "learning_rate": 1.8232654470141528e-05, "loss": 1.0526, "step": 578 }, { "epoch": 0.5386766076421249, "loss_cot": 0.5791293382644653, "loss_nocot": 0.4865422248840332, "step": 578 }, { "epoch": 0.5396085740913327, "grad_norm": 0.6933161783903874, "learning_rate": 1.822575077666552e-05, "loss": 1.0256, "step": 579 }, { "epoch": 0.5396085740913327, "loss_cot": 0.5656838417053223, "loss_nocot": 0.471432089805603, "step": 579 }, { "epoch": 0.5405405405405406, "grad_norm": 0.8436438878714205, "learning_rate": 1.821884708318951e-05, "loss": 1.0174, "step": 580 }, { "epoch": 0.5405405405405406, "loss_cot": 0.5551379919052124, "loss_nocot": 0.4902379512786865, "step": 580 }, { "epoch": 0.5414725069897484, "grad_norm": 0.6254813333994393, "learning_rate": 1.8211943389713498e-05, "loss": 1.0017, "step": 581 }, { "epoch": 0.5414725069897484, "loss_cot": 0.6255195140838623, "loss_nocot": 0.43881797790527344, "step": 581 }, { "epoch": 0.5424044734389561, "grad_norm": 0.6768408853860254, "learning_rate": 1.8205039696237487e-05, "loss": 1.0726, "step": 582 }, { "epoch": 0.5424044734389561, "loss_cot": 0.5583902597427368, "loss_nocot": 0.4120289087295532, "step": 582 }, { "epoch": 0.543336439888164, "grad_norm": 0.6435428638159074, "learning_rate": 1.819813600276148e-05, "loss": 0.9705, "step": 583 }, { "epoch": 0.543336439888164, "loss_cot": 0.5729960203170776, "loss_nocot": 0.33658552169799805, "step": 583 }, { "epoch": 0.5442684063373718, "grad_norm": 0.6434215895630202, "learning_rate": 1.819123230928547e-05, "loss": 1.0218, "step": 584 }, { "epoch": 0.5442684063373718, "loss_cot": 0.518886387348175, "loss_nocot": 0.5032491683959961, "step": 584 }, { "epoch": 0.5452003727865797, "grad_norm": 0.7170149709901205, "learning_rate": 1.8184328615809458e-05, "loss": 0.9969, "step": 585 }, { "epoch": 0.5452003727865797, "loss_cot": 0.5171257257461548, "loss_nocot": 0.5533331632614136, "step": 585 }, { "epoch": 0.5461323392357875, "grad_norm": 0.6995650340309503, "learning_rate": 1.817742492233345e-05, "loss": 1.0674, "step": 586 }, { "epoch": 0.5461323392357875, "loss_cot": 0.5183802843093872, "loss_nocot": 0.5022509098052979, "step": 586 }, { "epoch": 0.5470643056849953, "grad_norm": 0.6213518083962929, "learning_rate": 1.817052122885744e-05, "loss": 0.9784, "step": 587 }, { "epoch": 0.5470643056849953, "loss_cot": 0.5108910202980042, "loss_nocot": 0.41367506980895996, "step": 587 }, { "epoch": 0.5479962721342032, "grad_norm": 0.6362374567272091, "learning_rate": 1.816361753538143e-05, "loss": 0.966, "step": 588 }, { "epoch": 0.5479962721342032, "loss_cot": 0.5919803977012634, "loss_nocot": 0.4468863308429718, "step": 588 }, { "epoch": 0.548928238583411, "grad_norm": 0.6376702068762012, "learning_rate": 1.815671384190542e-05, "loss": 1.0333, "step": 589 }, { "epoch": 0.548928238583411, "loss_cot": 0.5390002727508545, "loss_nocot": 0.526030421257019, "step": 589 }, { "epoch": 0.5498602050326188, "grad_norm": 0.6955185093398308, "learning_rate": 1.8149810148429413e-05, "loss": 1.0226, "step": 590 }, { "epoch": 0.5498602050326188, "loss_cot": 0.5307592153549194, "loss_nocot": 0.5099111795425415, "step": 590 }, { "epoch": 0.5507921714818267, "grad_norm": 0.6694544290084625, "learning_rate": 1.8142906454953402e-05, "loss": 1.0309, "step": 591 }, { "epoch": 0.5507921714818267, "loss_cot": 0.505524218082428, "loss_nocot": 0.5518564581871033, "step": 591 }, { "epoch": 0.5517241379310345, "grad_norm": 0.6951272153173295, "learning_rate": 1.813600276147739e-05, "loss": 1.0098, "step": 592 }, { "epoch": 0.5517241379310345, "loss_cot": 0.5509015917778015, "loss_nocot": 0.44483649730682373, "step": 592 }, { "epoch": 0.5526561043802423, "grad_norm": 0.6413944153731003, "learning_rate": 1.812909906800138e-05, "loss": 0.9855, "step": 593 }, { "epoch": 0.5526561043802423, "loss_cot": 0.6054931282997131, "loss_nocot": 0.5347986221313477, "step": 593 }, { "epoch": 0.5535880708294502, "grad_norm": 0.6315388357965218, "learning_rate": 1.8122195374525372e-05, "loss": 0.9914, "step": 594 }, { "epoch": 0.5535880708294502, "loss_cot": 0.6468380093574524, "loss_nocot": 0.515294075012207, "step": 594 }, { "epoch": 0.554520037278658, "grad_norm": 0.621583914826794, "learning_rate": 1.811529168104936e-05, "loss": 1.0031, "step": 595 }, { "epoch": 0.554520037278658, "loss_cot": 0.4825809895992279, "loss_nocot": 0.6313289403915405, "step": 595 }, { "epoch": 0.5554520037278659, "grad_norm": 0.7764389783357369, "learning_rate": 1.8108387987573354e-05, "loss": 1.0536, "step": 596 }, { "epoch": 0.5554520037278659, "loss_cot": 0.5734590888023376, "loss_nocot": 0.4452076554298401, "step": 596 }, { "epoch": 0.5563839701770736, "grad_norm": 0.6785135117188105, "learning_rate": 1.8101484294097343e-05, "loss": 0.994, "step": 597 }, { "epoch": 0.5563839701770736, "loss_cot": 0.5773146152496338, "loss_nocot": 0.3848051428794861, "step": 597 }, { "epoch": 0.5573159366262814, "grad_norm": 0.6527367980682081, "learning_rate": 1.8094580600621335e-05, "loss": 1.0454, "step": 598 }, { "epoch": 0.5573159366262814, "loss_cot": 0.5447382926940918, "loss_nocot": 0.3767865300178528, "step": 598 }, { "epoch": 0.5582479030754893, "grad_norm": 0.7077720601045603, "learning_rate": 1.8087676907145324e-05, "loss": 1.0695, "step": 599 }, { "epoch": 0.5582479030754893, "loss_cot": 0.5086944103240967, "loss_nocot": 0.4596547782421112, "step": 599 }, { "epoch": 0.5591798695246971, "grad_norm": 0.63767098362101, "learning_rate": 1.8080773213669313e-05, "loss": 1.0078, "step": 600 }, { "epoch": 0.5591798695246971, "loss_cot": 0.5522834658622742, "loss_nocot": 0.4662061631679535, "step": 600 }, { "epoch": 0.5601118359739049, "grad_norm": 0.6101208407038267, "learning_rate": 1.8073869520193306e-05, "loss": 0.9569, "step": 601 }, { "epoch": 0.5601118359739049, "loss_cot": 0.5604706406593323, "loss_nocot": 0.39899060130119324, "step": 601 }, { "epoch": 0.5610438024231128, "grad_norm": 0.6910023886430201, "learning_rate": 1.8066965826717295e-05, "loss": 1.0344, "step": 602 }, { "epoch": 0.5610438024231128, "loss_cot": 0.609375, "loss_nocot": 0.3528956174850464, "step": 602 }, { "epoch": 0.5619757688723206, "grad_norm": 0.6291003076551718, "learning_rate": 1.8060062133241284e-05, "loss": 0.9902, "step": 603 }, { "epoch": 0.5619757688723206, "loss_cot": 0.5215955376625061, "loss_nocot": 0.47169390320777893, "step": 603 }, { "epoch": 0.5629077353215284, "grad_norm": 0.6230718104528844, "learning_rate": 1.8053158439765276e-05, "loss": 0.9708, "step": 604 }, { "epoch": 0.5629077353215284, "loss_cot": 0.49844104051589966, "loss_nocot": 0.29298532009124756, "step": 604 }, { "epoch": 0.5638397017707363, "grad_norm": 0.6345770285103461, "learning_rate": 1.8046254746289265e-05, "loss": 0.9278, "step": 605 }, { "epoch": 0.5638397017707363, "loss_cot": 0.5572748184204102, "loss_nocot": 0.43107908964157104, "step": 605 }, { "epoch": 0.5647716682199441, "grad_norm": 0.6887536145219223, "learning_rate": 1.8039351052813258e-05, "loss": 1.0822, "step": 606 }, { "epoch": 0.5647716682199441, "loss_cot": 0.5617218613624573, "loss_nocot": 0.44408172369003296, "step": 606 }, { "epoch": 0.5657036346691519, "grad_norm": 0.6117732252726525, "learning_rate": 1.8032447359337247e-05, "loss": 0.9648, "step": 607 }, { "epoch": 0.5657036346691519, "loss_cot": 0.5816943049430847, "loss_nocot": 0.36375588178634644, "step": 607 }, { "epoch": 0.5666356011183598, "grad_norm": 0.6441167115410041, "learning_rate": 1.802554366586124e-05, "loss": 0.9999, "step": 608 }, { "epoch": 0.5666356011183598, "loss_cot": 0.5715529918670654, "loss_nocot": 0.530497670173645, "step": 608 }, { "epoch": 0.5675675675675675, "grad_norm": 0.6237859388265843, "learning_rate": 1.801863997238523e-05, "loss": 1.0043, "step": 609 }, { "epoch": 0.5675675675675675, "loss_cot": 0.4999042749404907, "loss_nocot": 0.5277514457702637, "step": 609 }, { "epoch": 0.5684995340167754, "grad_norm": 0.7334659303161426, "learning_rate": 1.8011736278909217e-05, "loss": 1.0037, "step": 610 }, { "epoch": 0.5684995340167754, "loss_cot": 0.5597009062767029, "loss_nocot": 0.35767167806625366, "step": 610 }, { "epoch": 0.5694315004659832, "grad_norm": 0.6655394038273708, "learning_rate": 1.8004832585433206e-05, "loss": 1.0416, "step": 611 }, { "epoch": 0.5694315004659832, "loss_cot": 0.5148113965988159, "loss_nocot": 0.5438401699066162, "step": 611 }, { "epoch": 0.570363466915191, "grad_norm": 0.698595957490179, "learning_rate": 1.79979288919572e-05, "loss": 1.0216, "step": 612 }, { "epoch": 0.570363466915191, "loss_cot": 0.5323963761329651, "loss_nocot": 0.39111629128456116, "step": 612 }, { "epoch": 0.5712954333643989, "grad_norm": 0.6756727430361152, "learning_rate": 1.7991025198481188e-05, "loss": 1.0654, "step": 613 }, { "epoch": 0.5712954333643989, "loss_cot": 0.5036591291427612, "loss_nocot": 0.39678338170051575, "step": 613 }, { "epoch": 0.5722273998136067, "grad_norm": 0.6649836505654304, "learning_rate": 1.798412150500518e-05, "loss": 0.9937, "step": 614 }, { "epoch": 0.5722273998136067, "loss_cot": 0.5526018142700195, "loss_nocot": 0.44578978419303894, "step": 614 }, { "epoch": 0.5731593662628145, "grad_norm": 0.6576850471474228, "learning_rate": 1.797721781152917e-05, "loss": 1.0017, "step": 615 }, { "epoch": 0.5731593662628145, "loss_cot": 0.5367957353591919, "loss_nocot": 0.44042620062828064, "step": 615 }, { "epoch": 0.5740913327120224, "grad_norm": 0.5669518510056226, "learning_rate": 1.7970314118053162e-05, "loss": 0.9472, "step": 616 }, { "epoch": 0.5740913327120224, "loss_cot": 0.5567467212677002, "loss_nocot": 0.43512165546417236, "step": 616 }, { "epoch": 0.5750232991612302, "grad_norm": 0.5856253443208378, "learning_rate": 1.796341042457715e-05, "loss": 0.9565, "step": 617 }, { "epoch": 0.5750232991612302, "loss_cot": 0.5493724346160889, "loss_nocot": 0.5970170497894287, "step": 617 }, { "epoch": 0.575955265610438, "grad_norm": 0.6790780109553621, "learning_rate": 1.795650673110114e-05, "loss": 1.0032, "step": 618 }, { "epoch": 0.575955265610438, "loss_cot": 0.5635700821876526, "loss_nocot": 0.36949223279953003, "step": 618 }, { "epoch": 0.5768872320596459, "grad_norm": 0.6448878798533165, "learning_rate": 1.7949603037625132e-05, "loss": 1.0266, "step": 619 }, { "epoch": 0.5768872320596459, "loss_cot": 0.5320090651512146, "loss_nocot": 0.4452242851257324, "step": 619 }, { "epoch": 0.5778191985088537, "grad_norm": 0.6562190689544791, "learning_rate": 1.794269934414912e-05, "loss": 1.0092, "step": 620 }, { "epoch": 0.5778191985088537, "loss_cot": 0.5559424161911011, "loss_nocot": 0.43495476245880127, "step": 620 }, { "epoch": 0.5787511649580616, "grad_norm": 0.6407155771866214, "learning_rate": 1.793579565067311e-05, "loss": 1.031, "step": 621 }, { "epoch": 0.5787511649580616, "loss_cot": 0.5398285388946533, "loss_nocot": 0.48884445428848267, "step": 621 }, { "epoch": 0.5796831314072693, "grad_norm": 0.6402995996159955, "learning_rate": 1.79288919571971e-05, "loss": 1.0116, "step": 622 }, { "epoch": 0.5796831314072693, "loss_cot": 0.5553011298179626, "loss_nocot": 0.2916925251483917, "step": 622 }, { "epoch": 0.5806150978564771, "grad_norm": 0.5915161581957201, "learning_rate": 1.7921988263721092e-05, "loss": 0.9403, "step": 623 }, { "epoch": 0.5806150978564771, "loss_cot": 0.584338903427124, "loss_nocot": 0.5132250785827637, "step": 623 }, { "epoch": 0.581547064305685, "grad_norm": 0.7194483963132711, "learning_rate": 1.7915084570245084e-05, "loss": 1.0085, "step": 624 }, { "epoch": 0.581547064305685, "loss_cot": 0.6156867742538452, "loss_nocot": 0.45346471667289734, "step": 624 }, { "epoch": 0.5824790307548928, "grad_norm": 0.6874796533751155, "learning_rate": 1.7908180876769073e-05, "loss": 1.0182, "step": 625 }, { "epoch": 0.5824790307548928, "loss_cot": 0.5643149018287659, "loss_nocot": 0.4474630355834961, "step": 625 }, { "epoch": 0.5834109972041006, "grad_norm": 0.636141213257686, "learning_rate": 1.7901277183293066e-05, "loss": 1.0158, "step": 626 }, { "epoch": 0.5834109972041006, "loss_cot": 0.6451801657676697, "loss_nocot": 0.7425605058670044, "step": 626 }, { "epoch": 0.5843429636533085, "grad_norm": 0.7983206862964888, "learning_rate": 1.7894373489817055e-05, "loss": 1.1629, "step": 627 }, { "epoch": 0.5843429636533085, "loss_cot": 0.5318068265914917, "loss_nocot": 0.3864758312702179, "step": 627 }, { "epoch": 0.5852749301025163, "grad_norm": 0.6396481420645188, "learning_rate": 1.7887469796341044e-05, "loss": 1.0273, "step": 628 }, { "epoch": 0.5852749301025163, "loss_cot": 0.5599919557571411, "loss_nocot": 0.46779927611351013, "step": 628 }, { "epoch": 0.5862068965517241, "grad_norm": 0.6292288257937428, "learning_rate": 1.7880566102865033e-05, "loss": 0.9724, "step": 629 }, { "epoch": 0.5862068965517241, "loss_cot": 0.49311187863349915, "loss_nocot": 0.45764976739883423, "step": 629 }, { "epoch": 0.587138863000932, "grad_norm": 0.6970423443048561, "learning_rate": 1.7873662409389025e-05, "loss": 1.0348, "step": 630 }, { "epoch": 0.587138863000932, "loss_cot": 0.5729870796203613, "loss_nocot": 0.5566900968551636, "step": 630 }, { "epoch": 0.5880708294501398, "grad_norm": 0.8319211216249471, "learning_rate": 1.7866758715913014e-05, "loss": 1.0472, "step": 631 }, { "epoch": 0.5880708294501398, "loss_cot": 0.5693645477294922, "loss_nocot": 0.4176635146141052, "step": 631 }, { "epoch": 0.5890027958993477, "grad_norm": 0.6993096108808508, "learning_rate": 1.7859855022437003e-05, "loss": 1.0391, "step": 632 }, { "epoch": 0.5890027958993477, "loss_cot": 0.5420637726783752, "loss_nocot": 0.5212006568908691, "step": 632 }, { "epoch": 0.5899347623485555, "grad_norm": 0.6694346482050293, "learning_rate": 1.7852951328960996e-05, "loss": 1.034, "step": 633 }, { "epoch": 0.5899347623485555, "loss_cot": 0.5599693059921265, "loss_nocot": 0.47369396686553955, "step": 633 }, { "epoch": 0.5908667287977633, "grad_norm": 0.5982819737283657, "learning_rate": 1.7846047635484988e-05, "loss": 1.0136, "step": 634 }, { "epoch": 0.5908667287977633, "loss_cot": 0.5236194133758545, "loss_nocot": 0.43813610076904297, "step": 634 }, { "epoch": 0.5917986952469712, "grad_norm": 0.698131478571763, "learning_rate": 1.7839143942008977e-05, "loss": 1.0005, "step": 635 }, { "epoch": 0.5917986952469712, "loss_cot": 0.5202159285545349, "loss_nocot": 0.5586469173431396, "step": 635 }, { "epoch": 0.5927306616961789, "grad_norm": 0.6633920747983125, "learning_rate": 1.7832240248532966e-05, "loss": 0.9973, "step": 636 }, { "epoch": 0.5927306616961789, "loss_cot": 0.5509973168373108, "loss_nocot": 0.47308605909347534, "step": 636 }, { "epoch": 0.5936626281453867, "grad_norm": 0.6614587750779936, "learning_rate": 1.782533655505696e-05, "loss": 1.0443, "step": 637 }, { "epoch": 0.5936626281453867, "loss_cot": 0.5642670392990112, "loss_nocot": 0.3922789990901947, "step": 637 }, { "epoch": 0.5945945945945946, "grad_norm": 0.6604817365202762, "learning_rate": 1.7818432861580948e-05, "loss": 0.943, "step": 638 }, { "epoch": 0.5945945945945946, "loss_cot": 0.6317489147186279, "loss_nocot": 0.46925339102745056, "step": 638 }, { "epoch": 0.5955265610438024, "grad_norm": 0.6447360742643719, "learning_rate": 1.7811529168104937e-05, "loss": 1.0159, "step": 639 }, { "epoch": 0.5955265610438024, "loss_cot": 0.5175796151161194, "loss_nocot": 0.5400874614715576, "step": 639 }, { "epoch": 0.5964585274930102, "grad_norm": 0.6808376635433003, "learning_rate": 1.7804625474628926e-05, "loss": 1.0528, "step": 640 }, { "epoch": 0.5964585274930102, "loss_cot": 0.5113701820373535, "loss_nocot": 0.4301511347293854, "step": 640 }, { "epoch": 0.5973904939422181, "grad_norm": 0.6554507376858321, "learning_rate": 1.7797721781152918e-05, "loss": 1.0196, "step": 641 }, { "epoch": 0.5973904939422181, "loss_cot": 0.6279122829437256, "loss_nocot": 0.4820648431777954, "step": 641 }, { "epoch": 0.5983224603914259, "grad_norm": 0.6670178941290339, "learning_rate": 1.7790818087676907e-05, "loss": 1.0864, "step": 642 }, { "epoch": 0.5983224603914259, "loss_cot": 0.6114934682846069, "loss_nocot": 0.478590190410614, "step": 642 }, { "epoch": 0.5992544268406338, "grad_norm": 0.6306324115111109, "learning_rate": 1.77839143942009e-05, "loss": 0.9948, "step": 643 }, { "epoch": 0.5992544268406338, "loss_cot": 0.506532609462738, "loss_nocot": 0.41970276832580566, "step": 643 }, { "epoch": 0.6001863932898416, "grad_norm": 0.6030901774431783, "learning_rate": 1.777701070072489e-05, "loss": 0.9553, "step": 644 }, { "epoch": 0.6001863932898416, "loss_cot": 0.5348023176193237, "loss_nocot": 0.46014028787612915, "step": 644 }, { "epoch": 0.6011183597390494, "grad_norm": 0.6827850645502641, "learning_rate": 1.777010700724888e-05, "loss": 1.0524, "step": 645 }, { "epoch": 0.6011183597390494, "loss_cot": 0.5686062574386597, "loss_nocot": 0.5228707790374756, "step": 645 }, { "epoch": 0.6020503261882573, "grad_norm": 0.6905922031446022, "learning_rate": 1.776320331377287e-05, "loss": 1.0858, "step": 646 }, { "epoch": 0.6020503261882573, "loss_cot": 0.6216949224472046, "loss_nocot": 0.39891698956489563, "step": 646 }, { "epoch": 0.6029822926374651, "grad_norm": 0.6635790225148924, "learning_rate": 1.775629962029686e-05, "loss": 1.0015, "step": 647 }, { "epoch": 0.6029822926374651, "loss_cot": 0.5882577896118164, "loss_nocot": 0.48222842812538147, "step": 647 }, { "epoch": 0.6039142590866728, "grad_norm": 0.6493962527616524, "learning_rate": 1.774939592682085e-05, "loss": 1.0795, "step": 648 }, { "epoch": 0.6039142590866728, "loss_cot": 0.48517414927482605, "loss_nocot": 0.4576171934604645, "step": 648 }, { "epoch": 0.6048462255358807, "grad_norm": 0.6934512912139248, "learning_rate": 1.774249223334484e-05, "loss": 1.0364, "step": 649 }, { "epoch": 0.6048462255358807, "loss_cot": 0.6353992223739624, "loss_nocot": 0.5514155030250549, "step": 649 }, { "epoch": 0.6057781919850885, "grad_norm": 0.6452473885434532, "learning_rate": 1.773558853986883e-05, "loss": 1.0084, "step": 650 }, { "epoch": 0.6057781919850885, "loss_cot": 0.5694332122802734, "loss_nocot": 0.47148633003234863, "step": 650 }, { "epoch": 0.6067101584342963, "grad_norm": 0.6730830443395351, "learning_rate": 1.7728684846392822e-05, "loss": 1.0535, "step": 651 }, { "epoch": 0.6067101584342963, "loss_cot": 0.5860759615898132, "loss_nocot": 0.4961560368537903, "step": 651 }, { "epoch": 0.6076421248835042, "grad_norm": 0.6168028485818846, "learning_rate": 1.772178115291681e-05, "loss": 0.9987, "step": 652 }, { "epoch": 0.6076421248835042, "loss_cot": 0.5409771203994751, "loss_nocot": 0.34122562408447266, "step": 652 }, { "epoch": 0.608574091332712, "grad_norm": 0.7018862294878097, "learning_rate": 1.7714877459440804e-05, "loss": 1.0081, "step": 653 }, { "epoch": 0.608574091332712, "loss_cot": 0.5105561017990112, "loss_nocot": 0.4147820770740509, "step": 653 }, { "epoch": 0.6095060577819198, "grad_norm": 0.5988743526833392, "learning_rate": 1.7707973765964793e-05, "loss": 0.9491, "step": 654 }, { "epoch": 0.6095060577819198, "loss_cot": 0.5267541408538818, "loss_nocot": 0.47634944319725037, "step": 654 }, { "epoch": 0.6104380242311277, "grad_norm": 0.6674248218469714, "learning_rate": 1.7701070072488782e-05, "loss": 1.0571, "step": 655 }, { "epoch": 0.6104380242311277, "loss_cot": 0.5709696412086487, "loss_nocot": 0.46413928270339966, "step": 655 }, { "epoch": 0.6113699906803355, "grad_norm": 0.6338944793638152, "learning_rate": 1.7694166379012774e-05, "loss": 0.9936, "step": 656 }, { "epoch": 0.6113699906803355, "loss_cot": 0.6031991839408875, "loss_nocot": 0.5724109411239624, "step": 656 }, { "epoch": 0.6123019571295434, "grad_norm": 26.279816786537065, "learning_rate": 1.7687262685536763e-05, "loss": 1.3658, "step": 657 }, { "epoch": 0.6123019571295434, "loss_cot": 0.5194910764694214, "loss_nocot": 0.4498651623725891, "step": 657 }, { "epoch": 0.6132339235787512, "grad_norm": 0.6216887987301899, "learning_rate": 1.7680358992060752e-05, "loss": 0.9718, "step": 658 }, { "epoch": 0.6132339235787512, "loss_cot": 0.4351022243499756, "loss_nocot": 0.5644389986991882, "step": 658 }, { "epoch": 0.614165890027959, "grad_norm": 0.7246705734092734, "learning_rate": 1.7673455298584745e-05, "loss": 1.0545, "step": 659 }, { "epoch": 0.614165890027959, "loss_cot": 0.5624748468399048, "loss_nocot": 0.39841726422309875, "step": 659 }, { "epoch": 0.6150978564771669, "grad_norm": 0.5730141993039858, "learning_rate": 1.7666551605108734e-05, "loss": 0.9412, "step": 660 }, { "epoch": 0.6150978564771669, "loss_cot": 0.4973410964012146, "loss_nocot": 0.4055781364440918, "step": 660 }, { "epoch": 0.6160298229263746, "grad_norm": 0.6779583418031856, "learning_rate": 1.7659647911632726e-05, "loss": 0.9779, "step": 661 }, { "epoch": 0.6160298229263746, "loss_cot": 0.49826887249946594, "loss_nocot": 0.6517941355705261, "step": 661 }, { "epoch": 0.6169617893755824, "grad_norm": 0.7781885222290638, "learning_rate": 1.7652744218156715e-05, "loss": 1.0893, "step": 662 }, { "epoch": 0.6169617893755824, "loss_cot": 0.5984795093536377, "loss_nocot": 0.45937490463256836, "step": 662 }, { "epoch": 0.6178937558247903, "grad_norm": 0.6177090296516209, "learning_rate": 1.7645840524680708e-05, "loss": 0.9743, "step": 663 }, { "epoch": 0.6178937558247903, "loss_cot": 0.5874831676483154, "loss_nocot": 0.49768126010894775, "step": 663 }, { "epoch": 0.6188257222739981, "grad_norm": 0.7588796858589489, "learning_rate": 1.7638936831204697e-05, "loss": 1.0885, "step": 664 }, { "epoch": 0.6188257222739981, "loss_cot": 0.5584537982940674, "loss_nocot": 0.438529908657074, "step": 664 }, { "epoch": 0.6197576887232059, "grad_norm": 0.6502028922086487, "learning_rate": 1.7632033137728686e-05, "loss": 1.0062, "step": 665 }, { "epoch": 0.6197576887232059, "loss_cot": 0.5846806168556213, "loss_nocot": 0.6793445348739624, "step": 665 }, { "epoch": 0.6206896551724138, "grad_norm": 0.6459847919054237, "learning_rate": 1.7625129444252678e-05, "loss": 0.9893, "step": 666 }, { "epoch": 0.6206896551724138, "loss_cot": 0.5160149335861206, "loss_nocot": 0.7958307266235352, "step": 666 }, { "epoch": 0.6216216216216216, "grad_norm": 0.7025951794591915, "learning_rate": 1.7618225750776667e-05, "loss": 1.0783, "step": 667 }, { "epoch": 0.6216216216216216, "loss_cot": 0.5361835956573486, "loss_nocot": 0.3381633162498474, "step": 667 }, { "epoch": 0.6225535880708295, "grad_norm": 0.6556605848056781, "learning_rate": 1.7611322057300656e-05, "loss": 0.9678, "step": 668 }, { "epoch": 0.6225535880708295, "loss_cot": 0.5752128958702087, "loss_nocot": 0.46292388439178467, "step": 668 }, { "epoch": 0.6234855545200373, "grad_norm": 0.6459980867340631, "learning_rate": 1.7604418363824645e-05, "loss": 1.0031, "step": 669 }, { "epoch": 0.6234855545200373, "loss_cot": 0.5728644728660583, "loss_nocot": 0.5029004812240601, "step": 669 }, { "epoch": 0.6244175209692451, "grad_norm": 0.7090936849679894, "learning_rate": 1.7597514670348638e-05, "loss": 1.0333, "step": 670 }, { "epoch": 0.6244175209692451, "loss_cot": 0.6004677414894104, "loss_nocot": 0.4955626130104065, "step": 670 }, { "epoch": 0.625349487418453, "grad_norm": 0.7281294246511761, "learning_rate": 1.759061097687263e-05, "loss": 1.1357, "step": 671 }, { "epoch": 0.625349487418453, "loss_cot": 0.5240557193756104, "loss_nocot": 0.3674253821372986, "step": 671 }, { "epoch": 0.6262814538676608, "grad_norm": 0.602515283574493, "learning_rate": 1.758370728339662e-05, "loss": 0.9775, "step": 672 }, { "epoch": 0.6262814538676608, "loss_cot": 0.5020172595977783, "loss_nocot": 0.440790593624115, "step": 672 }, { "epoch": 0.6272134203168686, "grad_norm": 0.6415498710502944, "learning_rate": 1.7576803589920608e-05, "loss": 1.0407, "step": 673 }, { "epoch": 0.6272134203168686, "loss_cot": 0.46620869636535645, "loss_nocot": 0.5272612571716309, "step": 673 }, { "epoch": 0.6281453867660765, "grad_norm": 0.6382607505749208, "learning_rate": 1.75698998964446e-05, "loss": 1.0042, "step": 674 }, { "epoch": 0.6281453867660765, "loss_cot": 0.5598251819610596, "loss_nocot": 0.41252434253692627, "step": 674 }, { "epoch": 0.6290773532152842, "grad_norm": 0.6552946601507003, "learning_rate": 1.756299620296859e-05, "loss": 0.9898, "step": 675 }, { "epoch": 0.6290773532152842, "loss_cot": 0.5841503739356995, "loss_nocot": 0.4235111474990845, "step": 675 }, { "epoch": 0.630009319664492, "grad_norm": 0.6725910300537338, "learning_rate": 1.755609250949258e-05, "loss": 1.0116, "step": 676 }, { "epoch": 0.630009319664492, "loss_cot": 0.5429768562316895, "loss_nocot": 0.33194971084594727, "step": 676 }, { "epoch": 0.6309412861136999, "grad_norm": 0.6288131254513679, "learning_rate": 1.754918881601657e-05, "loss": 0.9999, "step": 677 }, { "epoch": 0.6309412861136999, "loss_cot": 0.5429542064666748, "loss_nocot": 0.49511468410491943, "step": 677 }, { "epoch": 0.6318732525629077, "grad_norm": 0.6221590464765852, "learning_rate": 1.754228512254056e-05, "loss": 0.9844, "step": 678 }, { "epoch": 0.6318732525629077, "loss_cot": 0.5367998480796814, "loss_nocot": 0.4660998284816742, "step": 678 }, { "epoch": 0.6328052190121156, "grad_norm": 0.6018339473302462, "learning_rate": 1.753538142906455e-05, "loss": 0.9872, "step": 679 }, { "epoch": 0.6328052190121156, "loss_cot": 0.6188504099845886, "loss_nocot": 0.43700969219207764, "step": 679 }, { "epoch": 0.6337371854613234, "grad_norm": 0.6709338918991207, "learning_rate": 1.752847773558854e-05, "loss": 1.0346, "step": 680 }, { "epoch": 0.6337371854613234, "loss_cot": 0.5541263818740845, "loss_nocot": 0.4213048219680786, "step": 680 }, { "epoch": 0.6346691519105312, "grad_norm": 0.6711555433558724, "learning_rate": 1.7521574042112534e-05, "loss": 1.0442, "step": 681 }, { "epoch": 0.6346691519105312, "loss_cot": 0.5683122873306274, "loss_nocot": 0.35602158308029175, "step": 681 }, { "epoch": 0.6356011183597391, "grad_norm": 0.6175521936882751, "learning_rate": 1.7514670348636523e-05, "loss": 0.9292, "step": 682 }, { "epoch": 0.6356011183597391, "loss_cot": 0.5788356065750122, "loss_nocot": 0.3352218270301819, "step": 682 }, { "epoch": 0.6365330848089469, "grad_norm": 0.6236823616345663, "learning_rate": 1.7507766655160512e-05, "loss": 1.0071, "step": 683 }, { "epoch": 0.6365330848089469, "loss_cot": 0.5680866241455078, "loss_nocot": 0.5141556859016418, "step": 683 }, { "epoch": 0.6374650512581547, "grad_norm": 0.6958308355076518, "learning_rate": 1.75008629616845e-05, "loss": 1.0565, "step": 684 }, { "epoch": 0.6374650512581547, "loss_cot": 0.5754789710044861, "loss_nocot": 0.636256992816925, "step": 684 }, { "epoch": 0.6383970177073626, "grad_norm": 0.6824968693901619, "learning_rate": 1.7493959268208494e-05, "loss": 1.0593, "step": 685 }, { "epoch": 0.6383970177073626, "loss_cot": 0.5640847682952881, "loss_nocot": 0.45294925570487976, "step": 685 }, { "epoch": 0.6393289841565704, "grad_norm": 0.7372290536319228, "learning_rate": 1.7487055574732483e-05, "loss": 1.0488, "step": 686 }, { "epoch": 0.6393289841565704, "loss_cot": 0.5438417792320251, "loss_nocot": 0.7279820442199707, "step": 686 }, { "epoch": 0.6402609506057781, "grad_norm": 0.7590017756518728, "learning_rate": 1.748015188125647e-05, "loss": 1.1201, "step": 687 }, { "epoch": 0.6402609506057781, "loss_cot": 0.5908122062683105, "loss_nocot": 0.3920428156852722, "step": 687 }, { "epoch": 0.641192917054986, "grad_norm": 0.7282891726605947, "learning_rate": 1.7473248187780464e-05, "loss": 0.9698, "step": 688 }, { "epoch": 0.641192917054986, "loss_cot": 0.4852495491504669, "loss_nocot": 0.5280472040176392, "step": 688 }, { "epoch": 0.6421248835041938, "grad_norm": 0.6922041588786019, "learning_rate": 1.7466344494304453e-05, "loss": 1.0584, "step": 689 }, { "epoch": 0.6421248835041938, "loss_cot": 0.4994623064994812, "loss_nocot": 0.41783463954925537, "step": 689 }, { "epoch": 0.6430568499534017, "grad_norm": 0.6607498201540257, "learning_rate": 1.7459440800828446e-05, "loss": 0.946, "step": 690 }, { "epoch": 0.6430568499534017, "loss_cot": 0.5863887071609497, "loss_nocot": 0.3155795931816101, "step": 690 }, { "epoch": 0.6439888164026095, "grad_norm": 0.7221717038685825, "learning_rate": 1.7452537107352435e-05, "loss": 1.0558, "step": 691 }, { "epoch": 0.6439888164026095, "loss_cot": 0.5412486791610718, "loss_nocot": 0.4721285104751587, "step": 691 }, { "epoch": 0.6449207828518173, "grad_norm": 0.6701128645921763, "learning_rate": 1.7445633413876427e-05, "loss": 0.9968, "step": 692 }, { "epoch": 0.6449207828518173, "loss_cot": 0.48953843116760254, "loss_nocot": 0.5076068639755249, "step": 692 }, { "epoch": 0.6458527493010252, "grad_norm": 0.7493446958304085, "learning_rate": 1.7438729720400416e-05, "loss": 1.0475, "step": 693 }, { "epoch": 0.6458527493010252, "loss_cot": 0.5724257826805115, "loss_nocot": 0.42957568168640137, "step": 693 }, { "epoch": 0.646784715750233, "grad_norm": 0.6561496640745985, "learning_rate": 1.7431826026924405e-05, "loss": 1.0477, "step": 694 }, { "epoch": 0.646784715750233, "loss_cot": 0.5397483110427856, "loss_nocot": 0.43099910020828247, "step": 694 }, { "epoch": 0.6477166821994408, "grad_norm": 0.6009247319838361, "learning_rate": 1.7424922333448394e-05, "loss": 0.9453, "step": 695 }, { "epoch": 0.6477166821994408, "loss_cot": 0.6094689965248108, "loss_nocot": 0.6014806032180786, "step": 695 }, { "epoch": 0.6486486486486487, "grad_norm": 0.6782922044562221, "learning_rate": 1.7418018639972387e-05, "loss": 1.0873, "step": 696 }, { "epoch": 0.6486486486486487, "loss_cot": 0.5588388442993164, "loss_nocot": 0.3920902609825134, "step": 696 }, { "epoch": 0.6495806150978565, "grad_norm": 0.6463833978040981, "learning_rate": 1.7411114946496376e-05, "loss": 1.02, "step": 697 }, { "epoch": 0.6495806150978565, "loss_cot": 0.5153963565826416, "loss_nocot": 0.37021327018737793, "step": 697 }, { "epoch": 0.6505125815470643, "grad_norm": 0.6911084899187903, "learning_rate": 1.7404211253020368e-05, "loss": 1.0555, "step": 698 }, { "epoch": 0.6505125815470643, "loss_cot": 0.5198734998703003, "loss_nocot": 0.4577614665031433, "step": 698 }, { "epoch": 0.6514445479962722, "grad_norm": 0.6664520704485352, "learning_rate": 1.7397307559544357e-05, "loss": 1.0113, "step": 699 }, { "epoch": 0.6514445479962722, "loss_cot": 0.5921071767807007, "loss_nocot": 0.5102046132087708, "step": 699 }, { "epoch": 0.65237651444548, "grad_norm": 0.6419324673372717, "learning_rate": 1.739040386606835e-05, "loss": 0.9745, "step": 700 }, { "epoch": 0.65237651444548, "loss_cot": 0.5561087131500244, "loss_nocot": 0.4670218527317047, "step": 700 }, { "epoch": 0.6533084808946877, "grad_norm": 0.6203857218675722, "learning_rate": 1.738350017259234e-05, "loss": 0.914, "step": 701 }, { "epoch": 0.6533084808946877, "loss_cot": 0.589788019657135, "loss_nocot": 0.4523445665836334, "step": 701 }, { "epoch": 0.6542404473438956, "grad_norm": 0.7062391445202798, "learning_rate": 1.7376596479116328e-05, "loss": 1.0982, "step": 702 }, { "epoch": 0.6542404473438956, "loss_cot": 0.6015856266021729, "loss_nocot": 0.4555795192718506, "step": 702 }, { "epoch": 0.6551724137931034, "grad_norm": 0.7371652124792334, "learning_rate": 1.736969278564032e-05, "loss": 1.1164, "step": 703 }, { "epoch": 0.6551724137931034, "loss_cot": 0.6128077507019043, "loss_nocot": 0.5556735396385193, "step": 703 }, { "epoch": 0.6561043802423113, "grad_norm": 0.6475303611293014, "learning_rate": 1.736278909216431e-05, "loss": 1.0462, "step": 704 }, { "epoch": 0.6561043802423113, "loss_cot": 0.5434737205505371, "loss_nocot": 0.4501780569553375, "step": 704 }, { "epoch": 0.6570363466915191, "grad_norm": 0.6502349665779377, "learning_rate": 1.7355885398688298e-05, "loss": 1.0127, "step": 705 }, { "epoch": 0.6570363466915191, "loss_cot": 0.5050512552261353, "loss_nocot": 0.5203903913497925, "step": 705 }, { "epoch": 0.6579683131407269, "grad_norm": 0.5783939422502454, "learning_rate": 1.734898170521229e-05, "loss": 0.9055, "step": 706 }, { "epoch": 0.6579683131407269, "loss_cot": 0.5585849285125732, "loss_nocot": 0.49018728733062744, "step": 706 }, { "epoch": 0.6589002795899348, "grad_norm": 0.7508012412769143, "learning_rate": 1.734207801173628e-05, "loss": 1.0684, "step": 707 }, { "epoch": 0.6589002795899348, "loss_cot": 0.5496165156364441, "loss_nocot": 0.5536488890647888, "step": 707 }, { "epoch": 0.6598322460391426, "grad_norm": 0.6523312265145413, "learning_rate": 1.7335174318260272e-05, "loss": 0.9942, "step": 708 }, { "epoch": 0.6598322460391426, "loss_cot": 0.6395186185836792, "loss_nocot": 0.5352358222007751, "step": 708 }, { "epoch": 0.6607642124883504, "grad_norm": 0.7064762395196946, "learning_rate": 1.732827062478426e-05, "loss": 1.0775, "step": 709 }, { "epoch": 0.6607642124883504, "loss_cot": 0.47915133833885193, "loss_nocot": 0.4580227732658386, "step": 709 }, { "epoch": 0.6616961789375583, "grad_norm": 0.6629875387177612, "learning_rate": 1.7321366931308253e-05, "loss": 1.0423, "step": 710 }, { "epoch": 0.6616961789375583, "loss_cot": 0.44796228408813477, "loss_nocot": 0.5450288653373718, "step": 710 }, { "epoch": 0.6626281453867661, "grad_norm": 0.6942133170536404, "learning_rate": 1.7314463237832242e-05, "loss": 1.0342, "step": 711 }, { "epoch": 0.6626281453867661, "loss_cot": 0.5209367275238037, "loss_nocot": 0.5439882278442383, "step": 711 }, { "epoch": 0.6635601118359739, "grad_norm": 0.7047618373501257, "learning_rate": 1.730755954435623e-05, "loss": 1.0514, "step": 712 }, { "epoch": 0.6635601118359739, "loss_cot": 0.5340542793273926, "loss_nocot": 0.46388310194015503, "step": 712 }, { "epoch": 0.6644920782851818, "grad_norm": 0.6782534814136815, "learning_rate": 1.730065585088022e-05, "loss": 1.0145, "step": 713 }, { "epoch": 0.6644920782851818, "loss_cot": 0.524873673915863, "loss_nocot": 0.38778066635131836, "step": 713 }, { "epoch": 0.6654240447343895, "grad_norm": 0.6138531456412877, "learning_rate": 1.7293752157404213e-05, "loss": 0.9653, "step": 714 }, { "epoch": 0.6654240447343895, "loss_cot": 0.5724235773086548, "loss_nocot": 0.4939649701118469, "step": 714 }, { "epoch": 0.6663560111835974, "grad_norm": 0.7625154155955706, "learning_rate": 1.7286848463928202e-05, "loss": 1.0213, "step": 715 }, { "epoch": 0.6663560111835974, "loss_cot": 0.5554219484329224, "loss_nocot": 0.4462853968143463, "step": 715 }, { "epoch": 0.6672879776328052, "grad_norm": 0.7481461012845732, "learning_rate": 1.7279944770452194e-05, "loss": 1.0132, "step": 716 }, { "epoch": 0.6672879776328052, "loss_cot": 0.4889782965183258, "loss_nocot": 0.5389131307601929, "step": 716 }, { "epoch": 0.668219944082013, "grad_norm": 0.7082804487087822, "learning_rate": 1.7273041076976183e-05, "loss": 1.0833, "step": 717 }, { "epoch": 0.668219944082013, "loss_cot": 0.5841165781021118, "loss_nocot": 0.36598581075668335, "step": 717 }, { "epoch": 0.6691519105312209, "grad_norm": 0.6409653184357857, "learning_rate": 1.7266137383500176e-05, "loss": 0.9967, "step": 718 }, { "epoch": 0.6691519105312209, "loss_cot": 0.5220038890838623, "loss_nocot": 0.5497428774833679, "step": 718 }, { "epoch": 0.6700838769804287, "grad_norm": 0.6173601933065974, "learning_rate": 1.7259233690024165e-05, "loss": 0.968, "step": 719 }, { "epoch": 0.6700838769804287, "loss_cot": 0.5478889346122742, "loss_nocot": 0.3884373903274536, "step": 719 }, { "epoch": 0.6710158434296365, "grad_norm": 0.6602558844601676, "learning_rate": 1.7252329996548154e-05, "loss": 1.0674, "step": 720 }, { "epoch": 0.6710158434296365, "loss_cot": 0.5894821286201477, "loss_nocot": 0.47163212299346924, "step": 720 }, { "epoch": 0.6719478098788444, "grad_norm": 0.6571963464427238, "learning_rate": 1.7245426303072146e-05, "loss": 1.0246, "step": 721 }, { "epoch": 0.6719478098788444, "loss_cot": 0.49274295568466187, "loss_nocot": 0.3711046576499939, "step": 721 }, { "epoch": 0.6728797763280522, "grad_norm": 0.7272872729128165, "learning_rate": 1.7238522609596135e-05, "loss": 0.9939, "step": 722 }, { "epoch": 0.6728797763280522, "loss_cot": 0.6193133592605591, "loss_nocot": 0.31922343373298645, "step": 722 }, { "epoch": 0.67381174277726, "grad_norm": 0.658254042274184, "learning_rate": 1.7231618916120124e-05, "loss": 0.9799, "step": 723 }, { "epoch": 0.67381174277726, "loss_cot": 0.5381144285202026, "loss_nocot": 0.5777666568756104, "step": 723 }, { "epoch": 0.6747437092264679, "grad_norm": 0.6796164547742596, "learning_rate": 1.7224715222644113e-05, "loss": 1.0363, "step": 724 }, { "epoch": 0.6747437092264679, "loss_cot": 0.5424113869667053, "loss_nocot": 0.49903273582458496, "step": 724 }, { "epoch": 0.6756756756756757, "grad_norm": 0.7590098557800418, "learning_rate": 1.7217811529168106e-05, "loss": 1.113, "step": 725 }, { "epoch": 0.6756756756756757, "loss_cot": 0.5517323017120361, "loss_nocot": 0.5013907551765442, "step": 725 }, { "epoch": 0.6766076421248836, "grad_norm": 0.6220113830907269, "learning_rate": 1.72109078356921e-05, "loss": 0.9194, "step": 726 }, { "epoch": 0.6766076421248836, "loss_cot": 0.5422158241271973, "loss_nocot": 0.4339403510093689, "step": 726 }, { "epoch": 0.6775396085740913, "grad_norm": 0.7045207496006174, "learning_rate": 1.7204004142216087e-05, "loss": 1.0035, "step": 727 }, { "epoch": 0.6775396085740913, "loss_cot": 0.5108035802841187, "loss_nocot": 0.6086868643760681, "step": 727 }, { "epoch": 0.6784715750232991, "grad_norm": 0.6269198328747431, "learning_rate": 1.719710044874008e-05, "loss": 0.9805, "step": 728 }, { "epoch": 0.6784715750232991, "loss_cot": 0.5396972894668579, "loss_nocot": 0.3868505358695984, "step": 728 }, { "epoch": 0.679403541472507, "grad_norm": 0.6505924593388951, "learning_rate": 1.719019675526407e-05, "loss": 0.9589, "step": 729 }, { "epoch": 0.679403541472507, "loss_cot": 0.5257238149642944, "loss_nocot": 0.41180866956710815, "step": 729 }, { "epoch": 0.6803355079217148, "grad_norm": 0.576632185027591, "learning_rate": 1.7183293061788058e-05, "loss": 0.9341, "step": 730 }, { "epoch": 0.6803355079217148, "loss_cot": 0.47002193331718445, "loss_nocot": 0.4618570804595947, "step": 730 }, { "epoch": 0.6812674743709226, "grad_norm": 0.610658553881304, "learning_rate": 1.7176389368312047e-05, "loss": 0.9285, "step": 731 }, { "epoch": 0.6812674743709226, "loss_cot": 0.5301032662391663, "loss_nocot": 0.46921202540397644, "step": 731 }, { "epoch": 0.6821994408201305, "grad_norm": 0.6703033019381734, "learning_rate": 1.716948567483604e-05, "loss": 0.9423, "step": 732 }, { "epoch": 0.6821994408201305, "loss_cot": 0.5525355339050293, "loss_nocot": 0.34266602993011475, "step": 732 }, { "epoch": 0.6831314072693383, "grad_norm": 0.6663403083385789, "learning_rate": 1.716258198136003e-05, "loss": 1.0064, "step": 733 }, { "epoch": 0.6831314072693383, "loss_cot": 0.49946027994155884, "loss_nocot": 0.4567145109176636, "step": 733 }, { "epoch": 0.6840633737185461, "grad_norm": 0.6555879036305049, "learning_rate": 1.7155678287884017e-05, "loss": 0.995, "step": 734 }, { "epoch": 0.6840633737185461, "loss_cot": 0.5333667397499084, "loss_nocot": 0.4336961507797241, "step": 734 }, { "epoch": 0.684995340167754, "grad_norm": 0.6536297730223695, "learning_rate": 1.714877459440801e-05, "loss": 1.0275, "step": 735 }, { "epoch": 0.684995340167754, "loss_cot": 0.5119678974151611, "loss_nocot": 0.4376540184020996, "step": 735 }, { "epoch": 0.6859273066169618, "grad_norm": 0.6417147968633798, "learning_rate": 1.7141870900932002e-05, "loss": 1.0042, "step": 736 }, { "epoch": 0.6859273066169618, "loss_cot": 0.5172207951545715, "loss_nocot": 0.37813034653663635, "step": 736 }, { "epoch": 0.6868592730661697, "grad_norm": 0.6263024228925554, "learning_rate": 1.713496720745599e-05, "loss": 1.0049, "step": 737 }, { "epoch": 0.6868592730661697, "loss_cot": 0.5689287185668945, "loss_nocot": 0.49123531579971313, "step": 737 }, { "epoch": 0.6877912395153775, "grad_norm": 0.6192263713082423, "learning_rate": 1.712806351397998e-05, "loss": 0.9495, "step": 738 }, { "epoch": 0.6877912395153775, "loss_cot": 0.48231184482574463, "loss_nocot": 0.4356776773929596, "step": 738 }, { "epoch": 0.6887232059645852, "grad_norm": 0.6705191662919845, "learning_rate": 1.7121159820503973e-05, "loss": 1.0522, "step": 739 }, { "epoch": 0.6887232059645852, "loss_cot": 0.4613543450832367, "loss_nocot": 0.45279520750045776, "step": 739 }, { "epoch": 0.6896551724137931, "grad_norm": 0.6668693852207108, "learning_rate": 1.7114256127027962e-05, "loss": 1.0061, "step": 740 }, { "epoch": 0.6896551724137931, "loss_cot": 0.5140471458435059, "loss_nocot": 0.5319583415985107, "step": 740 }, { "epoch": 0.6905871388630009, "grad_norm": 0.6482577189873652, "learning_rate": 1.710735243355195e-05, "loss": 0.9801, "step": 741 }, { "epoch": 0.6905871388630009, "loss_cot": 0.5059027671813965, "loss_nocot": 0.5898715853691101, "step": 741 }, { "epoch": 0.6915191053122087, "grad_norm": 0.6620950057023273, "learning_rate": 1.710044874007594e-05, "loss": 0.9997, "step": 742 }, { "epoch": 0.6915191053122087, "loss_cot": 0.46920400857925415, "loss_nocot": 0.3927433490753174, "step": 742 }, { "epoch": 0.6924510717614166, "grad_norm": 0.6184462119242977, "learning_rate": 1.7093545046599932e-05, "loss": 0.9236, "step": 743 }, { "epoch": 0.6924510717614166, "loss_cot": 0.5427230000495911, "loss_nocot": 0.438332200050354, "step": 743 }, { "epoch": 0.6933830382106244, "grad_norm": 0.6362404660476215, "learning_rate": 1.708664135312392e-05, "loss": 0.9876, "step": 744 }, { "epoch": 0.6933830382106244, "loss_cot": 0.5002617835998535, "loss_nocot": 0.4549477696418762, "step": 744 }, { "epoch": 0.6943150046598322, "grad_norm": 0.696543690474228, "learning_rate": 1.7079737659647914e-05, "loss": 1.0157, "step": 745 }, { "epoch": 0.6943150046598322, "loss_cot": 0.5102992057800293, "loss_nocot": 0.433322012424469, "step": 745 }, { "epoch": 0.6952469711090401, "grad_norm": 0.7013532352631223, "learning_rate": 1.7072833966171903e-05, "loss": 0.9673, "step": 746 }, { "epoch": 0.6952469711090401, "loss_cot": 0.5716490745544434, "loss_nocot": 0.5272833108901978, "step": 746 }, { "epoch": 0.6961789375582479, "grad_norm": 0.7602573999151374, "learning_rate": 1.7065930272695895e-05, "loss": 1.0422, "step": 747 }, { "epoch": 0.6961789375582479, "loss_cot": 0.5069584846496582, "loss_nocot": 0.43908894062042236, "step": 747 }, { "epoch": 0.6971109040074557, "grad_norm": 0.7090817238754615, "learning_rate": 1.7059026579219884e-05, "loss": 1.0104, "step": 748 }, { "epoch": 0.6971109040074557, "loss_cot": 0.56792813539505, "loss_nocot": 0.4763363003730774, "step": 748 }, { "epoch": 0.6980428704566636, "grad_norm": 0.6624986526657644, "learning_rate": 1.7052122885743873e-05, "loss": 1.0117, "step": 749 }, { "epoch": 0.6980428704566636, "loss_cot": 0.48759618401527405, "loss_nocot": 0.43575000762939453, "step": 749 }, { "epoch": 0.6989748369058714, "grad_norm": 0.7263123190071681, "learning_rate": 1.7045219192267866e-05, "loss": 1.0315, "step": 750 }, { "epoch": 0.6989748369058714, "loss_cot": 0.6060641407966614, "loss_nocot": 0.35513460636138916, "step": 750 }, { "epoch": 0.6999068033550793, "grad_norm": 0.6810393185929231, "learning_rate": 1.7038315498791855e-05, "loss": 1.0853, "step": 751 }, { "epoch": 0.6999068033550793, "loss_cot": 0.4796932339668274, "loss_nocot": 0.4108023941516876, "step": 751 }, { "epoch": 0.700838769804287, "grad_norm": 0.6533145925645835, "learning_rate": 1.7031411805315844e-05, "loss": 0.9599, "step": 752 }, { "epoch": 0.700838769804287, "loss_cot": 0.5857398509979248, "loss_nocot": 0.4124051332473755, "step": 752 }, { "epoch": 0.7017707362534948, "grad_norm": 0.5977458012712688, "learning_rate": 1.7024508111839836e-05, "loss": 0.9416, "step": 753 }, { "epoch": 0.7017707362534948, "loss_cot": 0.6207472085952759, "loss_nocot": 0.4765717387199402, "step": 753 }, { "epoch": 0.7027027027027027, "grad_norm": 0.6544564855234865, "learning_rate": 1.7017604418363825e-05, "loss": 0.9952, "step": 754 }, { "epoch": 0.7027027027027027, "loss_cot": 0.5684760212898254, "loss_nocot": 0.47555798292160034, "step": 754 }, { "epoch": 0.7036346691519105, "grad_norm": 0.6909936108618325, "learning_rate": 1.7010700724887818e-05, "loss": 1.0333, "step": 755 }, { "epoch": 0.7036346691519105, "loss_cot": 0.5233334302902222, "loss_nocot": 0.511988639831543, "step": 755 }, { "epoch": 0.7045666356011183, "grad_norm": 0.6477879469184843, "learning_rate": 1.7003797031411807e-05, "loss": 0.9738, "step": 756 }, { "epoch": 0.7045666356011183, "loss_cot": 0.5240057110786438, "loss_nocot": 0.3752608597278595, "step": 756 }, { "epoch": 0.7054986020503262, "grad_norm": 0.6681759616859626, "learning_rate": 1.69968933379358e-05, "loss": 0.9926, "step": 757 }, { "epoch": 0.7054986020503262, "loss_cot": 0.6219981908798218, "loss_nocot": 0.3629864752292633, "step": 757 }, { "epoch": 0.706430568499534, "grad_norm": 0.6965839048774735, "learning_rate": 1.6989989644459788e-05, "loss": 1.0251, "step": 758 }, { "epoch": 0.706430568499534, "loss_cot": 0.6015850305557251, "loss_nocot": 0.5191463232040405, "step": 758 }, { "epoch": 0.7073625349487418, "grad_norm": 0.6282494840844813, "learning_rate": 1.6983085950983777e-05, "loss": 0.9533, "step": 759 }, { "epoch": 0.7073625349487418, "loss_cot": 0.5502256155014038, "loss_nocot": 0.45197397470474243, "step": 759 }, { "epoch": 0.7082945013979497, "grad_norm": 0.833987942366054, "learning_rate": 1.6976182257507766e-05, "loss": 1.0851, "step": 760 }, { "epoch": 0.7082945013979497, "loss_cot": 0.46547311544418335, "loss_nocot": 0.3685516119003296, "step": 760 }, { "epoch": 0.7092264678471575, "grad_norm": 0.6682362608330196, "learning_rate": 1.696927856403176e-05, "loss": 0.9448, "step": 761 }, { "epoch": 0.7092264678471575, "loss_cot": 0.5845258235931396, "loss_nocot": 0.5239805579185486, "step": 761 }, { "epoch": 0.7101584342963654, "grad_norm": 0.7210369103069442, "learning_rate": 1.6962374870555748e-05, "loss": 1.0608, "step": 762 }, { "epoch": 0.7101584342963654, "loss_cot": 0.4825158715248108, "loss_nocot": 0.40129154920578003, "step": 762 }, { "epoch": 0.7110904007455732, "grad_norm": 0.6862028670767248, "learning_rate": 1.695547117707974e-05, "loss": 0.9808, "step": 763 }, { "epoch": 0.7110904007455732, "loss_cot": 0.509523868560791, "loss_nocot": 0.38605278730392456, "step": 763 }, { "epoch": 0.712022367194781, "grad_norm": 0.7009978640436676, "learning_rate": 1.694856748360373e-05, "loss": 0.9129, "step": 764 }, { "epoch": 0.712022367194781, "loss_cot": 0.533171534538269, "loss_nocot": 0.5432416200637817, "step": 764 }, { "epoch": 0.7129543336439889, "grad_norm": 0.6637910096751097, "learning_rate": 1.694166379012772e-05, "loss": 0.9643, "step": 765 }, { "epoch": 0.7129543336439889, "loss_cot": 0.6205122470855713, "loss_nocot": 0.37644892930984497, "step": 765 }, { "epoch": 0.7138863000931966, "grad_norm": 0.6893586737673321, "learning_rate": 1.693476009665171e-05, "loss": 1.0051, "step": 766 }, { "epoch": 0.7138863000931966, "loss_cot": 0.4425005614757538, "loss_nocot": 0.46928101778030396, "step": 766 }, { "epoch": 0.7148182665424044, "grad_norm": 0.6129464054312129, "learning_rate": 1.69278564031757e-05, "loss": 0.9497, "step": 767 }, { "epoch": 0.7148182665424044, "loss_cot": 0.5198180675506592, "loss_nocot": 0.581283688545227, "step": 767 }, { "epoch": 0.7157502329916123, "grad_norm": 0.6436353199342357, "learning_rate": 1.6920952709699692e-05, "loss": 0.9623, "step": 768 }, { "epoch": 0.7157502329916123, "loss_cot": 0.5487531423568726, "loss_nocot": 0.27981895208358765, "step": 768 }, { "epoch": 0.7166821994408201, "grad_norm": 0.6730291313925687, "learning_rate": 1.691404901622368e-05, "loss": 0.9527, "step": 769 }, { "epoch": 0.7166821994408201, "loss_cot": 0.5046102404594421, "loss_nocot": 0.45213782787323, "step": 769 }, { "epoch": 0.7176141658900279, "grad_norm": 0.6372817715935154, "learning_rate": 1.690714532274767e-05, "loss": 1.0028, "step": 770 }, { "epoch": 0.7176141658900279, "loss_cot": 0.5498332977294922, "loss_nocot": 0.44790953397750854, "step": 770 }, { "epoch": 0.7185461323392358, "grad_norm": 0.6217593849884303, "learning_rate": 1.690024162927166e-05, "loss": 0.9824, "step": 771 }, { "epoch": 0.7185461323392358, "loss_cot": 0.5929572582244873, "loss_nocot": 0.4536110758781433, "step": 771 }, { "epoch": 0.7194780987884436, "grad_norm": 0.652231031625979, "learning_rate": 1.689333793579565e-05, "loss": 1.058, "step": 772 }, { "epoch": 0.7194780987884436, "loss_cot": 0.46604257822036743, "loss_nocot": 0.3811030387878418, "step": 772 }, { "epoch": 0.7204100652376515, "grad_norm": 0.6121336944898552, "learning_rate": 1.6886434242319644e-05, "loss": 0.9256, "step": 773 }, { "epoch": 0.7204100652376515, "loss_cot": 0.5329829454421997, "loss_nocot": 0.47258687019348145, "step": 773 }, { "epoch": 0.7213420316868593, "grad_norm": 0.6007729750453478, "learning_rate": 1.6879530548843633e-05, "loss": 0.974, "step": 774 }, { "epoch": 0.7213420316868593, "loss_cot": 0.4843050539493561, "loss_nocot": 0.5253740549087524, "step": 774 }, { "epoch": 0.7222739981360671, "grad_norm": 0.6487160583067374, "learning_rate": 1.6872626855367622e-05, "loss": 0.9932, "step": 775 }, { "epoch": 0.7222739981360671, "loss_cot": 0.5852912068367004, "loss_nocot": 0.43410012125968933, "step": 775 }, { "epoch": 0.723205964585275, "grad_norm": 0.6313073843739615, "learning_rate": 1.6865723161891615e-05, "loss": 0.9927, "step": 776 }, { "epoch": 0.723205964585275, "loss_cot": 0.570351243019104, "loss_nocot": 0.49574440717697144, "step": 776 }, { "epoch": 0.7241379310344828, "grad_norm": 0.6689772652995317, "learning_rate": 1.6858819468415604e-05, "loss": 0.9954, "step": 777 }, { "epoch": 0.7241379310344828, "loss_cot": 0.5352465510368347, "loss_nocot": 0.5466471910476685, "step": 777 }, { "epoch": 0.7250698974836906, "grad_norm": 0.6709261895640558, "learning_rate": 1.6851915774939593e-05, "loss": 1.0018, "step": 778 }, { "epoch": 0.7250698974836906, "loss_cot": 0.5114770531654358, "loss_nocot": 0.5511029362678528, "step": 778 }, { "epoch": 0.7260018639328985, "grad_norm": 0.6483640120344162, "learning_rate": 1.6845012081463585e-05, "loss": 0.982, "step": 779 }, { "epoch": 0.7260018639328985, "loss_cot": 0.5051453113555908, "loss_nocot": 0.40224528312683105, "step": 779 }, { "epoch": 0.7269338303821062, "grad_norm": 0.6428031396367053, "learning_rate": 1.6838108387987574e-05, "loss": 0.9542, "step": 780 }, { "epoch": 0.7269338303821062, "loss_cot": 0.544390857219696, "loss_nocot": 0.4848299026489258, "step": 780 }, { "epoch": 0.727865796831314, "grad_norm": 0.6062131668749081, "learning_rate": 1.6831204694511563e-05, "loss": 0.9485, "step": 781 }, { "epoch": 0.727865796831314, "loss_cot": 0.5623679161071777, "loss_nocot": 0.4098833203315735, "step": 781 }, { "epoch": 0.7287977632805219, "grad_norm": 0.6753237469751953, "learning_rate": 1.6824301001035556e-05, "loss": 1.0138, "step": 782 }, { "epoch": 0.7287977632805219, "loss_cot": 0.5478017330169678, "loss_nocot": 0.3851056396961212, "step": 782 }, { "epoch": 0.7297297297297297, "grad_norm": 0.8494831745556075, "learning_rate": 1.6817397307559548e-05, "loss": 1.0092, "step": 783 }, { "epoch": 0.7297297297297297, "loss_cot": 0.6238338947296143, "loss_nocot": 0.4241746962070465, "step": 783 }, { "epoch": 0.7306616961789375, "grad_norm": 0.6632557559135622, "learning_rate": 1.6810493614083537e-05, "loss": 1.0022, "step": 784 }, { "epoch": 0.7306616961789375, "loss_cot": 0.5177052617073059, "loss_nocot": 0.3823656737804413, "step": 784 }, { "epoch": 0.7315936626281454, "grad_norm": 0.6570298338912961, "learning_rate": 1.6803589920607526e-05, "loss": 0.9833, "step": 785 }, { "epoch": 0.7315936626281454, "loss_cot": 0.5529955625534058, "loss_nocot": 0.3956491947174072, "step": 785 }, { "epoch": 0.7325256290773532, "grad_norm": 0.644013052472949, "learning_rate": 1.6796686227131515e-05, "loss": 0.9617, "step": 786 }, { "epoch": 0.7325256290773532, "loss_cot": 0.5029157996177673, "loss_nocot": 0.42292311787605286, "step": 786 }, { "epoch": 0.7334575955265611, "grad_norm": 0.6631640033537494, "learning_rate": 1.6789782533655508e-05, "loss": 1.0086, "step": 787 }, { "epoch": 0.7334575955265611, "loss_cot": 0.5295207500457764, "loss_nocot": 0.4568138122558594, "step": 787 }, { "epoch": 0.7343895619757689, "grad_norm": 0.6216352973067065, "learning_rate": 1.6782878840179497e-05, "loss": 1.0099, "step": 788 }, { "epoch": 0.7343895619757689, "loss_cot": 0.5037468671798706, "loss_nocot": 0.5781553983688354, "step": 788 }, { "epoch": 0.7353215284249767, "grad_norm": 0.6298155177466425, "learning_rate": 1.6775975146703486e-05, "loss": 1.0439, "step": 789 }, { "epoch": 0.7353215284249767, "loss_cot": 0.5709503293037415, "loss_nocot": 0.5442823171615601, "step": 789 }, { "epoch": 0.7362534948741846, "grad_norm": 0.7614099439499692, "learning_rate": 1.6769071453227478e-05, "loss": 1.053, "step": 790 }, { "epoch": 0.7362534948741846, "loss_cot": 0.5742582082748413, "loss_nocot": 0.4778136909008026, "step": 790 }, { "epoch": 0.7371854613233924, "grad_norm": 0.6538688112819834, "learning_rate": 1.6762167759751467e-05, "loss": 1.0318, "step": 791 }, { "epoch": 0.7371854613233924, "loss_cot": 0.5690427422523499, "loss_nocot": 0.3132168650627136, "step": 791 }, { "epoch": 0.7381174277726001, "grad_norm": 0.5888782175241669, "learning_rate": 1.675526406627546e-05, "loss": 0.9456, "step": 792 }, { "epoch": 0.7381174277726001, "loss_cot": 0.5159832239151001, "loss_nocot": 0.40682047605514526, "step": 792 }, { "epoch": 0.739049394221808, "grad_norm": 0.6091402304028078, "learning_rate": 1.674836037279945e-05, "loss": 0.952, "step": 793 }, { "epoch": 0.739049394221808, "loss_cot": 0.5326430797576904, "loss_nocot": 0.4020879566669464, "step": 793 }, { "epoch": 0.7399813606710158, "grad_norm": 0.6466964509525734, "learning_rate": 1.674145667932344e-05, "loss": 1.008, "step": 794 }, { "epoch": 0.7399813606710158, "loss_cot": 0.5137202739715576, "loss_nocot": 0.49396371841430664, "step": 794 }, { "epoch": 0.7409133271202236, "grad_norm": 0.6739840223309218, "learning_rate": 1.673455298584743e-05, "loss": 1.0211, "step": 795 }, { "epoch": 0.7409133271202236, "loss_cot": 0.5027720928192139, "loss_nocot": 0.3053734302520752, "step": 795 }, { "epoch": 0.7418452935694315, "grad_norm": 0.7106636675784882, "learning_rate": 1.672764929237142e-05, "loss": 1.027, "step": 796 }, { "epoch": 0.7418452935694315, "loss_cot": 0.6121987104415894, "loss_nocot": 0.43038904666900635, "step": 796 }, { "epoch": 0.7427772600186393, "grad_norm": 0.6526090958618208, "learning_rate": 1.672074559889541e-05, "loss": 1.0223, "step": 797 }, { "epoch": 0.7427772600186393, "loss_cot": 0.523135781288147, "loss_nocot": 0.4115440249443054, "step": 797 }, { "epoch": 0.7437092264678472, "grad_norm": 0.6686065416654308, "learning_rate": 1.67138419054194e-05, "loss": 0.9848, "step": 798 }, { "epoch": 0.7437092264678472, "loss_cot": 0.586243748664856, "loss_nocot": 0.5260465741157532, "step": 798 }, { "epoch": 0.744641192917055, "grad_norm": 0.7034492599327073, "learning_rate": 1.670693821194339e-05, "loss": 1.0427, "step": 799 }, { "epoch": 0.744641192917055, "loss_cot": 0.512416422367096, "loss_nocot": 0.5985320806503296, "step": 799 }, { "epoch": 0.7455731593662628, "grad_norm": 0.7171371035160624, "learning_rate": 1.6700034518467382e-05, "loss": 1.0786, "step": 800 }, { "epoch": 0.7455731593662628, "loss_cot": 0.5093415379524231, "loss_nocot": 0.45863136649131775, "step": 800 }, { "epoch": 0.7465051258154707, "grad_norm": 0.6595900177542791, "learning_rate": 1.669313082499137e-05, "loss": 1.0259, "step": 801 }, { "epoch": 0.7465051258154707, "loss_cot": 0.5103179216384888, "loss_nocot": 0.3933568000793457, "step": 801 }, { "epoch": 0.7474370922646785, "grad_norm": 0.68954991880836, "learning_rate": 1.6686227131515363e-05, "loss": 0.9923, "step": 802 }, { "epoch": 0.7474370922646785, "loss_cot": 0.5472924113273621, "loss_nocot": 0.42924538254737854, "step": 802 }, { "epoch": 0.7483690587138863, "grad_norm": 0.662944577146576, "learning_rate": 1.6679323438039353e-05, "loss": 1.0127, "step": 803 }, { "epoch": 0.7483690587138863, "loss_cot": 0.4847109913825989, "loss_nocot": 0.40412086248397827, "step": 803 }, { "epoch": 0.7493010251630942, "grad_norm": 0.6657945006187423, "learning_rate": 1.667241974456334e-05, "loss": 1.0327, "step": 804 }, { "epoch": 0.7493010251630942, "loss_cot": 0.544723629951477, "loss_nocot": 0.648999810218811, "step": 804 }, { "epoch": 0.750232991612302, "grad_norm": 0.6681409089403686, "learning_rate": 1.6665516051087334e-05, "loss": 1.034, "step": 805 }, { "epoch": 0.750232991612302, "loss_cot": 0.5413591861724854, "loss_nocot": 0.49060767889022827, "step": 805 }, { "epoch": 0.7511649580615097, "grad_norm": 0.631886654799091, "learning_rate": 1.6658612357611323e-05, "loss": 1.0209, "step": 806 }, { "epoch": 0.7511649580615097, "loss_cot": 0.5043714046478271, "loss_nocot": 0.6063028573989868, "step": 806 }, { "epoch": 0.7520969245107176, "grad_norm": 0.6924589950331582, "learning_rate": 1.6651708664135312e-05, "loss": 1.029, "step": 807 }, { "epoch": 0.7520969245107176, "loss_cot": 0.5435351729393005, "loss_nocot": 0.3982914090156555, "step": 807 }, { "epoch": 0.7530288909599254, "grad_norm": 0.6289513062575645, "learning_rate": 1.6644804970659305e-05, "loss": 1.001, "step": 808 }, { "epoch": 0.7530288909599254, "loss_cot": 0.5712812542915344, "loss_nocot": 0.3884671926498413, "step": 808 }, { "epoch": 0.7539608574091333, "grad_norm": 0.6021746861692452, "learning_rate": 1.6637901277183294e-05, "loss": 0.9495, "step": 809 }, { "epoch": 0.7539608574091333, "loss_cot": 0.5728788375854492, "loss_nocot": 0.3543212115764618, "step": 809 }, { "epoch": 0.7548928238583411, "grad_norm": 0.7037112410306847, "learning_rate": 1.6630997583707286e-05, "loss": 0.9976, "step": 810 }, { "epoch": 0.7548928238583411, "loss_cot": 0.5300641655921936, "loss_nocot": 0.7733412981033325, "step": 810 }, { "epoch": 0.7558247903075489, "grad_norm": 0.7243313728651208, "learning_rate": 1.6624093890231275e-05, "loss": 1.0934, "step": 811 }, { "epoch": 0.7558247903075489, "loss_cot": 0.5265188217163086, "loss_nocot": 0.43092286586761475, "step": 811 }, { "epoch": 0.7567567567567568, "grad_norm": 0.6399076477479366, "learning_rate": 1.6617190196755267e-05, "loss": 0.9746, "step": 812 }, { "epoch": 0.7567567567567568, "loss_cot": 0.4621964395046234, "loss_nocot": 0.4560713469982147, "step": 812 }, { "epoch": 0.7576887232059646, "grad_norm": 0.7404551103042897, "learning_rate": 1.6610286503279256e-05, "loss": 1.0656, "step": 813 }, { "epoch": 0.7576887232059646, "loss_cot": 0.5465832948684692, "loss_nocot": 0.4054475724697113, "step": 813 }, { "epoch": 0.7586206896551724, "grad_norm": 0.6553905431517679, "learning_rate": 1.6603382809803246e-05, "loss": 0.9467, "step": 814 }, { "epoch": 0.7586206896551724, "loss_cot": 0.5074081420898438, "loss_nocot": 0.43788912892341614, "step": 814 }, { "epoch": 0.7595526561043803, "grad_norm": 0.654391140505457, "learning_rate": 1.6596479116327235e-05, "loss": 0.9253, "step": 815 }, { "epoch": 0.7595526561043803, "loss_cot": 0.5629929304122925, "loss_nocot": 0.525246262550354, "step": 815 }, { "epoch": 0.7604846225535881, "grad_norm": 0.6790069086458107, "learning_rate": 1.6589575422851227e-05, "loss": 0.9923, "step": 816 }, { "epoch": 0.7604846225535881, "loss_cot": 0.5512255430221558, "loss_nocot": 0.613795280456543, "step": 816 }, { "epoch": 0.7614165890027959, "grad_norm": 0.789214393198148, "learning_rate": 1.6582671729375216e-05, "loss": 1.0431, "step": 817 }, { "epoch": 0.7614165890027959, "loss_cot": 0.5776956677436829, "loss_nocot": 0.5496807098388672, "step": 817 }, { "epoch": 0.7623485554520038, "grad_norm": 0.6463247524606387, "learning_rate": 1.657576803589921e-05, "loss": 1.0455, "step": 818 }, { "epoch": 0.7623485554520038, "loss_cot": 0.5618289113044739, "loss_nocot": 0.36589986085891724, "step": 818 }, { "epoch": 0.7632805219012115, "grad_norm": 0.6423708409046317, "learning_rate": 1.6568864342423197e-05, "loss": 0.9845, "step": 819 }, { "epoch": 0.7632805219012115, "loss_cot": 0.511715292930603, "loss_nocot": 0.42715880274772644, "step": 819 }, { "epoch": 0.7642124883504194, "grad_norm": 0.6048379761358462, "learning_rate": 1.656196064894719e-05, "loss": 0.9653, "step": 820 }, { "epoch": 0.7642124883504194, "loss_cot": 0.5154099464416504, "loss_nocot": 0.6511037945747375, "step": 820 }, { "epoch": 0.7651444547996272, "grad_norm": 0.7302399346963367, "learning_rate": 1.655505695547118e-05, "loss": 0.9658, "step": 821 }, { "epoch": 0.7651444547996272, "loss_cot": 0.5358566045761108, "loss_nocot": 0.4147609770298004, "step": 821 }, { "epoch": 0.766076421248835, "grad_norm": 0.6968147648934463, "learning_rate": 1.6548153261995168e-05, "loss": 1.0258, "step": 822 }, { "epoch": 0.766076421248835, "loss_cot": 0.5437188148498535, "loss_nocot": 0.4942174255847931, "step": 822 }, { "epoch": 0.7670083876980429, "grad_norm": 0.6550387864009186, "learning_rate": 1.654124956851916e-05, "loss": 1.0177, "step": 823 }, { "epoch": 0.7670083876980429, "loss_cot": 0.5555657148361206, "loss_nocot": 0.42704877257347107, "step": 823 }, { "epoch": 0.7679403541472507, "grad_norm": 0.5794144828387879, "learning_rate": 1.653434587504315e-05, "loss": 0.9451, "step": 824 }, { "epoch": 0.7679403541472507, "loss_cot": 0.5704532861709595, "loss_nocot": 0.5549106001853943, "step": 824 }, { "epoch": 0.7688723205964585, "grad_norm": 0.6863057377816287, "learning_rate": 1.652744218156714e-05, "loss": 1.0168, "step": 825 }, { "epoch": 0.7688723205964585, "loss_cot": 0.5197305083274841, "loss_nocot": 0.3525179624557495, "step": 825 }, { "epoch": 0.7698042870456664, "grad_norm": 0.7402805549947414, "learning_rate": 1.6520538488091128e-05, "loss": 1.0545, "step": 826 }, { "epoch": 0.7698042870456664, "loss_cot": 0.537358283996582, "loss_nocot": 0.3435404300689697, "step": 826 }, { "epoch": 0.7707362534948742, "grad_norm": 0.6092250414788952, "learning_rate": 1.651363479461512e-05, "loss": 0.9055, "step": 827 }, { "epoch": 0.7707362534948742, "loss_cot": 0.5532375574111938, "loss_nocot": 0.5608305931091309, "step": 827 }, { "epoch": 0.771668219944082, "grad_norm": 0.6431870052897201, "learning_rate": 1.6506731101139112e-05, "loss": 1.0398, "step": 828 }, { "epoch": 0.771668219944082, "loss_cot": 0.4950355887413025, "loss_nocot": 0.4386404752731323, "step": 828 }, { "epoch": 0.7726001863932899, "grad_norm": 0.5904573441923409, "learning_rate": 1.64998274076631e-05, "loss": 0.9407, "step": 829 }, { "epoch": 0.7726001863932899, "loss_cot": 0.4933796525001526, "loss_nocot": 0.3912629783153534, "step": 829 }, { "epoch": 0.7735321528424977, "grad_norm": 0.6549601128524538, "learning_rate": 1.6492923714187094e-05, "loss": 0.9862, "step": 830 }, { "epoch": 0.7735321528424977, "loss_cot": 0.5368952751159668, "loss_nocot": 0.369414746761322, "step": 830 }, { "epoch": 0.7744641192917054, "grad_norm": 0.5862355802722037, "learning_rate": 1.6486020020711083e-05, "loss": 0.9416, "step": 831 }, { "epoch": 0.7744641192917054, "loss_cot": 0.500079333782196, "loss_nocot": 0.5423922538757324, "step": 831 }, { "epoch": 0.7753960857409133, "grad_norm": 0.5989766277543134, "learning_rate": 1.6479116327235072e-05, "loss": 0.9747, "step": 832 }, { "epoch": 0.7753960857409133, "loss_cot": 0.5739853382110596, "loss_nocot": 0.4081558585166931, "step": 832 }, { "epoch": 0.7763280521901211, "grad_norm": 0.6209725846213229, "learning_rate": 1.647221263375906e-05, "loss": 0.9506, "step": 833 }, { "epoch": 0.7763280521901211, "loss_cot": 0.5127597451210022, "loss_nocot": 0.3827584981918335, "step": 833 }, { "epoch": 0.777260018639329, "grad_norm": 0.619707793461393, "learning_rate": 1.6465308940283053e-05, "loss": 0.9653, "step": 834 }, { "epoch": 0.777260018639329, "loss_cot": 0.5161362290382385, "loss_nocot": 0.4781796336174011, "step": 834 }, { "epoch": 0.7781919850885368, "grad_norm": 0.6325532871169045, "learning_rate": 1.6458405246807042e-05, "loss": 1.0043, "step": 835 }, { "epoch": 0.7781919850885368, "loss_cot": 0.5799975395202637, "loss_nocot": 0.5283705592155457, "step": 835 }, { "epoch": 0.7791239515377446, "grad_norm": 0.6842354776919842, "learning_rate": 1.645150155333103e-05, "loss": 1.0397, "step": 836 }, { "epoch": 0.7791239515377446, "loss_cot": 0.5505814552307129, "loss_nocot": 0.5289109945297241, "step": 836 }, { "epoch": 0.7800559179869525, "grad_norm": 0.7053433285679891, "learning_rate": 1.6444597859855024e-05, "loss": 0.9831, "step": 837 }, { "epoch": 0.7800559179869525, "loss_cot": 0.5864120721817017, "loss_nocot": 0.45321595668792725, "step": 837 }, { "epoch": 0.7809878844361603, "grad_norm": 0.6510286064669887, "learning_rate": 1.6437694166379013e-05, "loss": 1.0526, "step": 838 }, { "epoch": 0.7809878844361603, "loss_cot": 0.5216495394706726, "loss_nocot": 0.36118894815444946, "step": 838 }, { "epoch": 0.7819198508853681, "grad_norm": 0.5921680942078554, "learning_rate": 1.6430790472903005e-05, "loss": 0.9022, "step": 839 }, { "epoch": 0.7819198508853681, "loss_cot": 0.5619100332260132, "loss_nocot": 0.5064370632171631, "step": 839 }, { "epoch": 0.782851817334576, "grad_norm": 0.691856847445647, "learning_rate": 1.6423886779426994e-05, "loss": 1.0636, "step": 840 }, { "epoch": 0.782851817334576, "loss_cot": 0.5869026780128479, "loss_nocot": 0.4867437481880188, "step": 840 }, { "epoch": 0.7837837837837838, "grad_norm": 0.6817792113939413, "learning_rate": 1.6416983085950987e-05, "loss": 1.0024, "step": 841 }, { "epoch": 0.7837837837837838, "loss_cot": 0.5785853266716003, "loss_nocot": 0.4214322566986084, "step": 841 }, { "epoch": 0.7847157502329916, "grad_norm": 0.6540638210639552, "learning_rate": 1.6410079392474976e-05, "loss": 1.0308, "step": 842 }, { "epoch": 0.7847157502329916, "loss_cot": 0.5419126152992249, "loss_nocot": 0.45325416326522827, "step": 842 }, { "epoch": 0.7856477166821995, "grad_norm": 0.634617455803596, "learning_rate": 1.6403175698998965e-05, "loss": 1.0015, "step": 843 }, { "epoch": 0.7856477166821995, "loss_cot": 0.5876247882843018, "loss_nocot": 0.5627361536026001, "step": 843 }, { "epoch": 0.7865796831314072, "grad_norm": 0.7191831020535591, "learning_rate": 1.6396272005522954e-05, "loss": 1.0727, "step": 844 }, { "epoch": 0.7865796831314072, "loss_cot": 0.5581247210502625, "loss_nocot": 0.5179620981216431, "step": 844 }, { "epoch": 0.7875116495806151, "grad_norm": 0.6271148031402619, "learning_rate": 1.6389368312046946e-05, "loss": 1.0116, "step": 845 }, { "epoch": 0.7875116495806151, "loss_cot": 0.5400745868682861, "loss_nocot": 0.3929901123046875, "step": 845 }, { "epoch": 0.7884436160298229, "grad_norm": 0.6135254750954263, "learning_rate": 1.6382464618570935e-05, "loss": 1.0019, "step": 846 }, { "epoch": 0.7884436160298229, "loss_cot": 0.5550051927566528, "loss_nocot": 0.39177581667900085, "step": 846 }, { "epoch": 0.7893755824790307, "grad_norm": 0.586332428005073, "learning_rate": 1.6375560925094928e-05, "loss": 0.9415, "step": 847 }, { "epoch": 0.7893755824790307, "loss_cot": 0.4790003001689911, "loss_nocot": 0.4434657692909241, "step": 847 }, { "epoch": 0.7903075489282386, "grad_norm": 0.6635138223221545, "learning_rate": 1.6368657231618917e-05, "loss": 0.9907, "step": 848 }, { "epoch": 0.7903075489282386, "loss_cot": 0.5633317232131958, "loss_nocot": 0.46113982796669006, "step": 848 }, { "epoch": 0.7912395153774464, "grad_norm": 0.6858234071502499, "learning_rate": 1.636175353814291e-05, "loss": 1.0443, "step": 849 }, { "epoch": 0.7912395153774464, "loss_cot": 0.592242956161499, "loss_nocot": 0.37339577078819275, "step": 849 }, { "epoch": 0.7921714818266542, "grad_norm": 0.6302203865238547, "learning_rate": 1.63548498446669e-05, "loss": 0.9794, "step": 850 }, { "epoch": 0.7921714818266542, "loss_cot": 0.5271639823913574, "loss_nocot": 0.5778950452804565, "step": 850 }, { "epoch": 0.7931034482758621, "grad_norm": 0.6638107339745193, "learning_rate": 1.6347946151190887e-05, "loss": 1.0483, "step": 851 }, { "epoch": 0.7931034482758621, "loss_cot": 0.5141088962554932, "loss_nocot": 0.42375850677490234, "step": 851 }, { "epoch": 0.7940354147250699, "grad_norm": 0.6273984244719448, "learning_rate": 1.634104245771488e-05, "loss": 0.9701, "step": 852 }, { "epoch": 0.7940354147250699, "loss_cot": 0.49045008420944214, "loss_nocot": 0.5402534604072571, "step": 852 }, { "epoch": 0.7949673811742777, "grad_norm": 0.629177876648348, "learning_rate": 1.633413876423887e-05, "loss": 0.9663, "step": 853 }, { "epoch": 0.7949673811742777, "loss_cot": 0.528683602809906, "loss_nocot": 0.3094417452812195, "step": 853 }, { "epoch": 0.7958993476234856, "grad_norm": 0.6271526261549077, "learning_rate": 1.6327235070762858e-05, "loss": 0.906, "step": 854 }, { "epoch": 0.7958993476234856, "loss_cot": 0.5363318920135498, "loss_nocot": 0.41436898708343506, "step": 854 }, { "epoch": 0.7968313140726934, "grad_norm": 0.6150925228938449, "learning_rate": 1.632033137728685e-05, "loss": 0.9916, "step": 855 }, { "epoch": 0.7968313140726934, "loss_cot": 0.5922803282737732, "loss_nocot": 0.5073111057281494, "step": 855 }, { "epoch": 0.7977632805219013, "grad_norm": 0.656046331290623, "learning_rate": 1.631342768381084e-05, "loss": 0.9792, "step": 856 }, { "epoch": 0.7977632805219013, "loss_cot": 0.5597679615020752, "loss_nocot": 0.3977610468864441, "step": 856 }, { "epoch": 0.798695246971109, "grad_norm": 0.6204568373281963, "learning_rate": 1.6306523990334832e-05, "loss": 0.9444, "step": 857 }, { "epoch": 0.798695246971109, "loss_cot": 0.49761974811553955, "loss_nocot": 0.6312687993049622, "step": 857 }, { "epoch": 0.7996272134203168, "grad_norm": 0.7081723562673604, "learning_rate": 1.629962029685882e-05, "loss": 1.0779, "step": 858 }, { "epoch": 0.7996272134203168, "loss_cot": 0.6191551685333252, "loss_nocot": 0.45280081033706665, "step": 858 }, { "epoch": 0.8005591798695247, "grad_norm": 0.6676081346016072, "learning_rate": 1.6292716603382813e-05, "loss": 1.0368, "step": 859 }, { "epoch": 0.8005591798695247, "loss_cot": 0.5299006700515747, "loss_nocot": 0.44780415296554565, "step": 859 }, { "epoch": 0.8014911463187325, "grad_norm": 0.6450743186691902, "learning_rate": 1.6285812909906802e-05, "loss": 0.9781, "step": 860 }, { "epoch": 0.8014911463187325, "loss_cot": 0.4854907989501953, "loss_nocot": 0.4654386341571808, "step": 860 }, { "epoch": 0.8024231127679403, "grad_norm": 0.5794396875156617, "learning_rate": 1.627890921643079e-05, "loss": 0.8705, "step": 861 }, { "epoch": 0.8024231127679403, "loss_cot": 0.5464282631874084, "loss_nocot": 0.5113816261291504, "step": 861 }, { "epoch": 0.8033550792171482, "grad_norm": 0.5968372203494756, "learning_rate": 1.627200552295478e-05, "loss": 0.9918, "step": 862 }, { "epoch": 0.8033550792171482, "loss_cot": 0.5425934195518494, "loss_nocot": 0.6152405738830566, "step": 862 }, { "epoch": 0.804287045666356, "grad_norm": 0.6950750526511243, "learning_rate": 1.6265101829478773e-05, "loss": 1.0798, "step": 863 }, { "epoch": 0.804287045666356, "loss_cot": 0.5280476808547974, "loss_nocot": 0.4971579313278198, "step": 863 }, { "epoch": 0.8052190121155638, "grad_norm": 0.6579177308783983, "learning_rate": 1.6258198136002762e-05, "loss": 1.0059, "step": 864 }, { "epoch": 0.8052190121155638, "loss_cot": 0.5405133962631226, "loss_nocot": 0.5066614747047424, "step": 864 }, { "epoch": 0.8061509785647717, "grad_norm": 0.6176011630621573, "learning_rate": 1.6251294442526754e-05, "loss": 1.0144, "step": 865 }, { "epoch": 0.8061509785647717, "loss_cot": 0.5724585056304932, "loss_nocot": 0.4264235198497772, "step": 865 }, { "epoch": 0.8070829450139795, "grad_norm": 0.6554616594252969, "learning_rate": 1.6244390749050743e-05, "loss": 0.9918, "step": 866 }, { "epoch": 0.8070829450139795, "loss_cot": 0.49761998653411865, "loss_nocot": 0.3616679608821869, "step": 866 }, { "epoch": 0.8080149114631874, "grad_norm": 0.6224188038389623, "learning_rate": 1.6237487055574736e-05, "loss": 0.9671, "step": 867 }, { "epoch": 0.8080149114631874, "loss_cot": 0.5556213855743408, "loss_nocot": 0.507720947265625, "step": 867 }, { "epoch": 0.8089468779123952, "grad_norm": 0.666634905002777, "learning_rate": 1.6230583362098725e-05, "loss": 1.0441, "step": 868 }, { "epoch": 0.8089468779123952, "loss_cot": 0.6150572896003723, "loss_nocot": 0.39254230260849, "step": 868 }, { "epoch": 0.809878844361603, "grad_norm": 0.6345496438585879, "learning_rate": 1.6223679668622714e-05, "loss": 0.9651, "step": 869 }, { "epoch": 0.809878844361603, "loss_cot": 0.585218071937561, "loss_nocot": 0.31772691011428833, "step": 869 }, { "epoch": 0.8108108108108109, "grad_norm": 0.7929729271321851, "learning_rate": 1.6216775975146706e-05, "loss": 0.8974, "step": 870 }, { "epoch": 0.8108108108108109, "loss_cot": 0.5286803245544434, "loss_nocot": 0.38407328724861145, "step": 870 }, { "epoch": 0.8117427772600186, "grad_norm": 0.594497802866764, "learning_rate": 1.6209872281670695e-05, "loss": 0.935, "step": 871 }, { "epoch": 0.8117427772600186, "loss_cot": 0.6002236008644104, "loss_nocot": 0.3403145372867584, "step": 871 }, { "epoch": 0.8126747437092264, "grad_norm": 0.5986351290371706, "learning_rate": 1.6202968588194684e-05, "loss": 0.9135, "step": 872 }, { "epoch": 0.8126747437092264, "loss_cot": 0.4930558502674103, "loss_nocot": 0.40524691343307495, "step": 872 }, { "epoch": 0.8136067101584343, "grad_norm": 0.5820152769731031, "learning_rate": 1.6196064894718673e-05, "loss": 0.8974, "step": 873 }, { "epoch": 0.8136067101584343, "loss_cot": 0.5532659292221069, "loss_nocot": 0.4020628333091736, "step": 873 }, { "epoch": 0.8145386766076421, "grad_norm": 0.6395597919464593, "learning_rate": 1.6189161201242666e-05, "loss": 0.9971, "step": 874 }, { "epoch": 0.8145386766076421, "loss_cot": 0.5004292726516724, "loss_nocot": 0.5060951709747314, "step": 874 }, { "epoch": 0.8154706430568499, "grad_norm": 0.6726518219677334, "learning_rate": 1.6182257507766658e-05, "loss": 0.9906, "step": 875 }, { "epoch": 0.8154706430568499, "loss_cot": 0.5123953819274902, "loss_nocot": 0.4678472876548767, "step": 875 }, { "epoch": 0.8164026095060578, "grad_norm": 0.639446527541939, "learning_rate": 1.6175353814290647e-05, "loss": 0.9818, "step": 876 }, { "epoch": 0.8164026095060578, "loss_cot": 0.5059673190116882, "loss_nocot": 0.474022775888443, "step": 876 }, { "epoch": 0.8173345759552656, "grad_norm": 0.62129545968822, "learning_rate": 1.6168450120814636e-05, "loss": 0.9594, "step": 877 }, { "epoch": 0.8173345759552656, "loss_cot": 0.4845164120197296, "loss_nocot": 0.520564079284668, "step": 877 }, { "epoch": 0.8182665424044734, "grad_norm": 0.652497401313848, "learning_rate": 1.616154642733863e-05, "loss": 0.9589, "step": 878 }, { "epoch": 0.8182665424044734, "loss_cot": 0.5324424505233765, "loss_nocot": 0.4431920051574707, "step": 878 }, { "epoch": 0.8191985088536813, "grad_norm": 0.6195131765508815, "learning_rate": 1.6154642733862618e-05, "loss": 0.9976, "step": 879 }, { "epoch": 0.8191985088536813, "loss_cot": 0.5198091268539429, "loss_nocot": 0.3211670517921448, "step": 879 }, { "epoch": 0.8201304753028891, "grad_norm": 0.5772849558187836, "learning_rate": 1.6147739040386607e-05, "loss": 0.9059, "step": 880 }, { "epoch": 0.8201304753028891, "loss_cot": 0.5777846574783325, "loss_nocot": 0.5331366062164307, "step": 880 }, { "epoch": 0.821062441752097, "grad_norm": 0.6876801370108112, "learning_rate": 1.61408353469106e-05, "loss": 1.0395, "step": 881 }, { "epoch": 0.821062441752097, "loss_cot": 0.4935424327850342, "loss_nocot": 0.39139214158058167, "step": 881 }, { "epoch": 0.8219944082013048, "grad_norm": 0.6472271005899148, "learning_rate": 1.6133931653434588e-05, "loss": 0.9949, "step": 882 }, { "epoch": 0.8219944082013048, "loss_cot": 0.5441287755966187, "loss_nocot": 0.6439171433448792, "step": 882 }, { "epoch": 0.8229263746505125, "grad_norm": 0.7319122442276208, "learning_rate": 1.6127027959958577e-05, "loss": 1.0253, "step": 883 }, { "epoch": 0.8229263746505125, "loss_cot": 0.5619388222694397, "loss_nocot": 0.4537816643714905, "step": 883 }, { "epoch": 0.8238583410997204, "grad_norm": 0.7022955784371083, "learning_rate": 1.612012426648257e-05, "loss": 1.106, "step": 884 }, { "epoch": 0.8238583410997204, "loss_cot": 0.5090994834899902, "loss_nocot": 0.633088231086731, "step": 884 }, { "epoch": 0.8247903075489282, "grad_norm": 0.6700554056140974, "learning_rate": 1.6113220573006562e-05, "loss": 1.0879, "step": 885 }, { "epoch": 0.8247903075489282, "loss_cot": 0.5193506479263306, "loss_nocot": 0.48610711097717285, "step": 885 }, { "epoch": 0.825722273998136, "grad_norm": 0.651568330672181, "learning_rate": 1.610631687953055e-05, "loss": 1.023, "step": 886 }, { "epoch": 0.825722273998136, "loss_cot": 0.5662932991981506, "loss_nocot": 0.4880021810531616, "step": 886 }, { "epoch": 0.8266542404473439, "grad_norm": 0.6571002232543158, "learning_rate": 1.609941318605454e-05, "loss": 0.9519, "step": 887 }, { "epoch": 0.8266542404473439, "loss_cot": 0.5220128297805786, "loss_nocot": 0.37666258215904236, "step": 887 }, { "epoch": 0.8275862068965517, "grad_norm": 0.7041367464000461, "learning_rate": 1.6092509492578533e-05, "loss": 1.0005, "step": 888 }, { "epoch": 0.8275862068965517, "loss_cot": 0.5070561170578003, "loss_nocot": 0.6291896104812622, "step": 888 }, { "epoch": 0.8285181733457595, "grad_norm": 0.6629946815765134, "learning_rate": 1.608560579910252e-05, "loss": 1.02, "step": 889 }, { "epoch": 0.8285181733457595, "loss_cot": 0.5297434329986572, "loss_nocot": 0.4502207338809967, "step": 889 }, { "epoch": 0.8294501397949674, "grad_norm": 0.6349677841249717, "learning_rate": 1.607870210562651e-05, "loss": 0.998, "step": 890 }, { "epoch": 0.8294501397949674, "loss_cot": 0.542412519454956, "loss_nocot": 0.5561997890472412, "step": 890 }, { "epoch": 0.8303821062441752, "grad_norm": 0.6680385183667241, "learning_rate": 1.60717984121505e-05, "loss": 1.0456, "step": 891 }, { "epoch": 0.8303821062441752, "loss_cot": 0.6024608612060547, "loss_nocot": 0.4076542854309082, "step": 891 }, { "epoch": 0.8313140726933831, "grad_norm": 0.5749729770326156, "learning_rate": 1.6064894718674492e-05, "loss": 0.9882, "step": 892 }, { "epoch": 0.8313140726933831, "loss_cot": 0.5176221132278442, "loss_nocot": 0.6704446077346802, "step": 892 }, { "epoch": 0.8322460391425909, "grad_norm": 0.7975400635860004, "learning_rate": 1.605799102519848e-05, "loss": 1.0516, "step": 893 }, { "epoch": 0.8322460391425909, "loss_cot": 0.6013687252998352, "loss_nocot": 0.42448675632476807, "step": 893 }, { "epoch": 0.8331780055917987, "grad_norm": 0.6123990783877331, "learning_rate": 1.6051087331722474e-05, "loss": 0.9921, "step": 894 }, { "epoch": 0.8331780055917987, "loss_cot": 0.558096706867218, "loss_nocot": 0.42926299571990967, "step": 894 }, { "epoch": 0.8341099720410066, "grad_norm": 0.6127035374205689, "learning_rate": 1.6044183638246463e-05, "loss": 0.9851, "step": 895 }, { "epoch": 0.8341099720410066, "loss_cot": 0.5371986627578735, "loss_nocot": 0.3305143415927887, "step": 895 }, { "epoch": 0.8350419384902144, "grad_norm": 0.5853895855623783, "learning_rate": 1.6037279944770455e-05, "loss": 0.9239, "step": 896 }, { "epoch": 0.8350419384902144, "loss_cot": 0.5317396521568298, "loss_nocot": 0.3670184016227722, "step": 896 }, { "epoch": 0.8359739049394221, "grad_norm": 0.605150202265523, "learning_rate": 1.6030376251294444e-05, "loss": 0.936, "step": 897 }, { "epoch": 0.8359739049394221, "loss_cot": 0.578231692314148, "loss_nocot": 0.37272512912750244, "step": 897 }, { "epoch": 0.83690587138863, "grad_norm": 0.6271977043046079, "learning_rate": 1.6023472557818433e-05, "loss": 0.9802, "step": 898 }, { "epoch": 0.83690587138863, "loss_cot": 0.5380859375, "loss_nocot": 0.3965752124786377, "step": 898 }, { "epoch": 0.8378378378378378, "grad_norm": 0.5731664978612019, "learning_rate": 1.6016568864342426e-05, "loss": 0.8901, "step": 899 }, { "epoch": 0.8378378378378378, "loss_cot": 0.546271562576294, "loss_nocot": 0.6924254298210144, "step": 899 }, { "epoch": 0.8387698042870456, "grad_norm": 0.712700447371432, "learning_rate": 1.6009665170866415e-05, "loss": 1.0886, "step": 900 }, { "epoch": 0.8387698042870456, "loss_cot": 0.567084789276123, "loss_nocot": 0.38946017622947693, "step": 900 }, { "epoch": 0.8397017707362535, "grad_norm": 0.6476941630679793, "learning_rate": 1.6002761477390404e-05, "loss": 1.0052, "step": 901 }, { "epoch": 0.8397017707362535, "loss_cot": 0.4911888539791107, "loss_nocot": 0.4276539385318756, "step": 901 }, { "epoch": 0.8406337371854613, "grad_norm": 0.5822895078245219, "learning_rate": 1.5995857783914396e-05, "loss": 0.9056, "step": 902 }, { "epoch": 0.8406337371854613, "loss_cot": 0.5427792072296143, "loss_nocot": 0.44847342371940613, "step": 902 }, { "epoch": 0.8415657036346692, "grad_norm": 0.6524119472756803, "learning_rate": 1.5988954090438385e-05, "loss": 1.0276, "step": 903 }, { "epoch": 0.8415657036346692, "loss_cot": 0.5089203119277954, "loss_nocot": 0.3166668713092804, "step": 903 }, { "epoch": 0.842497670083877, "grad_norm": 0.6637859672752074, "learning_rate": 1.5982050396962378e-05, "loss": 0.9462, "step": 904 }, { "epoch": 0.842497670083877, "loss_cot": 0.46074026823043823, "loss_nocot": 0.46121495962142944, "step": 904 }, { "epoch": 0.8434296365330848, "grad_norm": 0.6851174550196527, "learning_rate": 1.5975146703486367e-05, "loss": 1.0077, "step": 905 }, { "epoch": 0.8434296365330848, "loss_cot": 0.6637627482414246, "loss_nocot": 0.5662970542907715, "step": 905 }, { "epoch": 0.8443616029822927, "grad_norm": 0.7018601986945051, "learning_rate": 1.5968243010010356e-05, "loss": 1.0601, "step": 906 }, { "epoch": 0.8443616029822927, "loss_cot": 0.5785327553749084, "loss_nocot": 0.4275818169116974, "step": 906 }, { "epoch": 0.8452935694315005, "grad_norm": 0.6082252033599196, "learning_rate": 1.5961339316534348e-05, "loss": 0.9732, "step": 907 }, { "epoch": 0.8452935694315005, "loss_cot": 0.5226367712020874, "loss_nocot": 0.47043704986572266, "step": 907 }, { "epoch": 0.8462255358807083, "grad_norm": 0.6673894604872004, "learning_rate": 1.5954435623058337e-05, "loss": 0.955, "step": 908 }, { "epoch": 0.8462255358807083, "loss_cot": 0.5115325450897217, "loss_nocot": 0.33661192655563354, "step": 908 }, { "epoch": 0.8471575023299162, "grad_norm": 0.6340727201264363, "learning_rate": 1.5947531929582326e-05, "loss": 0.9501, "step": 909 }, { "epoch": 0.8471575023299162, "loss_cot": 0.5228753089904785, "loss_nocot": 0.3860267400741577, "step": 909 }, { "epoch": 0.848089468779124, "grad_norm": 0.6662111985001217, "learning_rate": 1.594062823610632e-05, "loss": 0.9501, "step": 910 }, { "epoch": 0.848089468779124, "loss_cot": 0.4847356975078583, "loss_nocot": 0.5627145171165466, "step": 910 }, { "epoch": 0.8490214352283317, "grad_norm": 0.5897540800212807, "learning_rate": 1.5933724542630308e-05, "loss": 0.9736, "step": 911 }, { "epoch": 0.8490214352283317, "loss_cot": 0.5090354084968567, "loss_nocot": 0.44023117423057556, "step": 911 }, { "epoch": 0.8499534016775396, "grad_norm": 0.6421409637343554, "learning_rate": 1.59268208491543e-05, "loss": 0.9578, "step": 912 }, { "epoch": 0.8499534016775396, "loss_cot": 0.5801595449447632, "loss_nocot": 0.37633436918258667, "step": 912 }, { "epoch": 0.8508853681267474, "grad_norm": 0.6825165143017744, "learning_rate": 1.591991715567829e-05, "loss": 1.0068, "step": 913 }, { "epoch": 0.8508853681267474, "loss_cot": 0.5645138621330261, "loss_nocot": 0.4020874798297882, "step": 913 }, { "epoch": 0.8518173345759553, "grad_norm": 1.2775663290497064, "learning_rate": 1.591301346220228e-05, "loss": 0.9897, "step": 914 }, { "epoch": 0.8518173345759553, "loss_cot": 0.47112759947776794, "loss_nocot": 0.48582470417022705, "step": 914 }, { "epoch": 0.8527493010251631, "grad_norm": 0.6638126947002089, "learning_rate": 1.590610976872627e-05, "loss": 1.0484, "step": 915 }, { "epoch": 0.8527493010251631, "loss_cot": 0.5179150700569153, "loss_nocot": 0.48055750131607056, "step": 915 }, { "epoch": 0.8536812674743709, "grad_norm": 0.6240328698899466, "learning_rate": 1.589920607525026e-05, "loss": 0.942, "step": 916 }, { "epoch": 0.8536812674743709, "loss_cot": 0.5735864043235779, "loss_nocot": 0.5241096615791321, "step": 916 }, { "epoch": 0.8546132339235788, "grad_norm": 0.6264936269141895, "learning_rate": 1.589230238177425e-05, "loss": 0.9921, "step": 917 }, { "epoch": 0.8546132339235788, "loss_cot": 0.5038743019104004, "loss_nocot": 0.49533021450042725, "step": 917 }, { "epoch": 0.8555452003727866, "grad_norm": 0.6166237852497857, "learning_rate": 1.588539868829824e-05, "loss": 0.9322, "step": 918 }, { "epoch": 0.8555452003727866, "loss_cot": 0.5393151640892029, "loss_nocot": 0.4816945195198059, "step": 918 }, { "epoch": 0.8564771668219944, "grad_norm": 0.6854629901175895, "learning_rate": 1.587849499482223e-05, "loss": 1.0579, "step": 919 }, { "epoch": 0.8564771668219944, "loss_cot": 0.5975088477134705, "loss_nocot": 0.4228915572166443, "step": 919 }, { "epoch": 0.8574091332712023, "grad_norm": 0.6236688563024185, "learning_rate": 1.5871591301346222e-05, "loss": 1.0022, "step": 920 }, { "epoch": 0.8574091332712023, "loss_cot": 0.46668803691864014, "loss_nocot": 0.5131195187568665, "step": 920 }, { "epoch": 0.8583410997204101, "grad_norm": 0.6457802343798437, "learning_rate": 1.586468760787021e-05, "loss": 0.9748, "step": 921 }, { "epoch": 0.8583410997204101, "loss_cot": 0.5337077975273132, "loss_nocot": 0.46173667907714844, "step": 921 }, { "epoch": 0.8592730661696178, "grad_norm": 0.6636667353753957, "learning_rate": 1.5857783914394204e-05, "loss": 0.9847, "step": 922 }, { "epoch": 0.8592730661696178, "loss_cot": 0.5418111681938171, "loss_nocot": 0.2483246922492981, "step": 922 }, { "epoch": 0.8602050326188257, "grad_norm": 0.6257366371772093, "learning_rate": 1.5850880220918193e-05, "loss": 0.9327, "step": 923 }, { "epoch": 0.8602050326188257, "loss_cot": 0.5156156420707703, "loss_nocot": 0.4221052825450897, "step": 923 }, { "epoch": 0.8611369990680335, "grad_norm": 0.6827479562481019, "learning_rate": 1.5843976527442182e-05, "loss": 1.0616, "step": 924 }, { "epoch": 0.8611369990680335, "loss_cot": 0.5410165190696716, "loss_nocot": 0.5864274501800537, "step": 924 }, { "epoch": 0.8620689655172413, "grad_norm": 0.6334803444067144, "learning_rate": 1.5837072833966174e-05, "loss": 1.0051, "step": 925 }, { "epoch": 0.8620689655172413, "loss_cot": 0.49687546491622925, "loss_nocot": 0.5320568084716797, "step": 925 }, { "epoch": 0.8630009319664492, "grad_norm": 0.6636333624456854, "learning_rate": 1.5830169140490164e-05, "loss": 0.9943, "step": 926 }, { "epoch": 0.8630009319664492, "loss_cot": 0.5370995998382568, "loss_nocot": 0.4003499746322632, "step": 926 }, { "epoch": 0.863932898415657, "grad_norm": 0.6155486631180741, "learning_rate": 1.5823265447014153e-05, "loss": 0.954, "step": 927 }, { "epoch": 0.863932898415657, "loss_cot": 0.5104483962059021, "loss_nocot": 0.413277268409729, "step": 927 }, { "epoch": 0.8648648648648649, "grad_norm": 0.6204848069636741, "learning_rate": 1.5816361753538145e-05, "loss": 0.9223, "step": 928 }, { "epoch": 0.8648648648648649, "loss_cot": 0.539362907409668, "loss_nocot": 0.4710063636302948, "step": 928 }, { "epoch": 0.8657968313140727, "grad_norm": 0.6939985087200842, "learning_rate": 1.5809458060062134e-05, "loss": 0.9804, "step": 929 }, { "epoch": 0.8657968313140727, "loss_cot": 0.5130277276039124, "loss_nocot": 0.4288175702095032, "step": 929 }, { "epoch": 0.8667287977632805, "grad_norm": 0.6795103244084738, "learning_rate": 1.5802554366586126e-05, "loss": 1.0148, "step": 930 }, { "epoch": 0.8667287977632805, "loss_cot": 0.49960416555404663, "loss_nocot": 0.3927021026611328, "step": 930 }, { "epoch": 0.8676607642124884, "grad_norm": 0.6973964335934857, "learning_rate": 1.5795650673110115e-05, "loss": 1.0225, "step": 931 }, { "epoch": 0.8676607642124884, "loss_cot": 0.5319132804870605, "loss_nocot": 0.4302036166191101, "step": 931 }, { "epoch": 0.8685927306616962, "grad_norm": 0.6330209262995644, "learning_rate": 1.5788746979634108e-05, "loss": 0.988, "step": 932 }, { "epoch": 0.8685927306616962, "loss_cot": 0.583099365234375, "loss_nocot": 0.37579041719436646, "step": 932 }, { "epoch": 0.869524697110904, "grad_norm": 0.6389963130179203, "learning_rate": 1.5781843286158097e-05, "loss": 0.9624, "step": 933 }, { "epoch": 0.869524697110904, "loss_cot": 0.5471342206001282, "loss_nocot": 0.41685938835144043, "step": 933 }, { "epoch": 0.8704566635601119, "grad_norm": 0.6041863017977668, "learning_rate": 1.5774939592682086e-05, "loss": 0.9458, "step": 934 }, { "epoch": 0.8704566635601119, "loss_cot": 0.5136797428131104, "loss_nocot": 0.4436941146850586, "step": 934 }, { "epoch": 0.8713886300093197, "grad_norm": 0.6723328605833312, "learning_rate": 1.5768035899206075e-05, "loss": 1.0342, "step": 935 }, { "epoch": 0.8713886300093197, "loss_cot": 0.5545135736465454, "loss_nocot": 0.5212368369102478, "step": 935 }, { "epoch": 0.8723205964585274, "grad_norm": 0.606199418983036, "learning_rate": 1.5761132205730067e-05, "loss": 0.9627, "step": 936 }, { "epoch": 0.8723205964585274, "loss_cot": 0.5030509233474731, "loss_nocot": 0.4580974876880646, "step": 936 }, { "epoch": 0.8732525629077353, "grad_norm": 0.6198790522516314, "learning_rate": 1.5754228512254056e-05, "loss": 0.9564, "step": 937 }, { "epoch": 0.8732525629077353, "loss_cot": 0.46897363662719727, "loss_nocot": 0.34769755601882935, "step": 937 }, { "epoch": 0.8741845293569431, "grad_norm": 0.6340204239765878, "learning_rate": 1.5747324818778046e-05, "loss": 0.9488, "step": 938 }, { "epoch": 0.8741845293569431, "loss_cot": 0.5687319040298462, "loss_nocot": 0.44783663749694824, "step": 938 }, { "epoch": 0.875116495806151, "grad_norm": 0.6865179705788844, "learning_rate": 1.5740421125302038e-05, "loss": 1.0631, "step": 939 }, { "epoch": 0.875116495806151, "loss_cot": 0.5552887916564941, "loss_nocot": 0.5785829424858093, "step": 939 }, { "epoch": 0.8760484622553588, "grad_norm": 0.6363256961788814, "learning_rate": 1.5733517431826027e-05, "loss": 1.008, "step": 940 }, { "epoch": 0.8760484622553588, "loss_cot": 0.4727950990200043, "loss_nocot": 0.3541603684425354, "step": 940 }, { "epoch": 0.8769804287045666, "grad_norm": 0.590641385952506, "learning_rate": 1.572661373835002e-05, "loss": 0.9138, "step": 941 }, { "epoch": 0.8769804287045666, "loss_cot": 0.5002965331077576, "loss_nocot": 0.3809148967266083, "step": 941 }, { "epoch": 0.8779123951537745, "grad_norm": 0.6281566451048636, "learning_rate": 1.571971004487401e-05, "loss": 0.972, "step": 942 }, { "epoch": 0.8779123951537745, "loss_cot": 0.5580909252166748, "loss_nocot": 0.3781876266002655, "step": 942 }, { "epoch": 0.8788443616029823, "grad_norm": 0.6253051030798399, "learning_rate": 1.5712806351398e-05, "loss": 0.9688, "step": 943 }, { "epoch": 0.8788443616029823, "loss_cot": 0.5716970562934875, "loss_nocot": 0.38083410263061523, "step": 943 }, { "epoch": 0.8797763280521901, "grad_norm": 0.5970629170014718, "learning_rate": 1.570590265792199e-05, "loss": 0.9603, "step": 944 }, { "epoch": 0.8797763280521901, "loss_cot": 0.5284870862960815, "loss_nocot": 0.46125513315200806, "step": 944 }, { "epoch": 0.880708294501398, "grad_norm": 0.5947926106438685, "learning_rate": 1.569899896444598e-05, "loss": 0.9346, "step": 945 }, { "epoch": 0.880708294501398, "loss_cot": 0.4945991039276123, "loss_nocot": 0.38777315616607666, "step": 945 }, { "epoch": 0.8816402609506058, "grad_norm": 0.6069442636015568, "learning_rate": 1.5692095270969968e-05, "loss": 0.9592, "step": 946 }, { "epoch": 0.8816402609506058, "loss_cot": 0.5139039754867554, "loss_nocot": 0.36079031229019165, "step": 946 }, { "epoch": 0.8825722273998136, "grad_norm": 0.6059777223485067, "learning_rate": 1.568519157749396e-05, "loss": 0.9603, "step": 947 }, { "epoch": 0.8825722273998136, "loss_cot": 0.5783287286758423, "loss_nocot": 0.3627496361732483, "step": 947 }, { "epoch": 0.8835041938490215, "grad_norm": 0.6204724830081686, "learning_rate": 1.567828788401795e-05, "loss": 0.9665, "step": 948 }, { "epoch": 0.8835041938490215, "loss_cot": 0.5329154133796692, "loss_nocot": 0.5277366638183594, "step": 948 }, { "epoch": 0.8844361602982292, "grad_norm": 0.6277750185290365, "learning_rate": 1.5671384190541942e-05, "loss": 0.9813, "step": 949 }, { "epoch": 0.8844361602982292, "loss_cot": 0.5449846386909485, "loss_nocot": 0.4230285882949829, "step": 949 }, { "epoch": 0.8853681267474371, "grad_norm": 0.6192545872987335, "learning_rate": 1.566448049706593e-05, "loss": 0.9779, "step": 950 }, { "epoch": 0.8853681267474371, "loss_cot": 0.4913126826286316, "loss_nocot": 0.39062705636024475, "step": 950 }, { "epoch": 0.8863000931966449, "grad_norm": 0.5676036851920264, "learning_rate": 1.5657576803589923e-05, "loss": 0.9028, "step": 951 }, { "epoch": 0.8863000931966449, "loss_cot": 0.5621998310089111, "loss_nocot": 0.3823056221008301, "step": 951 }, { "epoch": 0.8872320596458527, "grad_norm": 0.6697284728889564, "learning_rate": 1.5650673110113912e-05, "loss": 0.9625, "step": 952 }, { "epoch": 0.8872320596458527, "loss_cot": 0.6326028108596802, "loss_nocot": 0.42828959226608276, "step": 952 }, { "epoch": 0.8881640260950606, "grad_norm": 0.6319584670478884, "learning_rate": 1.56437694166379e-05, "loss": 1.0309, "step": 953 }, { "epoch": 0.8881640260950606, "loss_cot": 0.5146369934082031, "loss_nocot": 0.5316677093505859, "step": 953 }, { "epoch": 0.8890959925442684, "grad_norm": 0.6361918142028886, "learning_rate": 1.5636865723161894e-05, "loss": 1.0023, "step": 954 }, { "epoch": 0.8890959925442684, "loss_cot": 0.48937350511550903, "loss_nocot": 0.4221456050872803, "step": 954 }, { "epoch": 0.8900279589934762, "grad_norm": 0.6235128200220894, "learning_rate": 1.5629962029685883e-05, "loss": 0.9983, "step": 955 }, { "epoch": 0.8900279589934762, "loss_cot": 0.5335060358047485, "loss_nocot": 0.4238729476928711, "step": 955 }, { "epoch": 0.8909599254426841, "grad_norm": 0.5752459838652123, "learning_rate": 1.5623058336209872e-05, "loss": 0.9151, "step": 956 }, { "epoch": 0.8909599254426841, "loss_cot": 0.5859730243682861, "loss_nocot": 0.460304856300354, "step": 956 }, { "epoch": 0.8918918918918919, "grad_norm": 0.627048823097109, "learning_rate": 1.5616154642733864e-05, "loss": 1.0099, "step": 957 }, { "epoch": 0.8918918918918919, "loss_cot": 0.5710284113883972, "loss_nocot": 0.33249184489250183, "step": 957 }, { "epoch": 0.8928238583410997, "grad_norm": 0.6200484134321017, "learning_rate": 1.5609250949257853e-05, "loss": 0.9284, "step": 958 }, { "epoch": 0.8928238583410997, "loss_cot": 0.5324417352676392, "loss_nocot": 0.4742509722709656, "step": 958 }, { "epoch": 0.8937558247903076, "grad_norm": 0.6108634515206228, "learning_rate": 1.5602347255781846e-05, "loss": 0.9373, "step": 959 }, { "epoch": 0.8937558247903076, "loss_cot": 0.4525212049484253, "loss_nocot": 0.3087655305862427, "step": 959 }, { "epoch": 0.8946877912395154, "grad_norm": 0.595389860929834, "learning_rate": 1.5595443562305835e-05, "loss": 0.9217, "step": 960 }, { "epoch": 0.8946877912395154, "loss_cot": 0.5253559947013855, "loss_nocot": 0.5016927719116211, "step": 960 }, { "epoch": 0.8956197576887233, "grad_norm": 0.6477279640474649, "learning_rate": 1.5588539868829827e-05, "loss": 0.9759, "step": 961 }, { "epoch": 0.8956197576887233, "loss_cot": 0.503751277923584, "loss_nocot": 0.3523825407028198, "step": 961 }, { "epoch": 0.896551724137931, "grad_norm": 0.5922645659192031, "learning_rate": 1.5581636175353816e-05, "loss": 0.8895, "step": 962 }, { "epoch": 0.896551724137931, "loss_cot": 0.4562985599040985, "loss_nocot": 0.4192506968975067, "step": 962 }, { "epoch": 0.8974836905871388, "grad_norm": 0.6419612332769699, "learning_rate": 1.5574732481877805e-05, "loss": 0.9566, "step": 963 }, { "epoch": 0.8974836905871388, "loss_cot": 0.49935418367385864, "loss_nocot": 0.5068681240081787, "step": 963 }, { "epoch": 0.8984156570363467, "grad_norm": 0.6125676621241216, "learning_rate": 1.5567828788401794e-05, "loss": 0.9299, "step": 964 }, { "epoch": 0.8984156570363467, "loss_cot": 0.4889518618583679, "loss_nocot": 0.49172914028167725, "step": 964 }, { "epoch": 0.8993476234855545, "grad_norm": 0.6330886747859829, "learning_rate": 1.5560925094925787e-05, "loss": 0.9791, "step": 965 }, { "epoch": 0.8993476234855545, "loss_cot": 0.4762343764305115, "loss_nocot": 0.39481276273727417, "step": 965 }, { "epoch": 0.9002795899347623, "grad_norm": 0.6487742043041398, "learning_rate": 1.5554021401449776e-05, "loss": 0.9616, "step": 966 }, { "epoch": 0.9002795899347623, "loss_cot": 0.5285073518753052, "loss_nocot": 0.3638840913772583, "step": 966 }, { "epoch": 0.9012115563839702, "grad_norm": 0.6117580774614099, "learning_rate": 1.5547117707973768e-05, "loss": 0.9603, "step": 967 }, { "epoch": 0.9012115563839702, "loss_cot": 0.4817114472389221, "loss_nocot": 0.39853280782699585, "step": 967 }, { "epoch": 0.902143522833178, "grad_norm": 0.668270554333811, "learning_rate": 1.5540214014497757e-05, "loss": 1.0066, "step": 968 }, { "epoch": 0.902143522833178, "loss_cot": 0.5346254110336304, "loss_nocot": 0.37551769614219666, "step": 968 }, { "epoch": 0.9030754892823858, "grad_norm": 0.6436167461040435, "learning_rate": 1.553331032102175e-05, "loss": 0.9889, "step": 969 }, { "epoch": 0.9030754892823858, "loss_cot": 0.48953428864479065, "loss_nocot": 0.45953813195228577, "step": 969 }, { "epoch": 0.9040074557315937, "grad_norm": 0.6039360436107732, "learning_rate": 1.552640662754574e-05, "loss": 0.928, "step": 970 }, { "epoch": 0.9040074557315937, "loss_cot": 0.5495775938034058, "loss_nocot": 0.41405725479125977, "step": 970 }, { "epoch": 0.9049394221808015, "grad_norm": 0.5943703924744689, "learning_rate": 1.5519502934069728e-05, "loss": 0.944, "step": 971 }, { "epoch": 0.9049394221808015, "loss_cot": 0.5689111351966858, "loss_nocot": 0.44620177149772644, "step": 971 }, { "epoch": 0.9058713886300093, "grad_norm": 0.6071660765135652, "learning_rate": 1.551259924059372e-05, "loss": 0.9668, "step": 972 }, { "epoch": 0.9058713886300093, "loss_cot": 0.5427048206329346, "loss_nocot": 0.4188537001609802, "step": 972 }, { "epoch": 0.9068033550792172, "grad_norm": 0.5863051319107342, "learning_rate": 1.550569554711771e-05, "loss": 0.9874, "step": 973 }, { "epoch": 0.9068033550792172, "loss_cot": 0.5444126129150391, "loss_nocot": 0.4215388596057892, "step": 973 }, { "epoch": 0.907735321528425, "grad_norm": 0.7000694990062564, "learning_rate": 1.54987918536417e-05, "loss": 1.077, "step": 974 }, { "epoch": 0.907735321528425, "loss_cot": 0.5230339765548706, "loss_nocot": 0.6156208515167236, "step": 974 }, { "epoch": 0.9086672879776329, "grad_norm": 0.6138962609948776, "learning_rate": 1.5491888160165687e-05, "loss": 0.9471, "step": 975 }, { "epoch": 0.9086672879776329, "loss_cot": 0.5400028228759766, "loss_nocot": 0.4353976547718048, "step": 975 }, { "epoch": 0.9095992544268406, "grad_norm": 0.5896733249503124, "learning_rate": 1.548498446668968e-05, "loss": 0.9322, "step": 976 }, { "epoch": 0.9095992544268406, "loss_cot": 0.5183515548706055, "loss_nocot": 0.464523583650589, "step": 976 }, { "epoch": 0.9105312208760484, "grad_norm": 0.6059262127787862, "learning_rate": 1.5478080773213672e-05, "loss": 0.9677, "step": 977 }, { "epoch": 0.9105312208760484, "loss_cot": 0.5606117248535156, "loss_nocot": 0.3604978322982788, "step": 977 }, { "epoch": 0.9114631873252563, "grad_norm": 0.5890084510648427, "learning_rate": 1.547117707973766e-05, "loss": 0.8864, "step": 978 }, { "epoch": 0.9114631873252563, "loss_cot": 0.6152997016906738, "loss_nocot": 0.3682492673397064, "step": 978 }, { "epoch": 0.9123951537744641, "grad_norm": 0.728296141273276, "learning_rate": 1.5464273386261654e-05, "loss": 1.0124, "step": 979 }, { "epoch": 0.9123951537744641, "loss_cot": 0.558616042137146, "loss_nocot": 0.42735058069229126, "step": 979 }, { "epoch": 0.9133271202236719, "grad_norm": 0.6526720956680654, "learning_rate": 1.5457369692785643e-05, "loss": 1.0144, "step": 980 }, { "epoch": 0.9133271202236719, "loss_cot": 0.5312148928642273, "loss_nocot": 0.5035737752914429, "step": 980 }, { "epoch": 0.9142590866728798, "grad_norm": 0.6927064345835773, "learning_rate": 1.5450465999309632e-05, "loss": 0.9885, "step": 981 }, { "epoch": 0.9142590866728798, "loss_cot": 0.4671430289745331, "loss_nocot": 0.5559655427932739, "step": 981 }, { "epoch": 0.9151910531220876, "grad_norm": 0.6384204574426835, "learning_rate": 1.544356230583362e-05, "loss": 0.9393, "step": 982 }, { "epoch": 0.9151910531220876, "loss_cot": 0.5538814663887024, "loss_nocot": 0.34216201305389404, "step": 982 }, { "epoch": 0.9161230195712954, "grad_norm": 0.6468330264217227, "learning_rate": 1.5436658612357613e-05, "loss": 1.008, "step": 983 }, { "epoch": 0.9161230195712954, "loss_cot": 0.5370481014251709, "loss_nocot": 0.5622095465660095, "step": 983 }, { "epoch": 0.9170549860205033, "grad_norm": 0.8274685736449531, "learning_rate": 1.5429754918881602e-05, "loss": 1.119, "step": 984 }, { "epoch": 0.9170549860205033, "loss_cot": 0.6676973104476929, "loss_nocot": 0.4398793876171112, "step": 984 }, { "epoch": 0.9179869524697111, "grad_norm": 0.6657402399226411, "learning_rate": 1.542285122540559e-05, "loss": 1.0231, "step": 985 }, { "epoch": 0.9179869524697111, "loss_cot": 0.5003435015678406, "loss_nocot": 0.39386439323425293, "step": 985 }, { "epoch": 0.918918918918919, "grad_norm": 0.6626686048613355, "learning_rate": 1.5415947531929584e-05, "loss": 1.0122, "step": 986 }, { "epoch": 0.918918918918919, "loss_cot": 0.5473120808601379, "loss_nocot": 0.326051265001297, "step": 986 }, { "epoch": 0.9198508853681268, "grad_norm": 0.6355601474314799, "learning_rate": 1.5409043838453576e-05, "loss": 0.966, "step": 987 }, { "epoch": 0.9198508853681268, "loss_cot": 0.5902646780014038, "loss_nocot": 0.39517271518707275, "step": 987 }, { "epoch": 0.9207828518173345, "grad_norm": 0.5943449207831546, "learning_rate": 1.5402140144977565e-05, "loss": 0.9321, "step": 988 }, { "epoch": 0.9207828518173345, "loss_cot": 0.5668825507164001, "loss_nocot": 0.49261948466300964, "step": 988 }, { "epoch": 0.9217148182665424, "grad_norm": 0.7677518038117592, "learning_rate": 1.5395236451501554e-05, "loss": 0.9567, "step": 989 }, { "epoch": 0.9217148182665424, "loss_cot": 0.5487936735153198, "loss_nocot": 0.42687588930130005, "step": 989 }, { "epoch": 0.9226467847157502, "grad_norm": 0.6377688237165484, "learning_rate": 1.5388332758025547e-05, "loss": 1.0122, "step": 990 }, { "epoch": 0.9226467847157502, "loss_cot": 0.5257939696311951, "loss_nocot": 0.3920707702636719, "step": 990 }, { "epoch": 0.923578751164958, "grad_norm": 0.593678612852931, "learning_rate": 1.5381429064549536e-05, "loss": 0.9464, "step": 991 }, { "epoch": 0.923578751164958, "loss_cot": 0.5607371926307678, "loss_nocot": 0.36900264024734497, "step": 991 }, { "epoch": 0.9245107176141659, "grad_norm": 0.6284172893087415, "learning_rate": 1.5374525371073525e-05, "loss": 0.9757, "step": 992 }, { "epoch": 0.9245107176141659, "loss_cot": 0.5771471261978149, "loss_nocot": 0.32852643728256226, "step": 992 }, { "epoch": 0.9254426840633737, "grad_norm": 0.6257577393266697, "learning_rate": 1.5367621677597514e-05, "loss": 0.9529, "step": 993 }, { "epoch": 0.9254426840633737, "loss_cot": 0.5956746339797974, "loss_nocot": 0.4953715205192566, "step": 993 }, { "epoch": 0.9263746505125815, "grad_norm": 0.656449772715412, "learning_rate": 1.5360717984121506e-05, "loss": 1.0225, "step": 994 }, { "epoch": 0.9263746505125815, "loss_cot": 0.4966448247432709, "loss_nocot": 0.47232183814048767, "step": 994 }, { "epoch": 0.9273066169617894, "grad_norm": 0.62451619203449, "learning_rate": 1.5353814290645495e-05, "loss": 0.9678, "step": 995 }, { "epoch": 0.9273066169617894, "loss_cot": 0.47466978430747986, "loss_nocot": 0.5094864368438721, "step": 995 }, { "epoch": 0.9282385834109972, "grad_norm": 0.6339562254620031, "learning_rate": 1.5346910597169488e-05, "loss": 0.9828, "step": 996 }, { "epoch": 0.9282385834109972, "loss_cot": 0.4912724792957306, "loss_nocot": 0.4714902639389038, "step": 996 }, { "epoch": 0.9291705498602051, "grad_norm": 0.6805499362645491, "learning_rate": 1.5340006903693477e-05, "loss": 0.9955, "step": 997 }, { "epoch": 0.9291705498602051, "loss_cot": 0.444607138633728, "loss_nocot": 0.40651100873947144, "step": 997 }, { "epoch": 0.9301025163094129, "grad_norm": 0.5986283060316985, "learning_rate": 1.533310321021747e-05, "loss": 0.9281, "step": 998 }, { "epoch": 0.9301025163094129, "loss_cot": 0.5367223620414734, "loss_nocot": 0.5231203436851501, "step": 998 }, { "epoch": 0.9310344827586207, "grad_norm": 0.6811585476410841, "learning_rate": 1.5326199516741458e-05, "loss": 1.0533, "step": 999 }, { "epoch": 0.9310344827586207, "loss_cot": 0.5574831962585449, "loss_nocot": 0.32232972979545593, "step": 999 }, { "epoch": 0.9319664492078286, "grad_norm": 0.5798908360941399, "learning_rate": 1.5319295823265447e-05, "loss": 0.9377, "step": 1000 }, { "epoch": 0.9319664492078286, "loss_cot": 0.5278841257095337, "loss_nocot": 0.46084511280059814, "step": 1000 }, { "epoch": 0.9328984156570364, "grad_norm": 0.5872465875635021, "learning_rate": 1.531239212978944e-05, "loss": 0.9038, "step": 1001 }, { "epoch": 0.9328984156570364, "loss_cot": 0.4799790680408478, "loss_nocot": 0.4216497242450714, "step": 1001 }, { "epoch": 0.9338303821062441, "grad_norm": 0.6555095291311706, "learning_rate": 1.530548843631343e-05, "loss": 1.0359, "step": 1002 }, { "epoch": 0.9338303821062441, "loss_cot": 0.5131173133850098, "loss_nocot": 0.33138054609298706, "step": 1002 }, { "epoch": 0.934762348555452, "grad_norm": 0.5428143544528876, "learning_rate": 1.5298584742837418e-05, "loss": 0.8841, "step": 1003 }, { "epoch": 0.934762348555452, "loss_cot": 0.5066402554512024, "loss_nocot": 0.43513578176498413, "step": 1003 }, { "epoch": 0.9356943150046598, "grad_norm": 0.6531549943964603, "learning_rate": 1.529168104936141e-05, "loss": 1.0055, "step": 1004 }, { "epoch": 0.9356943150046598, "loss_cot": 0.5514756441116333, "loss_nocot": 0.5159157514572144, "step": 1004 }, { "epoch": 0.9366262814538676, "grad_norm": 0.6987165632715969, "learning_rate": 1.52847773558854e-05, "loss": 1.0481, "step": 1005 }, { "epoch": 0.9366262814538676, "loss_cot": 0.5182069540023804, "loss_nocot": 0.5222289562225342, "step": 1005 }, { "epoch": 0.9375582479030755, "grad_norm": 0.7199354800366383, "learning_rate": 1.527787366240939e-05, "loss": 1.0075, "step": 1006 }, { "epoch": 0.9375582479030755, "loss_cot": 0.5804667472839355, "loss_nocot": 0.6106528043746948, "step": 1006 }, { "epoch": 0.9384902143522833, "grad_norm": 0.6252379346703276, "learning_rate": 1.527096996893338e-05, "loss": 1.0397, "step": 1007 }, { "epoch": 0.9384902143522833, "loss_cot": 0.5594730377197266, "loss_nocot": 0.5132849216461182, "step": 1007 }, { "epoch": 0.9394221808014911, "grad_norm": 0.6669271353756722, "learning_rate": 1.526406627545737e-05, "loss": 0.9513, "step": 1008 }, { "epoch": 0.9394221808014911, "loss_cot": 0.537695050239563, "loss_nocot": 0.40394866466522217, "step": 1008 }, { "epoch": 0.940354147250699, "grad_norm": 0.6308911825687961, "learning_rate": 1.5257162581981362e-05, "loss": 1.0213, "step": 1009 }, { "epoch": 0.940354147250699, "loss_cot": 0.5733052492141724, "loss_nocot": 0.5408420562744141, "step": 1009 }, { "epoch": 0.9412861136999068, "grad_norm": 0.8052840367085966, "learning_rate": 1.5250258888505351e-05, "loss": 0.9881, "step": 1010 }, { "epoch": 0.9412861136999068, "loss_cot": 0.5545737743377686, "loss_nocot": 0.44127368927001953, "step": 1010 }, { "epoch": 0.9422180801491147, "grad_norm": 0.5982092678117025, "learning_rate": 1.5243355195029342e-05, "loss": 0.9654, "step": 1011 }, { "epoch": 0.9422180801491147, "loss_cot": 0.4883647859096527, "loss_nocot": 0.44995418190956116, "step": 1011 }, { "epoch": 0.9431500465983225, "grad_norm": 0.674131147160806, "learning_rate": 1.5236451501553333e-05, "loss": 0.9421, "step": 1012 }, { "epoch": 0.9431500465983225, "loss_cot": 0.4909743666648865, "loss_nocot": 0.411740779876709, "step": 1012 }, { "epoch": 0.9440820130475303, "grad_norm": 0.6152350888065222, "learning_rate": 1.5229547808077323e-05, "loss": 0.9507, "step": 1013 }, { "epoch": 0.9440820130475303, "loss_cot": 0.5655925869941711, "loss_nocot": 0.3636191487312317, "step": 1013 }, { "epoch": 0.9450139794967382, "grad_norm": 0.588118974417869, "learning_rate": 1.5222644114601312e-05, "loss": 0.9334, "step": 1014 }, { "epoch": 0.9450139794967382, "loss_cot": 0.5199223160743713, "loss_nocot": 0.35466212034225464, "step": 1014 }, { "epoch": 0.9459459459459459, "grad_norm": 0.7705582091940021, "learning_rate": 1.5215740421125303e-05, "loss": 0.9671, "step": 1015 }, { "epoch": 0.9459459459459459, "loss_cot": 0.513310968875885, "loss_nocot": 0.5024242401123047, "step": 1015 }, { "epoch": 0.9468779123951537, "grad_norm": 0.6833272054413309, "learning_rate": 1.5208836727649294e-05, "loss": 1.0942, "step": 1016 }, { "epoch": 0.9468779123951537, "loss_cot": 0.5697188973426819, "loss_nocot": 0.3764241337776184, "step": 1016 }, { "epoch": 0.9478098788443616, "grad_norm": 0.5971002288748408, "learning_rate": 1.5201933034173285e-05, "loss": 0.9387, "step": 1017 }, { "epoch": 0.9478098788443616, "loss_cot": 0.5111895799636841, "loss_nocot": 0.42020970582962036, "step": 1017 }, { "epoch": 0.9487418452935694, "grad_norm": 0.7711071660692327, "learning_rate": 1.5195029340697274e-05, "loss": 1.0551, "step": 1018 }, { "epoch": 0.9487418452935694, "loss_cot": 0.5929569602012634, "loss_nocot": 0.38038134574890137, "step": 1018 }, { "epoch": 0.9496738117427772, "grad_norm": 0.5900537384274348, "learning_rate": 1.5188125647221266e-05, "loss": 0.944, "step": 1019 }, { "epoch": 0.9496738117427772, "loss_cot": 0.46845269203186035, "loss_nocot": 0.5463449954986572, "step": 1019 }, { "epoch": 0.9506057781919851, "grad_norm": 0.6515733631336627, "learning_rate": 1.5181221953745255e-05, "loss": 1.0014, "step": 1020 }, { "epoch": 0.9506057781919851, "loss_cot": 0.4809418320655823, "loss_nocot": 0.3608117699623108, "step": 1020 }, { "epoch": 0.9515377446411929, "grad_norm": 0.6313833698273811, "learning_rate": 1.5174318260269246e-05, "loss": 0.9487, "step": 1021 }, { "epoch": 0.9515377446411929, "loss_cot": 0.5547662973403931, "loss_nocot": 0.33301180601119995, "step": 1021 }, { "epoch": 0.9524697110904008, "grad_norm": 0.7171225567868286, "learning_rate": 1.5167414566793235e-05, "loss": 0.9796, "step": 1022 }, { "epoch": 0.9524697110904008, "loss_cot": 0.4847691059112549, "loss_nocot": 0.46570947766304016, "step": 1022 }, { "epoch": 0.9534016775396086, "grad_norm": 0.5916822993195866, "learning_rate": 1.5160510873317227e-05, "loss": 0.9181, "step": 1023 }, { "epoch": 0.9534016775396086, "loss_cot": 0.5172840356826782, "loss_nocot": 0.44075196981430054, "step": 1023 }, { "epoch": 0.9543336439888164, "grad_norm": 0.7629078722304138, "learning_rate": 1.5153607179841216e-05, "loss": 0.9697, "step": 1024 }, { "epoch": 0.9543336439888164, "loss_cot": 0.5546292066574097, "loss_nocot": 0.3324935734272003, "step": 1024 }, { "epoch": 0.9552656104380243, "grad_norm": 0.5422688256333625, "learning_rate": 1.5146703486365207e-05, "loss": 0.8864, "step": 1025 }, { "epoch": 0.9552656104380243, "loss_cot": 0.5087995529174805, "loss_nocot": 0.49680590629577637, "step": 1025 }, { "epoch": 0.9561975768872321, "grad_norm": 0.7389873328532557, "learning_rate": 1.5139799792889196e-05, "loss": 0.9249, "step": 1026 }, { "epoch": 0.9561975768872321, "loss_cot": 0.5026813745498657, "loss_nocot": 0.4250674247741699, "step": 1026 }, { "epoch": 0.9571295433364398, "grad_norm": 0.6241230219264114, "learning_rate": 1.5132896099413189e-05, "loss": 0.9948, "step": 1027 }, { "epoch": 0.9571295433364398, "loss_cot": 0.5971578359603882, "loss_nocot": 0.4730227589607239, "step": 1027 }, { "epoch": 0.9580615097856477, "grad_norm": 0.6576309548070955, "learning_rate": 1.5125992405937178e-05, "loss": 1.0336, "step": 1028 }, { "epoch": 0.9580615097856477, "loss_cot": 0.504615306854248, "loss_nocot": 0.43579620122909546, "step": 1028 }, { "epoch": 0.9589934762348555, "grad_norm": 0.6106155873099315, "learning_rate": 1.5119088712461167e-05, "loss": 0.9863, "step": 1029 }, { "epoch": 0.9589934762348555, "loss_cot": 0.48938220739364624, "loss_nocot": 0.35508543252944946, "step": 1029 }, { "epoch": 0.9599254426840633, "grad_norm": 0.6839740400414885, "learning_rate": 1.5112185018985159e-05, "loss": 0.9781, "step": 1030 }, { "epoch": 0.9599254426840633, "loss_cot": 0.5727494359016418, "loss_nocot": 0.45656025409698486, "step": 1030 }, { "epoch": 0.9608574091332712, "grad_norm": 0.6351775213589707, "learning_rate": 1.510528132550915e-05, "loss": 0.9997, "step": 1031 }, { "epoch": 0.9608574091332712, "loss_cot": 0.4514011740684509, "loss_nocot": 0.34780463576316833, "step": 1031 }, { "epoch": 0.961789375582479, "grad_norm": 0.5784870061357621, "learning_rate": 1.5098377632033139e-05, "loss": 0.9275, "step": 1032 }, { "epoch": 0.961789375582479, "loss_cot": 0.5400924682617188, "loss_nocot": 0.3982810974121094, "step": 1032 }, { "epoch": 0.9627213420316869, "grad_norm": 0.5949932594008583, "learning_rate": 1.5091473938557128e-05, "loss": 0.9512, "step": 1033 }, { "epoch": 0.9627213420316869, "loss_cot": 0.5173097848892212, "loss_nocot": 0.3687688708305359, "step": 1033 }, { "epoch": 0.9636533084808947, "grad_norm": 0.5812062299976668, "learning_rate": 1.508457024508112e-05, "loss": 0.9078, "step": 1034 }, { "epoch": 0.9636533084808947, "loss_cot": 0.5077385902404785, "loss_nocot": 0.4028598964214325, "step": 1034 }, { "epoch": 0.9645852749301025, "grad_norm": 0.66403248006052, "learning_rate": 1.5077666551605111e-05, "loss": 0.9903, "step": 1035 }, { "epoch": 0.9645852749301025, "loss_cot": 0.4977305233478546, "loss_nocot": 0.45491600036621094, "step": 1035 }, { "epoch": 0.9655172413793104, "grad_norm": 0.6564497914600724, "learning_rate": 1.50707628581291e-05, "loss": 0.9905, "step": 1036 }, { "epoch": 0.9655172413793104, "loss_cot": 0.5125761032104492, "loss_nocot": 0.35891902446746826, "step": 1036 }, { "epoch": 0.9664492078285182, "grad_norm": 0.6288240724201642, "learning_rate": 1.5063859164653089e-05, "loss": 0.9545, "step": 1037 }, { "epoch": 0.9664492078285182, "loss_cot": 0.5052803754806519, "loss_nocot": 0.29629775881767273, "step": 1037 }, { "epoch": 0.967381174277726, "grad_norm": 0.6017232994632493, "learning_rate": 1.5056955471177081e-05, "loss": 0.9546, "step": 1038 }, { "epoch": 0.967381174277726, "loss_cot": 0.5898993015289307, "loss_nocot": 0.4674534201622009, "step": 1038 }, { "epoch": 0.9683131407269339, "grad_norm": 0.6259157722246674, "learning_rate": 1.505005177770107e-05, "loss": 1.0075, "step": 1039 }, { "epoch": 0.9683131407269339, "loss_cot": 0.5278370380401611, "loss_nocot": 0.31465548276901245, "step": 1039 }, { "epoch": 0.9692451071761417, "grad_norm": 0.6143557651182667, "learning_rate": 1.5043148084225061e-05, "loss": 0.8981, "step": 1040 }, { "epoch": 0.9692451071761417, "loss_cot": 0.5576247572898865, "loss_nocot": 0.44599246978759766, "step": 1040 }, { "epoch": 0.9701770736253494, "grad_norm": 0.6447687996923867, "learning_rate": 1.5036244390749054e-05, "loss": 1.0056, "step": 1041 }, { "epoch": 0.9701770736253494, "loss_cot": 0.5057435035705566, "loss_nocot": 0.5947384238243103, "step": 1041 }, { "epoch": 0.9711090400745573, "grad_norm": 0.6202611938562752, "learning_rate": 1.5029340697273043e-05, "loss": 0.9719, "step": 1042 }, { "epoch": 0.9711090400745573, "loss_cot": 0.45965084433555603, "loss_nocot": 0.4637834131717682, "step": 1042 }, { "epoch": 0.9720410065237651, "grad_norm": 0.6005859263699208, "learning_rate": 1.5022437003797032e-05, "loss": 0.9212, "step": 1043 }, { "epoch": 0.9720410065237651, "loss_cot": 0.5197039246559143, "loss_nocot": 0.4829179644584656, "step": 1043 }, { "epoch": 0.972972972972973, "grad_norm": 0.6452921375893026, "learning_rate": 1.5015533310321023e-05, "loss": 0.9685, "step": 1044 }, { "epoch": 0.972972972972973, "loss_cot": 0.5392241477966309, "loss_nocot": 0.39752280712127686, "step": 1044 }, { "epoch": 0.9739049394221808, "grad_norm": 0.6546173617243563, "learning_rate": 1.5008629616845013e-05, "loss": 0.9996, "step": 1045 }, { "epoch": 0.9739049394221808, "loss_cot": 0.6000933647155762, "loss_nocot": 0.3757938742637634, "step": 1045 }, { "epoch": 0.9748369058713886, "grad_norm": 0.6179046819411522, "learning_rate": 1.5001725923369004e-05, "loss": 0.9819, "step": 1046 }, { "epoch": 0.9748369058713886, "loss_cot": 0.5411558151245117, "loss_nocot": 0.42810845375061035, "step": 1046 }, { "epoch": 0.9757688723205965, "grad_norm": 0.6180609289803055, "learning_rate": 1.4994822229892993e-05, "loss": 1.0018, "step": 1047 }, { "epoch": 0.9757688723205965, "loss_cot": 0.5029258131980896, "loss_nocot": 0.6580080986022949, "step": 1047 }, { "epoch": 0.9767008387698043, "grad_norm": 0.6430572042903092, "learning_rate": 1.4987918536416984e-05, "loss": 0.9934, "step": 1048 }, { "epoch": 0.9767008387698043, "loss_cot": 0.5169677734375, "loss_nocot": 0.4380176365375519, "step": 1048 }, { "epoch": 0.9776328052190121, "grad_norm": 0.5820219279169155, "learning_rate": 1.4981014842940974e-05, "loss": 0.9424, "step": 1049 }, { "epoch": 0.9776328052190121, "loss_cot": 0.5680961608886719, "loss_nocot": 0.4029449224472046, "step": 1049 }, { "epoch": 0.97856477166822, "grad_norm": 0.6494362624286081, "learning_rate": 1.4974111149464965e-05, "loss": 1.0454, "step": 1050 }, { "epoch": 0.97856477166822, "loss_cot": 0.5027568340301514, "loss_nocot": 0.3349708318710327, "step": 1050 }, { "epoch": 0.9794967381174278, "grad_norm": 0.5752077744912871, "learning_rate": 1.4967207455988954e-05, "loss": 0.8525, "step": 1051 }, { "epoch": 0.9794967381174278, "loss_cot": 0.5338367223739624, "loss_nocot": 0.3489847779273987, "step": 1051 }, { "epoch": 0.9804287045666356, "grad_norm": 0.6126949864800949, "learning_rate": 1.4960303762512947e-05, "loss": 0.9754, "step": 1052 }, { "epoch": 0.9804287045666356, "loss_cot": 0.459709107875824, "loss_nocot": 0.4146483242511749, "step": 1052 }, { "epoch": 0.9813606710158435, "grad_norm": 0.5940713889860081, "learning_rate": 1.4953400069036936e-05, "loss": 0.9062, "step": 1053 }, { "epoch": 0.9813606710158435, "loss_cot": 0.545271635055542, "loss_nocot": 0.43172773718833923, "step": 1053 }, { "epoch": 0.9822926374650512, "grad_norm": 0.6490498917901072, "learning_rate": 1.4946496375560926e-05, "loss": 1.0147, "step": 1054 }, { "epoch": 0.9822926374650512, "loss_cot": 0.5154860019683838, "loss_nocot": 0.34960001707077026, "step": 1054 }, { "epoch": 0.983224603914259, "grad_norm": 0.6504916654276979, "learning_rate": 1.4939592682084915e-05, "loss": 1.0246, "step": 1055 }, { "epoch": 0.983224603914259, "loss_cot": 0.5529017448425293, "loss_nocot": 0.3802376985549927, "step": 1055 }, { "epoch": 0.9841565703634669, "grad_norm": 0.5857313868719565, "learning_rate": 1.4932688988608908e-05, "loss": 0.9129, "step": 1056 }, { "epoch": 0.9841565703634669, "loss_cot": 0.5394028425216675, "loss_nocot": 0.37995344400405884, "step": 1056 }, { "epoch": 0.9850885368126747, "grad_norm": 0.6167861499976144, "learning_rate": 1.4925785295132897e-05, "loss": 0.9729, "step": 1057 }, { "epoch": 0.9850885368126747, "loss_cot": 0.522244930267334, "loss_nocot": 0.3019512891769409, "step": 1057 }, { "epoch": 0.9860205032618826, "grad_norm": 0.5949801120678553, "learning_rate": 1.4918881601656888e-05, "loss": 0.9323, "step": 1058 }, { "epoch": 0.9860205032618826, "loss_cot": 0.5465773940086365, "loss_nocot": 0.5479813814163208, "step": 1058 }, { "epoch": 0.9869524697110904, "grad_norm": 0.6346421656120536, "learning_rate": 1.4911977908180878e-05, "loss": 0.9649, "step": 1059 }, { "epoch": 0.9869524697110904, "loss_cot": 0.48500603437423706, "loss_nocot": 0.38209089636802673, "step": 1059 }, { "epoch": 0.9878844361602982, "grad_norm": 0.6446241117919319, "learning_rate": 1.4905074214704869e-05, "loss": 0.9202, "step": 1060 }, { "epoch": 0.9878844361602982, "loss_cot": 0.545624852180481, "loss_nocot": 0.36853185296058655, "step": 1060 }, { "epoch": 0.9888164026095061, "grad_norm": 0.6355880435881983, "learning_rate": 1.4898170521228858e-05, "loss": 0.9701, "step": 1061 }, { "epoch": 0.9888164026095061, "loss_cot": 0.5729348063468933, "loss_nocot": 0.4963279366493225, "step": 1061 }, { "epoch": 0.9897483690587139, "grad_norm": 0.6445868157710012, "learning_rate": 1.4891266827752849e-05, "loss": 1.0, "step": 1062 }, { "epoch": 0.9897483690587139, "loss_cot": 0.4812731146812439, "loss_nocot": 0.37064629793167114, "step": 1062 }, { "epoch": 0.9906803355079217, "grad_norm": 0.6535312614024633, "learning_rate": 1.488436313427684e-05, "loss": 1.0247, "step": 1063 }, { "epoch": 0.9906803355079217, "loss_cot": 0.5369276404380798, "loss_nocot": 0.4646562933921814, "step": 1063 }, { "epoch": 0.9916123019571296, "grad_norm": 0.6621399089650691, "learning_rate": 1.487745944080083e-05, "loss": 0.9464, "step": 1064 }, { "epoch": 0.9916123019571296, "loss_cot": 0.5525665879249573, "loss_nocot": 0.40957796573638916, "step": 1064 }, { "epoch": 0.9925442684063374, "grad_norm": 0.6152160390184728, "learning_rate": 1.487055574732482e-05, "loss": 0.9406, "step": 1065 }, { "epoch": 0.9925442684063374, "loss_cot": 0.5325205326080322, "loss_nocot": 0.4332118630409241, "step": 1065 }, { "epoch": 0.9934762348555451, "grad_norm": 0.5947083897539783, "learning_rate": 1.486365205384881e-05, "loss": 0.9405, "step": 1066 }, { "epoch": 0.9934762348555451, "loss_cot": 0.5054042339324951, "loss_nocot": 0.4173393249511719, "step": 1066 }, { "epoch": 0.994408201304753, "grad_norm": 0.60793393739224, "learning_rate": 1.4856748360372801e-05, "loss": 0.9279, "step": 1067 }, { "epoch": 0.994408201304753, "loss_cot": 0.5864136219024658, "loss_nocot": 0.592293381690979, "step": 1067 }, { "epoch": 0.9953401677539608, "grad_norm": 0.6570191141223616, "learning_rate": 1.4849844666896792e-05, "loss": 1.0097, "step": 1068 }, { "epoch": 0.9953401677539608, "loss_cot": 0.45756664872169495, "loss_nocot": 0.415521502494812, "step": 1068 }, { "epoch": 0.9962721342031687, "grad_norm": 0.6227839548717986, "learning_rate": 1.484294097342078e-05, "loss": 0.9732, "step": 1069 }, { "epoch": 0.9962721342031687, "loss_cot": 0.5243421792984009, "loss_nocot": 0.4610595703125, "step": 1069 }, { "epoch": 0.9972041006523765, "grad_norm": 0.6928598296457835, "learning_rate": 1.4836037279944773e-05, "loss": 0.9887, "step": 1070 }, { "epoch": 0.9972041006523765, "loss_cot": 0.514640748500824, "loss_nocot": 0.4547470211982727, "step": 1070 }, { "epoch": 0.9981360671015843, "grad_norm": 0.6418005719076904, "learning_rate": 1.4829133586468762e-05, "loss": 0.9749, "step": 1071 }, { "epoch": 0.9981360671015843, "loss_cot": 0.5109854936599731, "loss_nocot": 0.5698131322860718, "step": 1071 }, { "epoch": 0.9990680335507922, "grad_norm": 0.6870821705671244, "learning_rate": 1.4822229892992753e-05, "loss": 1.0051, "step": 1072 }, { "epoch": 0.9990680335507922, "loss_cot": 0.48051565885543823, "loss_nocot": 0.45361244678497314, "step": 1072 }, { "epoch": 1.0, "grad_norm": 0.6871205266939983, "learning_rate": 1.4815326199516742e-05, "loss": 1.0245, "step": 1073 }, { "epoch": 1.0, "loss_cot": 0.4725038707256317, "loss_nocot": 0.3286563754081726, "step": 1073 }, { "epoch": 1.0009319664492078, "grad_norm": 0.5710841049259854, "learning_rate": 1.4808422506040734e-05, "loss": 0.8465, "step": 1074 }, { "epoch": 1.0009319664492078, "loss_cot": 0.5003834962844849, "loss_nocot": 0.20632657408714294, "step": 1074 }, { "epoch": 1.0018639328984156, "grad_norm": 0.5624498690954719, "learning_rate": 1.4801518812564723e-05, "loss": 0.8543, "step": 1075 }, { "epoch": 1.0018639328984156, "loss_cot": 0.4341573417186737, "loss_nocot": 0.48016324639320374, "step": 1075 }, { "epoch": 1.0027958993476236, "grad_norm": 0.6409386581229224, "learning_rate": 1.4794615119088714e-05, "loss": 0.9251, "step": 1076 }, { "epoch": 1.0027958993476236, "loss_cot": 0.5359331965446472, "loss_nocot": 0.5158208012580872, "step": 1076 }, { "epoch": 1.0037278657968314, "grad_norm": 0.6346490535941429, "learning_rate": 1.4787711425612703e-05, "loss": 0.948, "step": 1077 }, { "epoch": 1.0037278657968314, "loss_cot": 0.5666937828063965, "loss_nocot": 0.38532721996307373, "step": 1077 }, { "epoch": 1.0046598322460392, "grad_norm": 0.7589010965830746, "learning_rate": 1.4780807732136696e-05, "loss": 0.9672, "step": 1078 }, { "epoch": 1.0046598322460392, "loss_cot": 0.5973014831542969, "loss_nocot": 0.37376511096954346, "step": 1078 }, { "epoch": 1.005591798695247, "grad_norm": 0.5849228601432485, "learning_rate": 1.4773904038660685e-05, "loss": 0.8771, "step": 1079 }, { "epoch": 1.005591798695247, "loss_cot": 0.5410674810409546, "loss_nocot": 0.3427797853946686, "step": 1079 }, { "epoch": 1.0065237651444547, "grad_norm": 0.5525801444196462, "learning_rate": 1.4767000345184674e-05, "loss": 0.8528, "step": 1080 }, { "epoch": 1.0065237651444547, "loss_cot": 0.5025793313980103, "loss_nocot": 0.4481664299964905, "step": 1080 }, { "epoch": 1.0074557315936625, "grad_norm": 0.5638184087053997, "learning_rate": 1.4760096651708666e-05, "loss": 0.8502, "step": 1081 }, { "epoch": 1.0074557315936625, "loss_cot": 0.48745155334472656, "loss_nocot": 0.30944544076919556, "step": 1081 }, { "epoch": 1.0083876980428705, "grad_norm": 0.5333065537501321, "learning_rate": 1.4753192958232657e-05, "loss": 0.8118, "step": 1082 }, { "epoch": 1.0083876980428705, "loss_cot": 0.5360758304595947, "loss_nocot": 0.3404037356376648, "step": 1082 }, { "epoch": 1.0093196644920783, "grad_norm": 0.5912257589517178, "learning_rate": 1.4746289264756646e-05, "loss": 0.8846, "step": 1083 }, { "epoch": 1.0093196644920783, "loss_cot": 0.5745646357536316, "loss_nocot": 0.4143597185611725, "step": 1083 }, { "epoch": 1.0102516309412861, "grad_norm": 0.6269597424946178, "learning_rate": 1.4739385571280635e-05, "loss": 0.8888, "step": 1084 }, { "epoch": 1.0102516309412861, "loss_cot": 0.5611474514007568, "loss_nocot": 0.3038879632949829, "step": 1084 }, { "epoch": 1.011183597390494, "grad_norm": 0.6624341548119388, "learning_rate": 1.4732481877804627e-05, "loss": 0.9535, "step": 1085 }, { "epoch": 1.011183597390494, "loss_cot": 0.5055975914001465, "loss_nocot": 0.518440842628479, "step": 1085 }, { "epoch": 1.0121155638397017, "grad_norm": 0.599472551747116, "learning_rate": 1.4725578184328618e-05, "loss": 0.8459, "step": 1086 }, { "epoch": 1.0121155638397017, "loss_cot": 0.5978081226348877, "loss_nocot": 0.3341255187988281, "step": 1086 }, { "epoch": 1.0130475302889097, "grad_norm": 0.6087620413247746, "learning_rate": 1.4718674490852607e-05, "loss": 0.9073, "step": 1087 }, { "epoch": 1.0130475302889097, "loss_cot": 0.5226515531539917, "loss_nocot": 0.420234739780426, "step": 1087 }, { "epoch": 1.0139794967381175, "grad_norm": 0.6604155048931909, "learning_rate": 1.4711770797376596e-05, "loss": 0.9856, "step": 1088 }, { "epoch": 1.0139794967381175, "loss_cot": 0.5897060632705688, "loss_nocot": 0.3040710389614105, "step": 1088 }, { "epoch": 1.0149114631873253, "grad_norm": 0.5984320453284789, "learning_rate": 1.4704867103900589e-05, "loss": 0.8873, "step": 1089 }, { "epoch": 1.0149114631873253, "loss_cot": 0.5467550754547119, "loss_nocot": 0.2937866151332855, "step": 1089 }, { "epoch": 1.015843429636533, "grad_norm": 0.6016999445585319, "learning_rate": 1.4697963410424578e-05, "loss": 0.8448, "step": 1090 }, { "epoch": 1.015843429636533, "loss_cot": 0.4934972822666168, "loss_nocot": 0.3468395471572876, "step": 1090 }, { "epoch": 1.0167753960857409, "grad_norm": 0.5814755169954906, "learning_rate": 1.4691059716948568e-05, "loss": 0.7991, "step": 1091 }, { "epoch": 1.0167753960857409, "loss_cot": 0.5448918342590332, "loss_nocot": 0.30153611302375793, "step": 1091 }, { "epoch": 1.0177073625349486, "grad_norm": 0.6769101395202284, "learning_rate": 1.468415602347256e-05, "loss": 0.9347, "step": 1092 }, { "epoch": 1.0177073625349486, "loss_cot": 0.5134238600730896, "loss_nocot": 0.3701362907886505, "step": 1092 }, { "epoch": 1.0186393289841567, "grad_norm": 0.6098968363924087, "learning_rate": 1.467725232999655e-05, "loss": 0.8686, "step": 1093 }, { "epoch": 1.0186393289841567, "loss_cot": 0.5006016492843628, "loss_nocot": 0.3603177070617676, "step": 1093 }, { "epoch": 1.0195712954333644, "grad_norm": 0.6551381876660721, "learning_rate": 1.4670348636520539e-05, "loss": 0.8928, "step": 1094 }, { "epoch": 1.0195712954333644, "loss_cot": 0.5069985389709473, "loss_nocot": 0.2924438714981079, "step": 1094 }, { "epoch": 1.0205032618825722, "grad_norm": 0.599901540170826, "learning_rate": 1.466344494304453e-05, "loss": 0.8447, "step": 1095 }, { "epoch": 1.0205032618825722, "loss_cot": 0.4785548150539398, "loss_nocot": 0.2860095500946045, "step": 1095 }, { "epoch": 1.02143522833178, "grad_norm": 0.5424223473209925, "learning_rate": 1.465654124956852e-05, "loss": 0.7824, "step": 1096 }, { "epoch": 1.02143522833178, "loss_cot": 0.48853474855422974, "loss_nocot": 0.33609867095947266, "step": 1096 }, { "epoch": 1.0223671947809878, "grad_norm": 0.6433281791815127, "learning_rate": 1.4649637556092511e-05, "loss": 0.8048, "step": 1097 }, { "epoch": 1.0223671947809878, "loss_cot": 0.5407665967941284, "loss_nocot": 0.4856705367565155, "step": 1097 }, { "epoch": 1.0232991612301958, "grad_norm": 0.5991737529925854, "learning_rate": 1.46427338626165e-05, "loss": 0.8641, "step": 1098 }, { "epoch": 1.0232991612301958, "loss_cot": 0.504170298576355, "loss_nocot": 0.30411386489868164, "step": 1098 }, { "epoch": 1.0242311276794036, "grad_norm": 0.6609600235503357, "learning_rate": 1.463583016914049e-05, "loss": 0.8717, "step": 1099 }, { "epoch": 1.0242311276794036, "loss_cot": 0.483031690120697, "loss_nocot": 0.4411487579345703, "step": 1099 }, { "epoch": 1.0251630941286114, "grad_norm": 0.6659275389202527, "learning_rate": 1.4628926475664481e-05, "loss": 0.9238, "step": 1100 }, { "epoch": 1.0251630941286114, "loss_cot": 0.5332688093185425, "loss_nocot": 0.4179835319519043, "step": 1100 }, { "epoch": 1.0260950605778192, "grad_norm": 25.313020152840235, "learning_rate": 1.4622022782188472e-05, "loss": 1.0686, "step": 1101 }, { "epoch": 1.0260950605778192, "loss_cot": 0.4939197897911072, "loss_nocot": 0.35189250111579895, "step": 1101 }, { "epoch": 1.027027027027027, "grad_norm": 0.6168283202198713, "learning_rate": 1.4615119088712461e-05, "loss": 0.8364, "step": 1102 }, { "epoch": 1.027027027027027, "loss_cot": 0.5441676378250122, "loss_nocot": 0.5019787549972534, "step": 1102 }, { "epoch": 1.0279589934762348, "grad_norm": 0.6216693611267124, "learning_rate": 1.4608215395236454e-05, "loss": 0.9107, "step": 1103 }, { "epoch": 1.0279589934762348, "loss_cot": 0.5263842344284058, "loss_nocot": 0.29920974373817444, "step": 1103 }, { "epoch": 1.0288909599254428, "grad_norm": 0.5892685264475989, "learning_rate": 1.4601311701760443e-05, "loss": 0.8278, "step": 1104 }, { "epoch": 1.0288909599254428, "loss_cot": 0.5015254020690918, "loss_nocot": 0.33836066722869873, "step": 1104 }, { "epoch": 1.0298229263746506, "grad_norm": 0.629647824386283, "learning_rate": 1.4594408008284433e-05, "loss": 0.8795, "step": 1105 }, { "epoch": 1.0298229263746506, "loss_cot": 0.47546547651290894, "loss_nocot": 0.5048177242279053, "step": 1105 }, { "epoch": 1.0307548928238583, "grad_norm": 0.7296383058600308, "learning_rate": 1.4587504314808423e-05, "loss": 0.9183, "step": 1106 }, { "epoch": 1.0307548928238583, "loss_cot": 0.5296932458877563, "loss_nocot": 0.4058492183685303, "step": 1106 }, { "epoch": 1.0316868592730661, "grad_norm": 0.7730567608440015, "learning_rate": 1.4580600621332415e-05, "loss": 0.9265, "step": 1107 }, { "epoch": 1.0316868592730661, "loss_cot": 0.5427374243736267, "loss_nocot": 0.363936185836792, "step": 1107 }, { "epoch": 1.032618825722274, "grad_norm": 0.6636497046781101, "learning_rate": 1.4573696927856404e-05, "loss": 0.9337, "step": 1108 }, { "epoch": 1.032618825722274, "loss_cot": 0.5209718942642212, "loss_nocot": 0.4774245023727417, "step": 1108 }, { "epoch": 1.0335507921714817, "grad_norm": 0.6897964024333698, "learning_rate": 1.4566793234380395e-05, "loss": 0.9068, "step": 1109 }, { "epoch": 1.0335507921714817, "loss_cot": 0.4999387562274933, "loss_nocot": 0.2595297396183014, "step": 1109 }, { "epoch": 1.0344827586206897, "grad_norm": 0.5475863499547469, "learning_rate": 1.4559889540904385e-05, "loss": 0.7993, "step": 1110 }, { "epoch": 1.0344827586206897, "loss_cot": 0.5744835138320923, "loss_nocot": 0.2580360770225525, "step": 1110 }, { "epoch": 1.0354147250698975, "grad_norm": 0.5830157433948812, "learning_rate": 1.4552985847428376e-05, "loss": 0.8517, "step": 1111 }, { "epoch": 1.0354147250698975, "loss_cot": 0.5170777440071106, "loss_nocot": 0.2715838551521301, "step": 1111 }, { "epoch": 1.0363466915191053, "grad_norm": 0.610396504085507, "learning_rate": 1.4546082153952365e-05, "loss": 0.8328, "step": 1112 }, { "epoch": 1.0363466915191053, "loss_cot": 0.5269643068313599, "loss_nocot": 0.30794772505760193, "step": 1112 }, { "epoch": 1.037278657968313, "grad_norm": 0.5749458233596244, "learning_rate": 1.4539178460476356e-05, "loss": 0.8627, "step": 1113 }, { "epoch": 1.037278657968313, "loss_cot": 0.5103540420532227, "loss_nocot": 0.3425522744655609, "step": 1113 }, { "epoch": 1.0382106244175209, "grad_norm": 0.5846917922196747, "learning_rate": 1.4532274767000347e-05, "loss": 0.8503, "step": 1114 }, { "epoch": 1.0382106244175209, "loss_cot": 0.4443153738975525, "loss_nocot": 0.39383232593536377, "step": 1114 }, { "epoch": 1.0391425908667289, "grad_norm": 0.6646884614125955, "learning_rate": 1.4525371073524337e-05, "loss": 0.9225, "step": 1115 }, { "epoch": 1.0391425908667289, "loss_cot": 0.4388062059879303, "loss_nocot": 0.5005305409431458, "step": 1115 }, { "epoch": 1.0400745573159367, "grad_norm": 0.6306402900032225, "learning_rate": 1.4518467380048326e-05, "loss": 0.8656, "step": 1116 }, { "epoch": 1.0400745573159367, "loss_cot": 0.5589820742607117, "loss_nocot": 0.330105185508728, "step": 1116 }, { "epoch": 1.0410065237651445, "grad_norm": 0.6147326750378991, "learning_rate": 1.4511563686572317e-05, "loss": 0.8564, "step": 1117 }, { "epoch": 1.0410065237651445, "loss_cot": 0.4736843705177307, "loss_nocot": 0.3331024646759033, "step": 1117 }, { "epoch": 1.0419384902143523, "grad_norm": 0.5945027351056859, "learning_rate": 1.4504659993096308e-05, "loss": 0.8427, "step": 1118 }, { "epoch": 1.0419384902143523, "loss_cot": 0.5450169444084167, "loss_nocot": 0.35544130206108093, "step": 1118 }, { "epoch": 1.04287045666356, "grad_norm": 0.7118931879504243, "learning_rate": 1.4497756299620299e-05, "loss": 0.8786, "step": 1119 }, { "epoch": 1.04287045666356, "loss_cot": 0.5035141110420227, "loss_nocot": 0.47847360372543335, "step": 1119 }, { "epoch": 1.0438024231127678, "grad_norm": 0.6930987189312974, "learning_rate": 1.4490852606144288e-05, "loss": 0.9372, "step": 1120 }, { "epoch": 1.0438024231127678, "loss_cot": 0.538343071937561, "loss_nocot": 0.3077380657196045, "step": 1120 }, { "epoch": 1.0447343895619758, "grad_norm": 0.6316888601831959, "learning_rate": 1.448394891266828e-05, "loss": 0.8661, "step": 1121 }, { "epoch": 1.0447343895619758, "loss_cot": 0.5382758378982544, "loss_nocot": 0.36595451831817627, "step": 1121 }, { "epoch": 1.0456663560111836, "grad_norm": 0.5698657708549318, "learning_rate": 1.4477045219192269e-05, "loss": 0.8692, "step": 1122 }, { "epoch": 1.0456663560111836, "loss_cot": 0.5150376558303833, "loss_nocot": 0.3369048833847046, "step": 1122 }, { "epoch": 1.0465983224603914, "grad_norm": 0.5769643429967783, "learning_rate": 1.447014152571626e-05, "loss": 0.8387, "step": 1123 }, { "epoch": 1.0465983224603914, "loss_cot": 0.5451681017875671, "loss_nocot": 0.4039088487625122, "step": 1123 }, { "epoch": 1.0475302889095992, "grad_norm": 0.6433221611545437, "learning_rate": 1.4463237832240249e-05, "loss": 0.8979, "step": 1124 }, { "epoch": 1.0475302889095992, "loss_cot": 0.5261644124984741, "loss_nocot": 0.4283146858215332, "step": 1124 }, { "epoch": 1.048462255358807, "grad_norm": 0.5904156181100714, "learning_rate": 1.4456334138764241e-05, "loss": 0.8497, "step": 1125 }, { "epoch": 1.048462255358807, "loss_cot": 0.5481706857681274, "loss_nocot": 0.3617202639579773, "step": 1125 }, { "epoch": 1.049394221808015, "grad_norm": 0.6159645500392191, "learning_rate": 1.444943044528823e-05, "loss": 0.8943, "step": 1126 }, { "epoch": 1.049394221808015, "loss_cot": 0.5914821624755859, "loss_nocot": 0.3438574969768524, "step": 1126 }, { "epoch": 1.0503261882572228, "grad_norm": 0.5763369532025956, "learning_rate": 1.4442526751812221e-05, "loss": 0.8642, "step": 1127 }, { "epoch": 1.0503261882572228, "loss_cot": 0.4890994131565094, "loss_nocot": 0.31054186820983887, "step": 1127 }, { "epoch": 1.0512581547064306, "grad_norm": 0.5833659019213384, "learning_rate": 1.443562305833621e-05, "loss": 0.8335, "step": 1128 }, { "epoch": 1.0512581547064306, "loss_cot": 0.5215123891830444, "loss_nocot": 0.3855687975883484, "step": 1128 }, { "epoch": 1.0521901211556384, "grad_norm": 0.631856278464641, "learning_rate": 1.4428719364860203e-05, "loss": 0.9113, "step": 1129 }, { "epoch": 1.0521901211556384, "loss_cot": 0.4809707999229431, "loss_nocot": 0.517609715461731, "step": 1129 }, { "epoch": 1.0531220876048462, "grad_norm": 0.6119084297857801, "learning_rate": 1.4421815671384192e-05, "loss": 0.8786, "step": 1130 }, { "epoch": 1.0531220876048462, "loss_cot": 0.5411105155944824, "loss_nocot": 0.3160632848739624, "step": 1130 }, { "epoch": 1.054054054054054, "grad_norm": 0.8332600167512104, "learning_rate": 1.441491197790818e-05, "loss": 0.9036, "step": 1131 }, { "epoch": 1.054054054054054, "loss_cot": 0.5483663082122803, "loss_nocot": 0.6006088256835938, "step": 1131 }, { "epoch": 1.054986020503262, "grad_norm": 0.6312742686986635, "learning_rate": 1.4408008284432173e-05, "loss": 0.8973, "step": 1132 }, { "epoch": 1.054986020503262, "loss_cot": 0.5084287524223328, "loss_nocot": 0.396409809589386, "step": 1132 }, { "epoch": 1.0559179869524697, "grad_norm": 0.6459925391110445, "learning_rate": 1.4401104590956164e-05, "loss": 0.9145, "step": 1133 }, { "epoch": 1.0559179869524697, "loss_cot": 0.5213051438331604, "loss_nocot": 0.38425713777542114, "step": 1133 }, { "epoch": 1.0568499534016775, "grad_norm": 0.6472325226789217, "learning_rate": 1.4394200897480153e-05, "loss": 0.8763, "step": 1134 }, { "epoch": 1.0568499534016775, "loss_cot": 0.5892985463142395, "loss_nocot": 0.31214022636413574, "step": 1134 }, { "epoch": 1.0577819198508853, "grad_norm": 0.6442001174087929, "learning_rate": 1.4387297204004142e-05, "loss": 0.8881, "step": 1135 }, { "epoch": 1.0577819198508853, "loss_cot": 0.5071302652359009, "loss_nocot": 0.3764515519142151, "step": 1135 }, { "epoch": 1.058713886300093, "grad_norm": 0.6904692534787907, "learning_rate": 1.4380393510528134e-05, "loss": 0.8788, "step": 1136 }, { "epoch": 1.058713886300093, "loss_cot": 0.5352458357810974, "loss_nocot": 0.37720948457717896, "step": 1136 }, { "epoch": 1.0596458527493011, "grad_norm": 0.6399417214263217, "learning_rate": 1.4373489817052125e-05, "loss": 0.9153, "step": 1137 }, { "epoch": 1.0596458527493011, "loss_cot": 0.5553171038627625, "loss_nocot": 0.3063725233078003, "step": 1137 }, { "epoch": 1.060577819198509, "grad_norm": 0.5995136709580751, "learning_rate": 1.4366586123576114e-05, "loss": 0.8426, "step": 1138 }, { "epoch": 1.060577819198509, "loss_cot": 0.5072603821754456, "loss_nocot": 0.2199455350637436, "step": 1138 }, { "epoch": 1.0615097856477167, "grad_norm": 0.6088556557554022, "learning_rate": 1.4359682430100103e-05, "loss": 0.8383, "step": 1139 }, { "epoch": 1.0615097856477167, "loss_cot": 0.541596531867981, "loss_nocot": 0.4232906699180603, "step": 1139 }, { "epoch": 1.0624417520969245, "grad_norm": 0.6153699904356148, "learning_rate": 1.4352778736624096e-05, "loss": 0.8946, "step": 1140 }, { "epoch": 1.0624417520969245, "loss_cot": 0.4875069260597229, "loss_nocot": 0.2978222370147705, "step": 1140 }, { "epoch": 1.0633737185461323, "grad_norm": 0.6238894258064496, "learning_rate": 1.4345875043148085e-05, "loss": 0.8549, "step": 1141 }, { "epoch": 1.0633737185461323, "loss_cot": 0.46546876430511475, "loss_nocot": 0.36249223351478577, "step": 1141 }, { "epoch": 1.06430568499534, "grad_norm": 0.590622460835773, "learning_rate": 1.4338971349672075e-05, "loss": 0.8219, "step": 1142 }, { "epoch": 1.06430568499534, "loss_cot": 0.5118206739425659, "loss_nocot": 0.2995736598968506, "step": 1142 }, { "epoch": 1.065237651444548, "grad_norm": 0.6327543989038622, "learning_rate": 1.4332067656196068e-05, "loss": 0.8835, "step": 1143 }, { "epoch": 1.065237651444548, "loss_cot": 0.47530287504196167, "loss_nocot": 0.38887858390808105, "step": 1143 }, { "epoch": 1.0661696178937559, "grad_norm": 0.938281326992134, "learning_rate": 1.4325163962720057e-05, "loss": 0.929, "step": 1144 }, { "epoch": 1.0661696178937559, "loss_cot": 0.5286458730697632, "loss_nocot": 0.40810781717300415, "step": 1144 }, { "epoch": 1.0671015843429636, "grad_norm": 0.6237739902355001, "learning_rate": 1.4318260269244046e-05, "loss": 0.8979, "step": 1145 }, { "epoch": 1.0671015843429636, "loss_cot": 0.49055200815200806, "loss_nocot": 0.3323892056941986, "step": 1145 }, { "epoch": 1.0680335507921714, "grad_norm": 0.6299429944282338, "learning_rate": 1.4311356575768037e-05, "loss": 0.8588, "step": 1146 }, { "epoch": 1.0680335507921714, "loss_cot": 0.4947749674320221, "loss_nocot": 0.3586336672306061, "step": 1146 }, { "epoch": 1.0689655172413792, "grad_norm": 0.6251105013001835, "learning_rate": 1.4304452882292027e-05, "loss": 0.8553, "step": 1147 }, { "epoch": 1.0689655172413792, "loss_cot": 0.43454810976982117, "loss_nocot": 0.27260828018188477, "step": 1147 }, { "epoch": 1.0698974836905872, "grad_norm": 0.6023892766683842, "learning_rate": 1.4297549188816018e-05, "loss": 0.8685, "step": 1148 }, { "epoch": 1.0698974836905872, "loss_cot": 0.5095653533935547, "loss_nocot": 0.22593677043914795, "step": 1148 }, { "epoch": 1.070829450139795, "grad_norm": 0.630094271886112, "learning_rate": 1.4290645495340007e-05, "loss": 0.829, "step": 1149 }, { "epoch": 1.070829450139795, "loss_cot": 0.5321608781814575, "loss_nocot": 0.2831476330757141, "step": 1149 }, { "epoch": 1.0717614165890028, "grad_norm": 0.5982330628953986, "learning_rate": 1.4283741801864e-05, "loss": 0.8468, "step": 1150 }, { "epoch": 1.0717614165890028, "loss_cot": 0.48814111948013306, "loss_nocot": 0.2846863865852356, "step": 1150 }, { "epoch": 1.0726933830382106, "grad_norm": 0.6037726700343086, "learning_rate": 1.4276838108387989e-05, "loss": 0.8272, "step": 1151 }, { "epoch": 1.0726933830382106, "loss_cot": 0.49439382553100586, "loss_nocot": 0.3562481999397278, "step": 1151 }, { "epoch": 1.0736253494874184, "grad_norm": 0.5853270844320538, "learning_rate": 1.426993441491198e-05, "loss": 0.7968, "step": 1152 }, { "epoch": 1.0736253494874184, "loss_cot": 0.565551221370697, "loss_nocot": 0.23141007125377655, "step": 1152 }, { "epoch": 1.0745573159366262, "grad_norm": 0.5877263071563951, "learning_rate": 1.4263030721435968e-05, "loss": 0.8211, "step": 1153 }, { "epoch": 1.0745573159366262, "loss_cot": 0.500131368637085, "loss_nocot": 0.34176796674728394, "step": 1153 }, { "epoch": 1.0754892823858342, "grad_norm": 0.584578731831824, "learning_rate": 1.425612702795996e-05, "loss": 0.817, "step": 1154 }, { "epoch": 1.0754892823858342, "loss_cot": 0.561673104763031, "loss_nocot": 0.3668108284473419, "step": 1154 }, { "epoch": 1.076421248835042, "grad_norm": 0.601278675287692, "learning_rate": 1.424922333448395e-05, "loss": 0.8599, "step": 1155 }, { "epoch": 1.076421248835042, "loss_cot": 0.5269356966018677, "loss_nocot": 0.3049597144126892, "step": 1155 }, { "epoch": 1.0773532152842498, "grad_norm": 0.5702283093389996, "learning_rate": 1.424231964100794e-05, "loss": 0.8288, "step": 1156 }, { "epoch": 1.0773532152842498, "loss_cot": 0.5217605233192444, "loss_nocot": 0.29909124970436096, "step": 1156 }, { "epoch": 1.0782851817334576, "grad_norm": 0.6332178680240536, "learning_rate": 1.423541594753193e-05, "loss": 0.861, "step": 1157 }, { "epoch": 1.0782851817334576, "loss_cot": 0.5762702226638794, "loss_nocot": 0.32676541805267334, "step": 1157 }, { "epoch": 1.0792171481826653, "grad_norm": 0.6471377002866548, "learning_rate": 1.4228512254055922e-05, "loss": 0.8782, "step": 1158 }, { "epoch": 1.0792171481826653, "loss_cot": 0.4919629693031311, "loss_nocot": 0.2991522550582886, "step": 1158 }, { "epoch": 1.0801491146318734, "grad_norm": 0.5964445799938722, "learning_rate": 1.4221608560579911e-05, "loss": 0.893, "step": 1159 }, { "epoch": 1.0801491146318734, "loss_cot": 0.47999414801597595, "loss_nocot": 0.37463217973709106, "step": 1159 }, { "epoch": 1.0810810810810811, "grad_norm": 0.6155637873751655, "learning_rate": 1.4214704867103902e-05, "loss": 0.8439, "step": 1160 }, { "epoch": 1.0810810810810811, "loss_cot": 0.4873160719871521, "loss_nocot": 0.3402992784976959, "step": 1160 }, { "epoch": 1.082013047530289, "grad_norm": 0.5751098968849827, "learning_rate": 1.4207801173627892e-05, "loss": 0.8275, "step": 1161 }, { "epoch": 1.082013047530289, "loss_cot": 0.5336782336235046, "loss_nocot": 0.5304980278015137, "step": 1161 }, { "epoch": 1.0829450139794967, "grad_norm": 0.6240716793555137, "learning_rate": 1.4200897480151883e-05, "loss": 0.9214, "step": 1162 }, { "epoch": 1.0829450139794967, "loss_cot": 0.5170240998268127, "loss_nocot": 0.292533814907074, "step": 1162 }, { "epoch": 1.0838769804287045, "grad_norm": 0.624415668117868, "learning_rate": 1.4193993786675872e-05, "loss": 0.8731, "step": 1163 }, { "epoch": 1.0838769804287045, "loss_cot": 0.44515755772590637, "loss_nocot": 0.2761792540550232, "step": 1163 }, { "epoch": 1.0848089468779123, "grad_norm": 0.5801405130176965, "learning_rate": 1.4187090093199863e-05, "loss": 0.8237, "step": 1164 }, { "epoch": 1.0848089468779123, "loss_cot": 0.4534538984298706, "loss_nocot": 0.3617953062057495, "step": 1164 }, { "epoch": 1.0857409133271203, "grad_norm": 0.7291548474846696, "learning_rate": 1.4180186399723854e-05, "loss": 0.8493, "step": 1165 }, { "epoch": 1.0857409133271203, "loss_cot": 0.4881264269351959, "loss_nocot": 0.3042677342891693, "step": 1165 }, { "epoch": 1.086672879776328, "grad_norm": 0.6229311678953059, "learning_rate": 1.4173282706247844e-05, "loss": 0.838, "step": 1166 }, { "epoch": 1.086672879776328, "loss_cot": 0.566508412361145, "loss_nocot": 0.3392322361469269, "step": 1166 }, { "epoch": 1.0876048462255359, "grad_norm": 0.6155471069187314, "learning_rate": 1.4166379012771833e-05, "loss": 0.8748, "step": 1167 }, { "epoch": 1.0876048462255359, "loss_cot": 0.48982003331184387, "loss_nocot": 0.29808154702186584, "step": 1167 }, { "epoch": 1.0885368126747437, "grad_norm": 0.6372762491511654, "learning_rate": 1.4159475319295824e-05, "loss": 0.8871, "step": 1168 }, { "epoch": 1.0885368126747437, "loss_cot": 0.5790360569953918, "loss_nocot": 0.2529994249343872, "step": 1168 }, { "epoch": 1.0894687791239515, "grad_norm": 0.63999680154211, "learning_rate": 1.4152571625819815e-05, "loss": 0.9678, "step": 1169 }, { "epoch": 1.0894687791239515, "loss_cot": 0.4845556318759918, "loss_nocot": 0.35234445333480835, "step": 1169 }, { "epoch": 1.0904007455731595, "grad_norm": 0.5855034139422646, "learning_rate": 1.4145667932343806e-05, "loss": 0.8534, "step": 1170 }, { "epoch": 1.0904007455731595, "loss_cot": 0.5818018317222595, "loss_nocot": 0.3304871618747711, "step": 1170 }, { "epoch": 1.0913327120223673, "grad_norm": 0.6641912156650229, "learning_rate": 1.4138764238867795e-05, "loss": 0.926, "step": 1171 }, { "epoch": 1.0913327120223673, "loss_cot": 0.5726797580718994, "loss_nocot": 0.45601117610931396, "step": 1171 }, { "epoch": 1.092264678471575, "grad_norm": 0.6079804334186892, "learning_rate": 1.4131860545391787e-05, "loss": 0.8602, "step": 1172 }, { "epoch": 1.092264678471575, "loss_cot": 0.5112026929855347, "loss_nocot": 0.3763526678085327, "step": 1172 }, { "epoch": 1.0931966449207828, "grad_norm": 0.5756927260295595, "learning_rate": 1.4124956851915776e-05, "loss": 0.8284, "step": 1173 }, { "epoch": 1.0931966449207828, "loss_cot": 0.4969685971736908, "loss_nocot": 0.29804134368896484, "step": 1173 }, { "epoch": 1.0941286113699906, "grad_norm": 0.5663666531856547, "learning_rate": 1.4118053158439767e-05, "loss": 0.7981, "step": 1174 }, { "epoch": 1.0941286113699906, "loss_cot": 0.525633692741394, "loss_nocot": 0.4466616213321686, "step": 1174 }, { "epoch": 1.0950605778191984, "grad_norm": 0.661248181502248, "learning_rate": 1.4111149464963756e-05, "loss": 0.932, "step": 1175 }, { "epoch": 1.0950605778191984, "loss_cot": 0.5237976908683777, "loss_nocot": 0.36660248041152954, "step": 1175 }, { "epoch": 1.0959925442684064, "grad_norm": 0.5990551284629031, "learning_rate": 1.4104245771487748e-05, "loss": 0.8324, "step": 1176 }, { "epoch": 1.0959925442684064, "loss_cot": 0.5133049488067627, "loss_nocot": 0.3360500931739807, "step": 1176 }, { "epoch": 1.0969245107176142, "grad_norm": 0.7271150813492285, "learning_rate": 1.4097342078011737e-05, "loss": 0.9564, "step": 1177 }, { "epoch": 1.0969245107176142, "loss_cot": 0.46420079469680786, "loss_nocot": 0.38161852955818176, "step": 1177 }, { "epoch": 1.097856477166822, "grad_norm": 0.6684986256303533, "learning_rate": 1.4090438384535728e-05, "loss": 0.9264, "step": 1178 }, { "epoch": 1.097856477166822, "loss_cot": 0.46054214239120483, "loss_nocot": 0.48089203238487244, "step": 1178 }, { "epoch": 1.0987884436160298, "grad_norm": 0.6124211092412656, "learning_rate": 1.4083534691059717e-05, "loss": 0.8526, "step": 1179 }, { "epoch": 1.0987884436160298, "loss_cot": 0.5745440125465393, "loss_nocot": 0.5183771252632141, "step": 1179 }, { "epoch": 1.0997204100652376, "grad_norm": 0.656266276214467, "learning_rate": 1.407663099758371e-05, "loss": 0.9179, "step": 1180 }, { "epoch": 1.0997204100652376, "loss_cot": 0.4543076157569885, "loss_nocot": 0.27526676654815674, "step": 1180 }, { "epoch": 1.1006523765144456, "grad_norm": 0.6340757187260095, "learning_rate": 1.4069727304107699e-05, "loss": 0.8265, "step": 1181 }, { "epoch": 1.1006523765144456, "loss_cot": 0.46617549657821655, "loss_nocot": 0.36996859312057495, "step": 1181 }, { "epoch": 1.1015843429636534, "grad_norm": 0.5946828063797885, "learning_rate": 1.4062823610631688e-05, "loss": 0.8432, "step": 1182 }, { "epoch": 1.1015843429636534, "loss_cot": 0.4939455986022949, "loss_nocot": 0.28284725546836853, "step": 1182 }, { "epoch": 1.1025163094128612, "grad_norm": 0.5789799593012092, "learning_rate": 1.405591991715568e-05, "loss": 0.7961, "step": 1183 }, { "epoch": 1.1025163094128612, "loss_cot": 0.5195215344429016, "loss_nocot": 0.4319547414779663, "step": 1183 }, { "epoch": 1.103448275862069, "grad_norm": 0.6376123858956763, "learning_rate": 1.404901622367967e-05, "loss": 0.9127, "step": 1184 }, { "epoch": 1.103448275862069, "loss_cot": 0.5699065923690796, "loss_nocot": 0.362135648727417, "step": 1184 }, { "epoch": 1.1043802423112767, "grad_norm": 0.6550614817491293, "learning_rate": 1.404211253020366e-05, "loss": 0.8748, "step": 1185 }, { "epoch": 1.1043802423112767, "loss_cot": 0.6331198215484619, "loss_nocot": 0.45562586188316345, "step": 1185 }, { "epoch": 1.1053122087604845, "grad_norm": 0.7185810376973129, "learning_rate": 1.4035208836727649e-05, "loss": 0.9453, "step": 1186 }, { "epoch": 1.1053122087604845, "loss_cot": 0.4638601243495941, "loss_nocot": 0.43366608023643494, "step": 1186 }, { "epoch": 1.1062441752096925, "grad_norm": 0.6484372408327379, "learning_rate": 1.4028305143251641e-05, "loss": 0.8999, "step": 1187 }, { "epoch": 1.1062441752096925, "loss_cot": 0.5249026417732239, "loss_nocot": 0.33840256929397583, "step": 1187 }, { "epoch": 1.1071761416589003, "grad_norm": 0.6534248270321356, "learning_rate": 1.402140144977563e-05, "loss": 0.8717, "step": 1188 }, { "epoch": 1.1071761416589003, "loss_cot": 0.43921107053756714, "loss_nocot": 0.2917104661464691, "step": 1188 }, { "epoch": 1.1081081081081081, "grad_norm": 0.6233345996817958, "learning_rate": 1.4014497756299621e-05, "loss": 0.8722, "step": 1189 }, { "epoch": 1.1081081081081081, "loss_cot": 0.4750867486000061, "loss_nocot": 0.28925514221191406, "step": 1189 }, { "epoch": 1.109040074557316, "grad_norm": 0.5945103481666184, "learning_rate": 1.400759406282361e-05, "loss": 0.8388, "step": 1190 }, { "epoch": 1.109040074557316, "loss_cot": 0.4955069124698639, "loss_nocot": 0.3016358017921448, "step": 1190 }, { "epoch": 1.1099720410065237, "grad_norm": 0.5926227542992547, "learning_rate": 1.4000690369347603e-05, "loss": 0.8561, "step": 1191 }, { "epoch": 1.1099720410065237, "loss_cot": 0.5609813332557678, "loss_nocot": 0.40692564845085144, "step": 1191 }, { "epoch": 1.1109040074557317, "grad_norm": 0.6309082291481284, "learning_rate": 1.3993786675871592e-05, "loss": 0.8664, "step": 1192 }, { "epoch": 1.1109040074557317, "loss_cot": 0.531777024269104, "loss_nocot": 0.3135319948196411, "step": 1192 }, { "epoch": 1.1118359739049395, "grad_norm": 0.544523268520459, "learning_rate": 1.3986882982395582e-05, "loss": 0.786, "step": 1193 }, { "epoch": 1.1118359739049395, "loss_cot": 0.5438772439956665, "loss_nocot": 0.5036190748214722, "step": 1193 }, { "epoch": 1.1127679403541473, "grad_norm": 0.6873796684747284, "learning_rate": 1.3979979288919575e-05, "loss": 0.9285, "step": 1194 }, { "epoch": 1.1127679403541473, "loss_cot": 0.5291925072669983, "loss_nocot": 0.29076170921325684, "step": 1194 }, { "epoch": 1.113699906803355, "grad_norm": 0.6422079655477574, "learning_rate": 1.3973075595443564e-05, "loss": 0.9089, "step": 1195 }, { "epoch": 1.113699906803355, "loss_cot": 0.5356322526931763, "loss_nocot": 0.31673169136047363, "step": 1195 }, { "epoch": 1.1146318732525629, "grad_norm": 0.5801310871674272, "learning_rate": 1.3966171901967553e-05, "loss": 0.8382, "step": 1196 }, { "epoch": 1.1146318732525629, "loss_cot": 0.5380335450172424, "loss_nocot": 0.3210487961769104, "step": 1196 }, { "epoch": 1.1155638397017706, "grad_norm": 0.6225786162841715, "learning_rate": 1.3959268208491544e-05, "loss": 0.8418, "step": 1197 }, { "epoch": 1.1155638397017706, "loss_cot": 0.5229440927505493, "loss_nocot": 0.33105218410491943, "step": 1197 }, { "epoch": 1.1164958061509787, "grad_norm": 0.5630146508594799, "learning_rate": 1.3952364515015534e-05, "loss": 0.8272, "step": 1198 }, { "epoch": 1.1164958061509787, "loss_cot": 0.5393533706665039, "loss_nocot": 0.38320091366767883, "step": 1198 }, { "epoch": 1.1174277726001864, "grad_norm": 0.6081723615277154, "learning_rate": 1.3945460821539525e-05, "loss": 0.8763, "step": 1199 }, { "epoch": 1.1174277726001864, "loss_cot": 0.5000026226043701, "loss_nocot": 0.36575034260749817, "step": 1199 }, { "epoch": 1.1183597390493942, "grad_norm": 0.6178402328123722, "learning_rate": 1.3938557128063514e-05, "loss": 0.862, "step": 1200 }, { "epoch": 1.1183597390493942, "loss_cot": 0.5471480488777161, "loss_nocot": 0.2686317265033722, "step": 1200 }, { "epoch": 1.119291705498602, "grad_norm": 0.5576090926669138, "learning_rate": 1.3931653434587507e-05, "loss": 0.8406, "step": 1201 }, { "epoch": 1.119291705498602, "loss_cot": 0.509986162185669, "loss_nocot": 0.362313836812973, "step": 1201 }, { "epoch": 1.1202236719478098, "grad_norm": 0.606924609652829, "learning_rate": 1.3924749741111496e-05, "loss": 0.8375, "step": 1202 }, { "epoch": 1.1202236719478098, "loss_cot": 0.4926005005836487, "loss_nocot": 0.43213772773742676, "step": 1202 }, { "epoch": 1.1211556383970178, "grad_norm": 0.6828812216640385, "learning_rate": 1.3917846047635486e-05, "loss": 0.9105, "step": 1203 }, { "epoch": 1.1211556383970178, "loss_cot": 0.47992175817489624, "loss_nocot": 0.3114524185657501, "step": 1203 }, { "epoch": 1.1220876048462256, "grad_norm": 0.6241853718305228, "learning_rate": 1.3910942354159475e-05, "loss": 0.8709, "step": 1204 }, { "epoch": 1.1220876048462256, "loss_cot": 0.5254722833633423, "loss_nocot": 0.4130197763442993, "step": 1204 }, { "epoch": 1.1230195712954334, "grad_norm": 0.6473696115392501, "learning_rate": 1.3904038660683468e-05, "loss": 0.9153, "step": 1205 }, { "epoch": 1.1230195712954334, "loss_cot": 0.5539445877075195, "loss_nocot": 0.36832302808761597, "step": 1205 }, { "epoch": 1.1239515377446412, "grad_norm": 0.6710752830028723, "learning_rate": 1.3897134967207457e-05, "loss": 0.8876, "step": 1206 }, { "epoch": 1.1239515377446412, "loss_cot": 0.49594181776046753, "loss_nocot": 0.4574907720088959, "step": 1206 }, { "epoch": 1.124883504193849, "grad_norm": 0.6322296475785711, "learning_rate": 1.3890231273731448e-05, "loss": 0.8853, "step": 1207 }, { "epoch": 1.124883504193849, "loss_cot": 0.5063822269439697, "loss_nocot": 0.3368402123451233, "step": 1207 }, { "epoch": 1.1258154706430568, "grad_norm": 0.6666323527363692, "learning_rate": 1.3883327580255437e-05, "loss": 0.9099, "step": 1208 }, { "epoch": 1.1258154706430568, "loss_cot": 0.4995138645172119, "loss_nocot": 0.33543992042541504, "step": 1208 }, { "epoch": 1.1267474370922648, "grad_norm": 0.6619487865849896, "learning_rate": 1.3876423886779429e-05, "loss": 0.8686, "step": 1209 }, { "epoch": 1.1267474370922648, "loss_cot": 0.4856211543083191, "loss_nocot": 0.4503031075000763, "step": 1209 }, { "epoch": 1.1276794035414726, "grad_norm": 0.8169105668622135, "learning_rate": 1.3869520193303418e-05, "loss": 0.9669, "step": 1210 }, { "epoch": 1.1276794035414726, "loss_cot": 0.5169901847839355, "loss_nocot": 0.3391897678375244, "step": 1210 }, { "epoch": 1.1286113699906803, "grad_norm": 0.6973685579775242, "learning_rate": 1.3862616499827409e-05, "loss": 0.8795, "step": 1211 }, { "epoch": 1.1286113699906803, "loss_cot": 0.5485138297080994, "loss_nocot": 0.3126834034919739, "step": 1211 }, { "epoch": 1.1295433364398881, "grad_norm": 0.5682666828470564, "learning_rate": 1.38557128063514e-05, "loss": 0.8169, "step": 1212 }, { "epoch": 1.1295433364398881, "loss_cot": 0.5413442850112915, "loss_nocot": 0.2784249782562256, "step": 1212 }, { "epoch": 1.130475302889096, "grad_norm": 0.57147329888465, "learning_rate": 1.384880911287539e-05, "loss": 0.8571, "step": 1213 }, { "epoch": 1.130475302889096, "loss_cot": 0.5042632818222046, "loss_nocot": 0.3731304705142975, "step": 1213 }, { "epoch": 1.131407269338304, "grad_norm": 0.6313374981522658, "learning_rate": 1.384190541939938e-05, "loss": 0.8617, "step": 1214 }, { "epoch": 1.131407269338304, "loss_cot": 0.5696777105331421, "loss_nocot": 0.23575347661972046, "step": 1214 }, { "epoch": 1.1323392357875117, "grad_norm": 0.6503698214909533, "learning_rate": 1.383500172592337e-05, "loss": 0.8229, "step": 1215 }, { "epoch": 1.1323392357875117, "loss_cot": 0.4993620812892914, "loss_nocot": 0.27798905968666077, "step": 1215 }, { "epoch": 1.1332712022367195, "grad_norm": 0.6311931541331108, "learning_rate": 1.382809803244736e-05, "loss": 0.8659, "step": 1216 }, { "epoch": 1.1332712022367195, "loss_cot": 0.49512964487075806, "loss_nocot": 0.4119452238082886, "step": 1216 }, { "epoch": 1.1342031686859273, "grad_norm": 0.6880156836804823, "learning_rate": 1.3821194338971351e-05, "loss": 0.944, "step": 1217 }, { "epoch": 1.1342031686859273, "loss_cot": 0.46330785751342773, "loss_nocot": 0.43198421597480774, "step": 1217 }, { "epoch": 1.135135135135135, "grad_norm": 0.6418816531210768, "learning_rate": 1.381429064549534e-05, "loss": 0.9045, "step": 1218 }, { "epoch": 1.135135135135135, "loss_cot": 0.49620214104652405, "loss_nocot": 0.31118959188461304, "step": 1218 }, { "epoch": 1.1360671015843429, "grad_norm": 0.5677477000417768, "learning_rate": 1.3807386952019331e-05, "loss": 0.806, "step": 1219 }, { "epoch": 1.1360671015843429, "loss_cot": 0.4861537218093872, "loss_nocot": 0.35027772188186646, "step": 1219 }, { "epoch": 1.1369990680335509, "grad_norm": 0.6573525097817725, "learning_rate": 1.3800483258543322e-05, "loss": 0.9175, "step": 1220 }, { "epoch": 1.1369990680335509, "loss_cot": 0.5201661586761475, "loss_nocot": 0.31656786799430847, "step": 1220 }, { "epoch": 1.1379310344827587, "grad_norm": 0.6196473463668172, "learning_rate": 1.3793579565067313e-05, "loss": 0.9118, "step": 1221 }, { "epoch": 1.1379310344827587, "loss_cot": 0.5474047660827637, "loss_nocot": 0.3602873682975769, "step": 1221 }, { "epoch": 1.1388630009319665, "grad_norm": 0.6102581336974818, "learning_rate": 1.3786675871591302e-05, "loss": 0.8605, "step": 1222 }, { "epoch": 1.1388630009319665, "loss_cot": 0.547571063041687, "loss_nocot": 0.46130532026290894, "step": 1222 }, { "epoch": 1.1397949673811743, "grad_norm": 0.6226228160208755, "learning_rate": 1.3779772178115294e-05, "loss": 0.8831, "step": 1223 }, { "epoch": 1.1397949673811743, "loss_cot": 0.4823414981365204, "loss_nocot": 0.34151598811149597, "step": 1223 }, { "epoch": 1.140726933830382, "grad_norm": 0.6021866529920177, "learning_rate": 1.3772868484639283e-05, "loss": 0.8337, "step": 1224 }, { "epoch": 1.140726933830382, "loss_cot": 0.5592236518859863, "loss_nocot": 0.33961695432662964, "step": 1224 }, { "epoch": 1.14165890027959, "grad_norm": 0.5955337042075878, "learning_rate": 1.3765964791163274e-05, "loss": 0.8667, "step": 1225 }, { "epoch": 1.14165890027959, "loss_cot": 0.5629808902740479, "loss_nocot": 0.3130878210067749, "step": 1225 }, { "epoch": 1.1425908667287978, "grad_norm": 0.5580917559498949, "learning_rate": 1.3759061097687263e-05, "loss": 0.8512, "step": 1226 }, { "epoch": 1.1425908667287978, "loss_cot": 0.45999500155448914, "loss_nocot": 0.42078691720962524, "step": 1226 }, { "epoch": 1.1435228331780056, "grad_norm": 0.6045362633957965, "learning_rate": 1.3752157404211255e-05, "loss": 0.8524, "step": 1227 }, { "epoch": 1.1435228331780056, "loss_cot": 0.4528449773788452, "loss_nocot": 0.30062171816825867, "step": 1227 }, { "epoch": 1.1444547996272134, "grad_norm": 0.7175067129293731, "learning_rate": 1.3745253710735244e-05, "loss": 0.8778, "step": 1228 }, { "epoch": 1.1444547996272134, "loss_cot": 0.5237494707107544, "loss_nocot": 0.3982846140861511, "step": 1228 }, { "epoch": 1.1453867660764212, "grad_norm": 0.6455451646925826, "learning_rate": 1.3738350017259235e-05, "loss": 0.9101, "step": 1229 }, { "epoch": 1.1453867660764212, "loss_cot": 0.5363725423812866, "loss_nocot": 0.3224184811115265, "step": 1229 }, { "epoch": 1.146318732525629, "grad_norm": 0.5859774803765053, "learning_rate": 1.3731446323783224e-05, "loss": 0.8322, "step": 1230 }, { "epoch": 1.146318732525629, "loss_cot": 0.5340355634689331, "loss_nocot": 0.29257932305336, "step": 1230 }, { "epoch": 1.147250698974837, "grad_norm": 0.6335853669507557, "learning_rate": 1.3724542630307217e-05, "loss": 0.894, "step": 1231 }, { "epoch": 1.147250698974837, "loss_cot": 0.5097137093544006, "loss_nocot": 0.5034449100494385, "step": 1231 }, { "epoch": 1.1481826654240448, "grad_norm": 0.6242979841132299, "learning_rate": 1.3717638936831206e-05, "loss": 0.8527, "step": 1232 }, { "epoch": 1.1481826654240448, "loss_cot": 0.4639451503753662, "loss_nocot": 0.4489493668079376, "step": 1232 }, { "epoch": 1.1491146318732526, "grad_norm": 0.8079115131564604, "learning_rate": 1.3710735243355195e-05, "loss": 0.9555, "step": 1233 }, { "epoch": 1.1491146318732526, "loss_cot": 0.5410072207450867, "loss_nocot": 0.25682276487350464, "step": 1233 }, { "epoch": 1.1500465983224604, "grad_norm": 0.6165713863315843, "learning_rate": 1.3703831549879187e-05, "loss": 0.8601, "step": 1234 }, { "epoch": 1.1500465983224604, "loss_cot": 0.4992574155330658, "loss_nocot": 0.459506630897522, "step": 1234 }, { "epoch": 1.1509785647716682, "grad_norm": 0.6386646161307025, "learning_rate": 1.3696927856403178e-05, "loss": 0.8951, "step": 1235 }, { "epoch": 1.1509785647716682, "loss_cot": 0.5461893677711487, "loss_nocot": 0.3595145642757416, "step": 1235 }, { "epoch": 1.1519105312208762, "grad_norm": 0.6167802383992929, "learning_rate": 1.3690024162927167e-05, "loss": 0.8501, "step": 1236 }, { "epoch": 1.1519105312208762, "loss_cot": 0.5134406089782715, "loss_nocot": 0.3454686999320984, "step": 1236 }, { "epoch": 1.152842497670084, "grad_norm": 0.6434256308444011, "learning_rate": 1.3683120469451156e-05, "loss": 0.9131, "step": 1237 }, { "epoch": 1.152842497670084, "loss_cot": 0.5037120580673218, "loss_nocot": 0.3745574951171875, "step": 1237 }, { "epoch": 1.1537744641192917, "grad_norm": 0.6487167098222019, "learning_rate": 1.3676216775975148e-05, "loss": 0.8496, "step": 1238 }, { "epoch": 1.1537744641192917, "loss_cot": 0.4685733914375305, "loss_nocot": 0.30724021792411804, "step": 1238 }, { "epoch": 1.1547064305684995, "grad_norm": 0.6091742487769902, "learning_rate": 1.3669313082499137e-05, "loss": 0.8347, "step": 1239 }, { "epoch": 1.1547064305684995, "loss_cot": 0.5462298393249512, "loss_nocot": 0.3480920195579529, "step": 1239 }, { "epoch": 1.1556383970177073, "grad_norm": 0.6677605773507921, "learning_rate": 1.3662409389023128e-05, "loss": 0.8975, "step": 1240 }, { "epoch": 1.1556383970177073, "loss_cot": 0.5932886600494385, "loss_nocot": 0.3559056520462036, "step": 1240 }, { "epoch": 1.156570363466915, "grad_norm": 0.6477171818612785, "learning_rate": 1.365550569554712e-05, "loss": 0.8916, "step": 1241 }, { "epoch": 1.156570363466915, "loss_cot": 0.48953473567962646, "loss_nocot": 0.3661186397075653, "step": 1241 }, { "epoch": 1.157502329916123, "grad_norm": 0.5947749131601795, "learning_rate": 1.364860200207111e-05, "loss": 0.839, "step": 1242 }, { "epoch": 1.157502329916123, "loss_cot": 0.4746593236923218, "loss_nocot": 0.3572264313697815, "step": 1242 }, { "epoch": 1.158434296365331, "grad_norm": 0.5755773641609997, "learning_rate": 1.3641698308595099e-05, "loss": 0.8585, "step": 1243 }, { "epoch": 1.158434296365331, "loss_cot": 0.5286042094230652, "loss_nocot": 0.3988219201564789, "step": 1243 }, { "epoch": 1.1593662628145387, "grad_norm": 0.5941548631380549, "learning_rate": 1.363479461511909e-05, "loss": 0.899, "step": 1244 }, { "epoch": 1.1593662628145387, "loss_cot": 0.5497783422470093, "loss_nocot": 0.36576104164123535, "step": 1244 }, { "epoch": 1.1602982292637465, "grad_norm": 0.6031440219984274, "learning_rate": 1.3627890921643082e-05, "loss": 0.8698, "step": 1245 }, { "epoch": 1.1602982292637465, "loss_cot": 0.49743548035621643, "loss_nocot": 0.36060819029808044, "step": 1245 }, { "epoch": 1.1612301957129543, "grad_norm": 0.641151902568306, "learning_rate": 1.362098722816707e-05, "loss": 0.8887, "step": 1246 }, { "epoch": 1.1612301957129543, "loss_cot": 0.5434456467628479, "loss_nocot": 0.4232008755207062, "step": 1246 }, { "epoch": 1.1621621621621623, "grad_norm": 0.6155292102059554, "learning_rate": 1.361408353469106e-05, "loss": 0.8824, "step": 1247 }, { "epoch": 1.1621621621621623, "loss_cot": 0.4822385609149933, "loss_nocot": 0.34793615341186523, "step": 1247 }, { "epoch": 1.16309412861137, "grad_norm": 0.6643272692616435, "learning_rate": 1.360717984121505e-05, "loss": 0.9138, "step": 1248 }, { "epoch": 1.16309412861137, "loss_cot": 0.5163154602050781, "loss_nocot": 0.25455617904663086, "step": 1248 }, { "epoch": 1.1640260950605779, "grad_norm": 0.6590575970493855, "learning_rate": 1.3600276147739041e-05, "loss": 0.8572, "step": 1249 }, { "epoch": 1.1640260950605779, "loss_cot": 0.49766409397125244, "loss_nocot": 0.3112899661064148, "step": 1249 }, { "epoch": 1.1649580615097856, "grad_norm": 0.601078990379936, "learning_rate": 1.3593372454263032e-05, "loss": 0.8308, "step": 1250 }, { "epoch": 1.1649580615097856, "loss_cot": 0.4889068007469177, "loss_nocot": 0.3483238220214844, "step": 1250 }, { "epoch": 1.1658900279589934, "grad_norm": 0.6701630315887831, "learning_rate": 1.3586468760787021e-05, "loss": 0.8325, "step": 1251 }, { "epoch": 1.1658900279589934, "loss_cot": 0.47476136684417725, "loss_nocot": 0.34632766246795654, "step": 1251 }, { "epoch": 1.1668219944082012, "grad_norm": 0.7560730003761317, "learning_rate": 1.3579565067311014e-05, "loss": 0.8635, "step": 1252 }, { "epoch": 1.1668219944082012, "loss_cot": 0.4911652207374573, "loss_nocot": 0.47160524129867554, "step": 1252 }, { "epoch": 1.167753960857409, "grad_norm": 0.6593464456301588, "learning_rate": 1.3572661373835003e-05, "loss": 0.8488, "step": 1253 }, { "epoch": 1.167753960857409, "loss_cot": 0.4806390702724457, "loss_nocot": 0.39603132009506226, "step": 1253 }, { "epoch": 1.168685927306617, "grad_norm": 0.6303828268621895, "learning_rate": 1.3565757680358993e-05, "loss": 0.8729, "step": 1254 }, { "epoch": 1.168685927306617, "loss_cot": 0.5470427870750427, "loss_nocot": 0.4128321409225464, "step": 1254 }, { "epoch": 1.1696178937558248, "grad_norm": 0.5912201489976813, "learning_rate": 1.3558853986882982e-05, "loss": 0.8218, "step": 1255 }, { "epoch": 1.1696178937558248, "loss_cot": 0.6195286512374878, "loss_nocot": 0.3312940299510956, "step": 1255 }, { "epoch": 1.1705498602050326, "grad_norm": 0.6233278526221769, "learning_rate": 1.3551950293406975e-05, "loss": 0.8516, "step": 1256 }, { "epoch": 1.1705498602050326, "loss_cot": 0.5155494213104248, "loss_nocot": 0.43558526039123535, "step": 1256 }, { "epoch": 1.1714818266542404, "grad_norm": 0.6296111607309992, "learning_rate": 1.3545046599930964e-05, "loss": 0.8698, "step": 1257 }, { "epoch": 1.1714818266542404, "loss_cot": 0.45753204822540283, "loss_nocot": 0.35226282477378845, "step": 1257 }, { "epoch": 1.1724137931034484, "grad_norm": 0.6174099190046605, "learning_rate": 1.3538142906454955e-05, "loss": 0.8326, "step": 1258 }, { "epoch": 1.1724137931034484, "loss_cot": 0.5937231183052063, "loss_nocot": 0.6153193116188049, "step": 1258 }, { "epoch": 1.1733457595526562, "grad_norm": 0.6755408438020398, "learning_rate": 1.3531239212978944e-05, "loss": 0.9592, "step": 1259 }, { "epoch": 1.1733457595526562, "loss_cot": 0.5064272880554199, "loss_nocot": 0.4282133877277374, "step": 1259 }, { "epoch": 1.174277726001864, "grad_norm": 0.6269418423896924, "learning_rate": 1.3524335519502936e-05, "loss": 0.8566, "step": 1260 }, { "epoch": 1.174277726001864, "loss_cot": 0.4810900390148163, "loss_nocot": 0.269856333732605, "step": 1260 }, { "epoch": 1.1752096924510718, "grad_norm": 0.623495398196974, "learning_rate": 1.3517431826026925e-05, "loss": 0.8506, "step": 1261 }, { "epoch": 1.1752096924510718, "loss_cot": 0.4390372037887573, "loss_nocot": 0.38931483030319214, "step": 1261 }, { "epoch": 1.1761416589002796, "grad_norm": 0.5993729256421234, "learning_rate": 1.3510528132550916e-05, "loss": 0.8295, "step": 1262 }, { "epoch": 1.1761416589002796, "loss_cot": 0.4975869953632355, "loss_nocot": 0.3827606439590454, "step": 1262 }, { "epoch": 1.1770736253494873, "grad_norm": 0.6070530130798155, "learning_rate": 1.3503624439074907e-05, "loss": 0.8164, "step": 1263 }, { "epoch": 1.1770736253494873, "loss_cot": 0.5491697788238525, "loss_nocot": 0.3136099874973297, "step": 1263 }, { "epoch": 1.1780055917986951, "grad_norm": 0.5878754692988518, "learning_rate": 1.3496720745598897e-05, "loss": 0.8295, "step": 1264 }, { "epoch": 1.1780055917986951, "loss_cot": 0.45308125019073486, "loss_nocot": 0.2652515172958374, "step": 1264 }, { "epoch": 1.1789375582479031, "grad_norm": 0.6267081660049899, "learning_rate": 1.3489817052122886e-05, "loss": 0.8853, "step": 1265 }, { "epoch": 1.1789375582479031, "loss_cot": 0.5299199819564819, "loss_nocot": 0.22612148523330688, "step": 1265 }, { "epoch": 1.179869524697111, "grad_norm": 0.6332393743734924, "learning_rate": 1.3482913358646877e-05, "loss": 0.9022, "step": 1266 }, { "epoch": 1.179869524697111, "loss_cot": 0.5116277933120728, "loss_nocot": 0.38039514422416687, "step": 1266 }, { "epoch": 1.1808014911463187, "grad_norm": 0.6240554851193788, "learning_rate": 1.3476009665170868e-05, "loss": 0.8963, "step": 1267 }, { "epoch": 1.1808014911463187, "loss_cot": 0.47557568550109863, "loss_nocot": 0.28984737396240234, "step": 1267 }, { "epoch": 1.1817334575955265, "grad_norm": 0.5844708422937515, "learning_rate": 1.3469105971694858e-05, "loss": 0.8352, "step": 1268 }, { "epoch": 1.1817334575955265, "loss_cot": 0.5265794396400452, "loss_nocot": 0.3384222984313965, "step": 1268 }, { "epoch": 1.1826654240447343, "grad_norm": 0.5947090309576031, "learning_rate": 1.3462202278218848e-05, "loss": 0.8758, "step": 1269 }, { "epoch": 1.1826654240447343, "loss_cot": 0.4899774491786957, "loss_nocot": 0.35226866602897644, "step": 1269 }, { "epoch": 1.1835973904939423, "grad_norm": 0.5619699381435478, "learning_rate": 1.3455298584742838e-05, "loss": 0.8084, "step": 1270 }, { "epoch": 1.1835973904939423, "loss_cot": 0.5529764294624329, "loss_nocot": 0.48285698890686035, "step": 1270 }, { "epoch": 1.18452935694315, "grad_norm": 0.6863642886556631, "learning_rate": 1.3448394891266829e-05, "loss": 0.9392, "step": 1271 }, { "epoch": 1.18452935694315, "loss_cot": 0.49583321809768677, "loss_nocot": 0.36356833577156067, "step": 1271 }, { "epoch": 1.1854613233923579, "grad_norm": 0.6724281870942115, "learning_rate": 1.344149119779082e-05, "loss": 0.9221, "step": 1272 }, { "epoch": 1.1854613233923579, "loss_cot": 0.4308086335659027, "loss_nocot": 0.31650930643081665, "step": 1272 }, { "epoch": 1.1863932898415657, "grad_norm": 0.6085314822819174, "learning_rate": 1.3434587504314809e-05, "loss": 0.8118, "step": 1273 }, { "epoch": 1.1863932898415657, "loss_cot": 0.5120810270309448, "loss_nocot": 0.42264285683631897, "step": 1273 }, { "epoch": 1.1873252562907735, "grad_norm": 9.479021206866916, "learning_rate": 1.3427683810838801e-05, "loss": 0.856, "step": 1274 }, { "epoch": 1.1873252562907735, "loss_cot": 0.5024795532226562, "loss_nocot": 0.3806006610393524, "step": 1274 }, { "epoch": 1.1882572227399812, "grad_norm": 0.6865965805320817, "learning_rate": 1.342078011736279e-05, "loss": 0.9387, "step": 1275 }, { "epoch": 1.1882572227399812, "loss_cot": 0.5109882354736328, "loss_nocot": 0.26741501688957214, "step": 1275 }, { "epoch": 1.1891891891891893, "grad_norm": 0.5882952159476174, "learning_rate": 1.3413876423886781e-05, "loss": 0.8445, "step": 1276 }, { "epoch": 1.1891891891891893, "loss_cot": 0.5001653432846069, "loss_nocot": 0.3420830965042114, "step": 1276 }, { "epoch": 1.190121155638397, "grad_norm": 0.6160502869508194, "learning_rate": 1.340697273041077e-05, "loss": 0.8779, "step": 1277 }, { "epoch": 1.190121155638397, "loss_cot": 0.5625916719436646, "loss_nocot": 0.49803784489631653, "step": 1277 }, { "epoch": 1.1910531220876048, "grad_norm": 0.6505741728347626, "learning_rate": 1.3400069036934762e-05, "loss": 0.9404, "step": 1278 }, { "epoch": 1.1910531220876048, "loss_cot": 0.4953927993774414, "loss_nocot": 0.3088003098964691, "step": 1278 }, { "epoch": 1.1919850885368126, "grad_norm": 0.6836151059785837, "learning_rate": 1.3393165343458751e-05, "loss": 0.868, "step": 1279 }, { "epoch": 1.1919850885368126, "loss_cot": 0.5310616493225098, "loss_nocot": 0.2985055446624756, "step": 1279 }, { "epoch": 1.1929170549860204, "grad_norm": 0.6343826589684888, "learning_rate": 1.3386261649982742e-05, "loss": 0.8766, "step": 1280 }, { "epoch": 1.1929170549860204, "loss_cot": 0.5084956288337708, "loss_nocot": 0.3681442439556122, "step": 1280 }, { "epoch": 1.1938490214352284, "grad_norm": 0.6498723745313413, "learning_rate": 1.3379357956506733e-05, "loss": 0.8655, "step": 1281 }, { "epoch": 1.1938490214352284, "loss_cot": 0.5148488879203796, "loss_nocot": 0.33773311972618103, "step": 1281 }, { "epoch": 1.1947809878844362, "grad_norm": 0.6860128398379711, "learning_rate": 1.3372454263030724e-05, "loss": 0.9128, "step": 1282 }, { "epoch": 1.1947809878844362, "loss_cot": 0.5453386306762695, "loss_nocot": 0.369941771030426, "step": 1282 }, { "epoch": 1.195712954333644, "grad_norm": 0.6275712870029898, "learning_rate": 1.3365550569554713e-05, "loss": 0.8903, "step": 1283 }, { "epoch": 1.195712954333644, "loss_cot": 0.5500719547271729, "loss_nocot": 0.26610177755355835, "step": 1283 }, { "epoch": 1.1966449207828518, "grad_norm": 0.5764263336322247, "learning_rate": 1.3358646876078702e-05, "loss": 0.819, "step": 1284 }, { "epoch": 1.1966449207828518, "loss_cot": 0.5013591647148132, "loss_nocot": 0.38719210028648376, "step": 1284 }, { "epoch": 1.1975768872320596, "grad_norm": 0.6521390835592411, "learning_rate": 1.3351743182602694e-05, "loss": 0.9175, "step": 1285 }, { "epoch": 1.1975768872320596, "loss_cot": 0.5717150568962097, "loss_nocot": 0.2520776093006134, "step": 1285 }, { "epoch": 1.1985088536812674, "grad_norm": 0.6218931904121192, "learning_rate": 1.3344839489126685e-05, "loss": 0.8887, "step": 1286 }, { "epoch": 1.1985088536812674, "loss_cot": 0.4575539231300354, "loss_nocot": 0.22779613733291626, "step": 1286 }, { "epoch": 1.1994408201304754, "grad_norm": 0.5753640001001695, "learning_rate": 1.3337935795650674e-05, "loss": 0.7924, "step": 1287 }, { "epoch": 1.1994408201304754, "loss_cot": 0.4750186800956726, "loss_nocot": 0.2800096869468689, "step": 1287 }, { "epoch": 1.2003727865796832, "grad_norm": 0.6622231640357812, "learning_rate": 1.3331032102174663e-05, "loss": 0.884, "step": 1288 }, { "epoch": 1.2003727865796832, "loss_cot": 0.5325268507003784, "loss_nocot": 0.34227102994918823, "step": 1288 }, { "epoch": 1.201304753028891, "grad_norm": 0.6586403619105469, "learning_rate": 1.3324128408698655e-05, "loss": 0.8703, "step": 1289 }, { "epoch": 1.201304753028891, "loss_cot": 0.5271912217140198, "loss_nocot": 0.3121894299983978, "step": 1289 }, { "epoch": 1.2022367194780987, "grad_norm": 0.6087592030581505, "learning_rate": 1.3317224715222644e-05, "loss": 0.8573, "step": 1290 }, { "epoch": 1.2022367194780987, "loss_cot": 0.5510470867156982, "loss_nocot": 0.3841140568256378, "step": 1290 }, { "epoch": 1.2031686859273065, "grad_norm": 0.6285257405276861, "learning_rate": 1.3310321021746635e-05, "loss": 0.902, "step": 1291 }, { "epoch": 1.2031686859273065, "loss_cot": 0.49104589223861694, "loss_nocot": 0.38860994577407837, "step": 1291 }, { "epoch": 1.2041006523765145, "grad_norm": 0.6825108172579387, "learning_rate": 1.3303417328270628e-05, "loss": 0.9, "step": 1292 }, { "epoch": 1.2041006523765145, "loss_cot": 0.5409026145935059, "loss_nocot": 0.3815940022468567, "step": 1292 }, { "epoch": 1.2050326188257223, "grad_norm": 0.5958371980661781, "learning_rate": 1.3296513634794617e-05, "loss": 0.8544, "step": 1293 }, { "epoch": 1.2050326188257223, "loss_cot": 0.5480028390884399, "loss_nocot": 0.37402352690696716, "step": 1293 }, { "epoch": 1.2059645852749301, "grad_norm": 0.6514558487326912, "learning_rate": 1.3289609941318606e-05, "loss": 0.8958, "step": 1294 }, { "epoch": 1.2059645852749301, "loss_cot": 0.5185215473175049, "loss_nocot": 0.29722994565963745, "step": 1294 }, { "epoch": 1.206896551724138, "grad_norm": 0.6064712959728812, "learning_rate": 1.3282706247842596e-05, "loss": 0.8277, "step": 1295 }, { "epoch": 1.206896551724138, "loss_cot": 0.51778244972229, "loss_nocot": 0.3843178153038025, "step": 1295 }, { "epoch": 1.2078285181733457, "grad_norm": 0.7080938383438677, "learning_rate": 1.3275802554366589e-05, "loss": 0.9722, "step": 1296 }, { "epoch": 1.2078285181733457, "loss_cot": 0.5943901538848877, "loss_nocot": 0.29217419028282166, "step": 1296 }, { "epoch": 1.2087604846225535, "grad_norm": 0.6089584185983259, "learning_rate": 1.3268898860890578e-05, "loss": 0.852, "step": 1297 }, { "epoch": 1.2087604846225535, "loss_cot": 0.481106162071228, "loss_nocot": 0.3197948932647705, "step": 1297 }, { "epoch": 1.2096924510717615, "grad_norm": 0.625424079170426, "learning_rate": 1.3261995167414567e-05, "loss": 0.8779, "step": 1298 }, { "epoch": 1.2096924510717615, "loss_cot": 0.5146872997283936, "loss_nocot": 0.24394287168979645, "step": 1298 }, { "epoch": 1.2106244175209693, "grad_norm": 0.5826113054892368, "learning_rate": 1.3255091473938558e-05, "loss": 0.8106, "step": 1299 }, { "epoch": 1.2106244175209693, "loss_cot": 0.5066233277320862, "loss_nocot": 0.30291634798049927, "step": 1299 }, { "epoch": 1.211556383970177, "grad_norm": 0.6373067052683561, "learning_rate": 1.3248187780462548e-05, "loss": 0.9146, "step": 1300 }, { "epoch": 1.211556383970177, "loss_cot": 0.529266357421875, "loss_nocot": 0.3957709074020386, "step": 1300 }, { "epoch": 1.2124883504193849, "grad_norm": 0.669662998620168, "learning_rate": 1.3241284086986539e-05, "loss": 0.8917, "step": 1301 }, { "epoch": 1.2124883504193849, "loss_cot": 0.5458452701568604, "loss_nocot": 0.48854589462280273, "step": 1301 }, { "epoch": 1.2134203168685926, "grad_norm": 0.6498239607870043, "learning_rate": 1.3234380393510528e-05, "loss": 0.9219, "step": 1302 }, { "epoch": 1.2134203168685926, "loss_cot": 0.4690091013908386, "loss_nocot": 0.251279354095459, "step": 1302 }, { "epoch": 1.2143522833178007, "grad_norm": 0.5988277023646038, "learning_rate": 1.322747670003452e-05, "loss": 0.837, "step": 1303 }, { "epoch": 1.2143522833178007, "loss_cot": 0.4200814962387085, "loss_nocot": 0.32782572507858276, "step": 1303 }, { "epoch": 1.2152842497670084, "grad_norm": 0.5648448328489651, "learning_rate": 1.322057300655851e-05, "loss": 0.8011, "step": 1304 }, { "epoch": 1.2152842497670084, "loss_cot": 0.5781860947608948, "loss_nocot": 0.31031161546707153, "step": 1304 }, { "epoch": 1.2162162162162162, "grad_norm": 0.6029562747641927, "learning_rate": 1.32136693130825e-05, "loss": 0.8308, "step": 1305 }, { "epoch": 1.2162162162162162, "loss_cot": 0.5902780890464783, "loss_nocot": 0.3816259205341339, "step": 1305 }, { "epoch": 1.217148182665424, "grad_norm": 0.7045457419547231, "learning_rate": 1.320676561960649e-05, "loss": 0.9536, "step": 1306 }, { "epoch": 1.217148182665424, "loss_cot": 0.4832417368888855, "loss_nocot": 0.3580731749534607, "step": 1306 }, { "epoch": 1.2180801491146318, "grad_norm": 0.6466372546944572, "learning_rate": 1.3199861926130482e-05, "loss": 0.8739, "step": 1307 }, { "epoch": 1.2180801491146318, "loss_cot": 0.49416422843933105, "loss_nocot": 0.30532902479171753, "step": 1307 }, { "epoch": 1.2190121155638396, "grad_norm": 0.6011714137037272, "learning_rate": 1.3192958232654471e-05, "loss": 0.8434, "step": 1308 }, { "epoch": 1.2190121155638396, "loss_cot": 0.5102155804634094, "loss_nocot": 0.31008583307266235, "step": 1308 }, { "epoch": 1.2199440820130476, "grad_norm": 0.6148546394766711, "learning_rate": 1.3186054539178462e-05, "loss": 0.8573, "step": 1309 }, { "epoch": 1.2199440820130476, "loss_cot": 0.5379067063331604, "loss_nocot": 0.4129309058189392, "step": 1309 }, { "epoch": 1.2208760484622554, "grad_norm": 0.6420597440548202, "learning_rate": 1.317915084570245e-05, "loss": 0.8771, "step": 1310 }, { "epoch": 1.2208760484622554, "loss_cot": 0.5546309947967529, "loss_nocot": 0.2582879662513733, "step": 1310 }, { "epoch": 1.2218080149114632, "grad_norm": 0.6776875394624542, "learning_rate": 1.3172247152226443e-05, "loss": 0.9361, "step": 1311 }, { "epoch": 1.2218080149114632, "loss_cot": 0.6539995670318604, "loss_nocot": 0.2956523299217224, "step": 1311 }, { "epoch": 1.222739981360671, "grad_norm": 0.6211340482573374, "learning_rate": 1.3165343458750432e-05, "loss": 0.9275, "step": 1312 }, { "epoch": 1.222739981360671, "loss_cot": 0.45648324489593506, "loss_nocot": 0.32277971506118774, "step": 1312 }, { "epoch": 1.2236719478098788, "grad_norm": 0.6674271301634555, "learning_rate": 1.3158439765274423e-05, "loss": 0.8479, "step": 1313 }, { "epoch": 1.2236719478098788, "loss_cot": 0.5854983329772949, "loss_nocot": 0.4235522150993347, "step": 1313 }, { "epoch": 1.2246039142590868, "grad_norm": 0.6521682659901166, "learning_rate": 1.3151536071798414e-05, "loss": 0.9267, "step": 1314 }, { "epoch": 1.2246039142590868, "loss_cot": 0.5812104940414429, "loss_nocot": 0.41188010573387146, "step": 1314 }, { "epoch": 1.2255358807082946, "grad_norm": 0.6562388793102217, "learning_rate": 1.3144632378322404e-05, "loss": 0.9188, "step": 1315 }, { "epoch": 1.2255358807082946, "loss_cot": 0.49643269181251526, "loss_nocot": 0.3175552487373352, "step": 1315 }, { "epoch": 1.2264678471575023, "grad_norm": 0.629291747266197, "learning_rate": 1.3137728684846393e-05, "loss": 0.8291, "step": 1316 }, { "epoch": 1.2264678471575023, "loss_cot": 0.5192266702651978, "loss_nocot": 0.36106911301612854, "step": 1316 }, { "epoch": 1.2273998136067101, "grad_norm": 0.6159750612098728, "learning_rate": 1.3130824991370384e-05, "loss": 0.8556, "step": 1317 }, { "epoch": 1.2273998136067101, "loss_cot": 0.5228615999221802, "loss_nocot": 0.28312572836875916, "step": 1317 }, { "epoch": 1.228331780055918, "grad_norm": 0.5799629189710602, "learning_rate": 1.3123921297894375e-05, "loss": 0.8213, "step": 1318 }, { "epoch": 1.228331780055918, "loss_cot": 0.5193634033203125, "loss_nocot": 0.35365068912506104, "step": 1318 }, { "epoch": 1.2292637465051257, "grad_norm": 0.6572776513476345, "learning_rate": 1.3117017604418366e-05, "loss": 0.884, "step": 1319 }, { "epoch": 1.2292637465051257, "loss_cot": 0.4880315661430359, "loss_nocot": 0.2885722219944, "step": 1319 }, { "epoch": 1.2301957129543337, "grad_norm": 0.5979280078349014, "learning_rate": 1.3110113910942355e-05, "loss": 0.8389, "step": 1320 }, { "epoch": 1.2301957129543337, "loss_cot": 0.5285265445709229, "loss_nocot": 0.2691399157047272, "step": 1320 }, { "epoch": 1.2311276794035415, "grad_norm": 0.6152282137401284, "learning_rate": 1.3103210217466345e-05, "loss": 0.9005, "step": 1321 }, { "epoch": 1.2311276794035415, "loss_cot": 0.5107311010360718, "loss_nocot": 0.2897265553474426, "step": 1321 }, { "epoch": 1.2320596458527493, "grad_norm": 0.6705125422047202, "learning_rate": 1.3096306523990336e-05, "loss": 0.9098, "step": 1322 }, { "epoch": 1.2320596458527493, "loss_cot": 0.5280277729034424, "loss_nocot": 0.41851621866226196, "step": 1322 }, { "epoch": 1.232991612301957, "grad_norm": 0.6771537778158966, "learning_rate": 1.3089402830514327e-05, "loss": 0.9645, "step": 1323 }, { "epoch": 1.232991612301957, "loss_cot": 0.5101559162139893, "loss_nocot": 0.30485183000564575, "step": 1323 }, { "epoch": 1.2339235787511649, "grad_norm": 0.6230576665272589, "learning_rate": 1.3082499137038316e-05, "loss": 0.8965, "step": 1324 }, { "epoch": 1.2339235787511649, "loss_cot": 0.478455513715744, "loss_nocot": 0.3633226752281189, "step": 1324 }, { "epoch": 1.2348555452003729, "grad_norm": 0.6800313051462683, "learning_rate": 1.3075595443562308e-05, "loss": 0.8724, "step": 1325 }, { "epoch": 1.2348555452003729, "loss_cot": 0.5384876728057861, "loss_nocot": 0.36683884263038635, "step": 1325 }, { "epoch": 1.2357875116495807, "grad_norm": 0.6115851036967206, "learning_rate": 1.3068691750086297e-05, "loss": 0.8444, "step": 1326 }, { "epoch": 1.2357875116495807, "loss_cot": 0.5182696580886841, "loss_nocot": 0.3435554802417755, "step": 1326 }, { "epoch": 1.2367194780987885, "grad_norm": 0.630387209768187, "learning_rate": 1.3061788056610288e-05, "loss": 0.8523, "step": 1327 }, { "epoch": 1.2367194780987885, "loss_cot": 0.5133790969848633, "loss_nocot": 0.4450697898864746, "step": 1327 }, { "epoch": 1.2376514445479962, "grad_norm": 0.6510462919493468, "learning_rate": 1.3054884363134277e-05, "loss": 0.9142, "step": 1328 }, { "epoch": 1.2376514445479962, "loss_cot": 0.5460889935493469, "loss_nocot": 0.27347421646118164, "step": 1328 }, { "epoch": 1.238583410997204, "grad_norm": 0.6540412614121203, "learning_rate": 1.304798066965827e-05, "loss": 0.8848, "step": 1329 }, { "epoch": 1.238583410997204, "loss_cot": 0.5288845896720886, "loss_nocot": 0.44883477687835693, "step": 1329 }, { "epoch": 1.2395153774464118, "grad_norm": 0.6835651994077203, "learning_rate": 1.3041076976182258e-05, "loss": 0.9213, "step": 1330 }, { "epoch": 1.2395153774464118, "loss_cot": 0.5144088268280029, "loss_nocot": 0.4042515158653259, "step": 1330 }, { "epoch": 1.2404473438956198, "grad_norm": 0.7033130353577906, "learning_rate": 1.3034173282706248e-05, "loss": 0.8988, "step": 1331 }, { "epoch": 1.2404473438956198, "loss_cot": 0.4597588777542114, "loss_nocot": 0.2581811547279358, "step": 1331 }, { "epoch": 1.2413793103448276, "grad_norm": 0.5884184119960192, "learning_rate": 1.302726958923024e-05, "loss": 0.7813, "step": 1332 }, { "epoch": 1.2413793103448276, "loss_cot": 0.4922226071357727, "loss_nocot": 0.313658207654953, "step": 1332 }, { "epoch": 1.2423112767940354, "grad_norm": 0.5902245742040249, "learning_rate": 1.302036589575423e-05, "loss": 0.8218, "step": 1333 }, { "epoch": 1.2423112767940354, "loss_cot": 0.5540647506713867, "loss_nocot": 0.3217713236808777, "step": 1333 }, { "epoch": 1.2432432432432432, "grad_norm": 0.6912145521611274, "learning_rate": 1.301346220227822e-05, "loss": 0.9013, "step": 1334 }, { "epoch": 1.2432432432432432, "loss_cot": 0.4665263891220093, "loss_nocot": 0.25943756103515625, "step": 1334 }, { "epoch": 1.244175209692451, "grad_norm": 0.6101543437919474, "learning_rate": 1.3006558508802209e-05, "loss": 0.8304, "step": 1335 }, { "epoch": 1.244175209692451, "loss_cot": 0.5057944059371948, "loss_nocot": 0.40535610914230347, "step": 1335 }, { "epoch": 1.245107176141659, "grad_norm": 0.6270167536080319, "learning_rate": 1.2999654815326201e-05, "loss": 0.8402, "step": 1336 }, { "epoch": 1.245107176141659, "loss_cot": 0.4947972297668457, "loss_nocot": 0.2969262897968292, "step": 1336 }, { "epoch": 1.2460391425908668, "grad_norm": 0.6139465914965079, "learning_rate": 1.2992751121850192e-05, "loss": 0.862, "step": 1337 }, { "epoch": 1.2460391425908668, "loss_cot": 0.4594429135322571, "loss_nocot": 0.2980063557624817, "step": 1337 }, { "epoch": 1.2469711090400746, "grad_norm": 0.5885133974406919, "learning_rate": 1.2985847428374181e-05, "loss": 0.8261, "step": 1338 }, { "epoch": 1.2469711090400746, "loss_cot": 0.558442234992981, "loss_nocot": 0.3653000593185425, "step": 1338 }, { "epoch": 1.2479030754892824, "grad_norm": 0.620951707496266, "learning_rate": 1.297894373489817e-05, "loss": 0.8882, "step": 1339 }, { "epoch": 1.2479030754892824, "loss_cot": 0.567512571811676, "loss_nocot": 0.27231210470199585, "step": 1339 }, { "epoch": 1.2488350419384902, "grad_norm": 0.6288615781007183, "learning_rate": 1.2972040041422162e-05, "loss": 0.9095, "step": 1340 }, { "epoch": 1.2488350419384902, "loss_cot": 0.5397025942802429, "loss_nocot": 0.3023220896720886, "step": 1340 }, { "epoch": 1.249767008387698, "grad_norm": 0.6053564458962736, "learning_rate": 1.2965136347946151e-05, "loss": 0.7999, "step": 1341 }, { "epoch": 1.249767008387698, "loss_cot": 0.5044729709625244, "loss_nocot": 0.2821422517299652, "step": 1341 }, { "epoch": 1.250698974836906, "grad_norm": 0.6202004983083653, "learning_rate": 1.2958232654470142e-05, "loss": 0.8624, "step": 1342 }, { "epoch": 1.250698974836906, "loss_cot": 0.49702343344688416, "loss_nocot": 0.3297770321369171, "step": 1342 }, { "epoch": 1.2516309412861137, "grad_norm": 0.6247865691682815, "learning_rate": 1.2951328960994135e-05, "loss": 0.846, "step": 1343 }, { "epoch": 1.2516309412861137, "loss_cot": 0.5161828994750977, "loss_nocot": 0.3535803556442261, "step": 1343 }, { "epoch": 1.2525629077353215, "grad_norm": 0.645908888759509, "learning_rate": 1.2944425267518124e-05, "loss": 0.8626, "step": 1344 }, { "epoch": 1.2525629077353215, "loss_cot": 0.5459742546081543, "loss_nocot": 0.30008482933044434, "step": 1344 }, { "epoch": 1.2534948741845293, "grad_norm": 0.658609689823168, "learning_rate": 1.2937521574042113e-05, "loss": 0.8869, "step": 1345 }, { "epoch": 1.2534948741845293, "loss_cot": 0.49499887228012085, "loss_nocot": 0.2371257245540619, "step": 1345 }, { "epoch": 1.254426840633737, "grad_norm": 0.5772408645395516, "learning_rate": 1.2930617880566103e-05, "loss": 0.8026, "step": 1346 }, { "epoch": 1.254426840633737, "loss_cot": 0.4899764955043793, "loss_nocot": 0.33820614218711853, "step": 1346 }, { "epoch": 1.2553588070829451, "grad_norm": 0.5816659461228275, "learning_rate": 1.2923714187090096e-05, "loss": 0.8024, "step": 1347 }, { "epoch": 1.2553588070829451, "loss_cot": 0.5030477046966553, "loss_nocot": 0.3214465379714966, "step": 1347 }, { "epoch": 1.256290773532153, "grad_norm": 0.6239818215920951, "learning_rate": 1.2916810493614085e-05, "loss": 0.9168, "step": 1348 }, { "epoch": 1.256290773532153, "loss_cot": 0.5699326992034912, "loss_nocot": 0.31248724460601807, "step": 1348 }, { "epoch": 1.2572227399813607, "grad_norm": 0.6255513730029489, "learning_rate": 1.2909906800138074e-05, "loss": 0.8783, "step": 1349 }, { "epoch": 1.2572227399813607, "loss_cot": 0.5337885618209839, "loss_nocot": 0.3090493679046631, "step": 1349 }, { "epoch": 1.2581547064305685, "grad_norm": 0.644626066750542, "learning_rate": 1.2903003106662065e-05, "loss": 0.873, "step": 1350 }, { "epoch": 1.2581547064305685, "loss_cot": 0.48782020807266235, "loss_nocot": 0.307100772857666, "step": 1350 }, { "epoch": 1.2590866728797763, "grad_norm": 0.6615349136383301, "learning_rate": 1.2896099413186055e-05, "loss": 0.9289, "step": 1351 }, { "epoch": 1.2590866728797763, "loss_cot": 0.5353630781173706, "loss_nocot": 0.5956454873085022, "step": 1351 }, { "epoch": 1.260018639328984, "grad_norm": 0.7197500059316239, "learning_rate": 1.2889195719710046e-05, "loss": 0.9767, "step": 1352 }, { "epoch": 1.260018639328984, "loss_cot": 0.5209375619888306, "loss_nocot": 0.34728100895881653, "step": 1352 }, { "epoch": 1.2609506057781918, "grad_norm": 0.5868776560725314, "learning_rate": 1.2882292026234035e-05, "loss": 0.8382, "step": 1353 }, { "epoch": 1.2609506057781918, "loss_cot": 0.5856282711029053, "loss_nocot": 0.5150933265686035, "step": 1353 }, { "epoch": 1.2618825722273999, "grad_norm": 0.6579446723821082, "learning_rate": 1.2875388332758028e-05, "loss": 0.9246, "step": 1354 }, { "epoch": 1.2618825722273999, "loss_cot": 0.49173006415367126, "loss_nocot": 0.4174054265022278, "step": 1354 }, { "epoch": 1.2628145386766076, "grad_norm": 0.5733578421914753, "learning_rate": 1.2868484639282017e-05, "loss": 0.8007, "step": 1355 }, { "epoch": 1.2628145386766076, "loss_cot": 0.5266802310943604, "loss_nocot": 0.44168224930763245, "step": 1355 }, { "epoch": 1.2637465051258154, "grad_norm": 0.7066712340130765, "learning_rate": 1.2861580945806007e-05, "loss": 0.9608, "step": 1356 }, { "epoch": 1.2637465051258154, "loss_cot": 0.4842177629470825, "loss_nocot": 0.29189395904541016, "step": 1356 }, { "epoch": 1.2646784715750232, "grad_norm": 0.5933959194891802, "learning_rate": 1.2854677252329996e-05, "loss": 0.8284, "step": 1357 }, { "epoch": 1.2646784715750232, "loss_cot": 0.5062404870986938, "loss_nocot": 0.340606689453125, "step": 1357 }, { "epoch": 1.2656104380242312, "grad_norm": 0.6043538509188562, "learning_rate": 1.2847773558853989e-05, "loss": 0.8634, "step": 1358 }, { "epoch": 1.2656104380242312, "loss_cot": 0.44324272871017456, "loss_nocot": 0.36845138669013977, "step": 1358 }, { "epoch": 1.266542404473439, "grad_norm": 0.6191587369516811, "learning_rate": 1.2840869865377978e-05, "loss": 0.817, "step": 1359 }, { "epoch": 1.266542404473439, "loss_cot": 0.5026891827583313, "loss_nocot": 0.3412390351295471, "step": 1359 }, { "epoch": 1.2674743709226468, "grad_norm": 0.6294633417321854, "learning_rate": 1.2833966171901969e-05, "loss": 0.8525, "step": 1360 }, { "epoch": 1.2674743709226468, "loss_cot": 0.5007408857345581, "loss_nocot": 0.4203612208366394, "step": 1360 }, { "epoch": 1.2684063373718546, "grad_norm": 0.6548660148925186, "learning_rate": 1.2827062478425958e-05, "loss": 0.9036, "step": 1361 }, { "epoch": 1.2684063373718546, "loss_cot": 0.47488152980804443, "loss_nocot": 0.44863420724868774, "step": 1361 }, { "epoch": 1.2693383038210624, "grad_norm": 0.6420924847078241, "learning_rate": 1.282015878494995e-05, "loss": 0.8758, "step": 1362 }, { "epoch": 1.2693383038210624, "loss_cot": 0.5747612714767456, "loss_nocot": 0.3533431887626648, "step": 1362 }, { "epoch": 1.2702702702702702, "grad_norm": 0.6204381831362741, "learning_rate": 1.2813255091473939e-05, "loss": 0.8058, "step": 1363 }, { "epoch": 1.2702702702702702, "loss_cot": 0.49793365597724915, "loss_nocot": 0.4387122392654419, "step": 1363 }, { "epoch": 1.271202236719478, "grad_norm": 0.6398078235726432, "learning_rate": 1.280635139799793e-05, "loss": 0.8954, "step": 1364 }, { "epoch": 1.271202236719478, "loss_cot": 0.5399281978607178, "loss_nocot": 0.2266068458557129, "step": 1364 }, { "epoch": 1.272134203168686, "grad_norm": 0.628827232277846, "learning_rate": 1.279944770452192e-05, "loss": 0.8128, "step": 1365 }, { "epoch": 1.272134203168686, "loss_cot": 0.5214607119560242, "loss_nocot": 0.36845022439956665, "step": 1365 }, { "epoch": 1.2730661696178938, "grad_norm": 0.5895487610249082, "learning_rate": 1.2792544011045911e-05, "loss": 0.814, "step": 1366 }, { "epoch": 1.2730661696178938, "loss_cot": 0.4543265700340271, "loss_nocot": 0.40908950567245483, "step": 1366 }, { "epoch": 1.2739981360671015, "grad_norm": 0.6350379602917546, "learning_rate": 1.27856403175699e-05, "loss": 0.8753, "step": 1367 }, { "epoch": 1.2739981360671015, "loss_cot": 0.5680857300758362, "loss_nocot": 0.4681529700756073, "step": 1367 }, { "epoch": 1.2749301025163093, "grad_norm": 0.6530273890503002, "learning_rate": 1.2778736624093891e-05, "loss": 0.9328, "step": 1368 }, { "epoch": 1.2749301025163093, "loss_cot": 0.5006275177001953, "loss_nocot": 0.31624895334243774, "step": 1368 }, { "epoch": 1.2758620689655173, "grad_norm": 0.6251923203889255, "learning_rate": 1.2771832930617882e-05, "loss": 0.8157, "step": 1369 }, { "epoch": 1.2758620689655173, "loss_cot": 0.4980151653289795, "loss_nocot": 0.3181772530078888, "step": 1369 }, { "epoch": 1.2767940354147251, "grad_norm": 0.5996760910419163, "learning_rate": 1.2764929237141873e-05, "loss": 0.8242, "step": 1370 }, { "epoch": 1.2767940354147251, "loss_cot": 0.4812214970588684, "loss_nocot": 0.3324209749698639, "step": 1370 }, { "epoch": 1.277726001863933, "grad_norm": 0.6382933871854563, "learning_rate": 1.2758025543665862e-05, "loss": 0.8405, "step": 1371 }, { "epoch": 1.277726001863933, "loss_cot": 0.5437679886817932, "loss_nocot": 0.327356219291687, "step": 1371 }, { "epoch": 1.2786579683131407, "grad_norm": 0.5952033622044066, "learning_rate": 1.2751121850189854e-05, "loss": 0.8523, "step": 1372 }, { "epoch": 1.2786579683131407, "loss_cot": 0.4728124737739563, "loss_nocot": 0.29271286725997925, "step": 1372 }, { "epoch": 1.2795899347623485, "grad_norm": 0.6143766253258558, "learning_rate": 1.2744218156713843e-05, "loss": 0.8311, "step": 1373 }, { "epoch": 1.2795899347623485, "loss_cot": 0.5054976344108582, "loss_nocot": 0.36427363753318787, "step": 1373 }, { "epoch": 1.2805219012115563, "grad_norm": 0.6614756254896126, "learning_rate": 1.2737314463237834e-05, "loss": 0.8936, "step": 1374 }, { "epoch": 1.2805219012115563, "loss_cot": 0.4532911777496338, "loss_nocot": 0.2652440369129181, "step": 1374 }, { "epoch": 1.281453867660764, "grad_norm": 0.6093216675780012, "learning_rate": 1.2730410769761823e-05, "loss": 0.802, "step": 1375 }, { "epoch": 1.281453867660764, "loss_cot": 0.5374487042427063, "loss_nocot": 0.363453209400177, "step": 1375 }, { "epoch": 1.282385834109972, "grad_norm": 0.5905359406336725, "learning_rate": 1.2723507076285815e-05, "loss": 0.8603, "step": 1376 }, { "epoch": 1.282385834109972, "loss_cot": 0.40866950154304504, "loss_nocot": 0.4551815986633301, "step": 1376 }, { "epoch": 1.2833178005591799, "grad_norm": 0.6193043772484395, "learning_rate": 1.2716603382809804e-05, "loss": 0.8585, "step": 1377 }, { "epoch": 1.2833178005591799, "loss_cot": 0.5338533520698547, "loss_nocot": 0.3310367166996002, "step": 1377 }, { "epoch": 1.2842497670083877, "grad_norm": 0.6240398283766705, "learning_rate": 1.2709699689333795e-05, "loss": 0.8438, "step": 1378 }, { "epoch": 1.2842497670083877, "loss_cot": 0.4834493100643158, "loss_nocot": 0.3407219648361206, "step": 1378 }, { "epoch": 1.2851817334575955, "grad_norm": 0.7466163420027936, "learning_rate": 1.2702795995857784e-05, "loss": 0.87, "step": 1379 }, { "epoch": 1.2851817334575955, "loss_cot": 0.5061825513839722, "loss_nocot": 0.3391144871711731, "step": 1379 }, { "epoch": 1.2861136999068035, "grad_norm": 0.6612453028104464, "learning_rate": 1.2695892302381776e-05, "loss": 0.9503, "step": 1380 }, { "epoch": 1.2861136999068035, "loss_cot": 0.5482182502746582, "loss_nocot": 0.43674659729003906, "step": 1380 }, { "epoch": 1.2870456663560113, "grad_norm": 0.62840969769862, "learning_rate": 1.2688988608905766e-05, "loss": 0.8808, "step": 1381 }, { "epoch": 1.2870456663560113, "loss_cot": 0.4830714464187622, "loss_nocot": 0.34335604310035706, "step": 1381 }, { "epoch": 1.287977632805219, "grad_norm": 0.6245994658588642, "learning_rate": 1.2682084915429755e-05, "loss": 0.8899, "step": 1382 }, { "epoch": 1.287977632805219, "loss_cot": 0.4769931137561798, "loss_nocot": 0.31660300493240356, "step": 1382 }, { "epoch": 1.2889095992544268, "grad_norm": 0.638087080084618, "learning_rate": 1.2675181221953747e-05, "loss": 0.8692, "step": 1383 }, { "epoch": 1.2889095992544268, "loss_cot": 0.5387762784957886, "loss_nocot": 0.3499404788017273, "step": 1383 }, { "epoch": 1.2898415657036346, "grad_norm": 0.6521148845919653, "learning_rate": 1.2668277528477738e-05, "loss": 0.882, "step": 1384 }, { "epoch": 1.2898415657036346, "loss_cot": 0.49721407890319824, "loss_nocot": 0.36862289905548096, "step": 1384 }, { "epoch": 1.2907735321528424, "grad_norm": 0.6676729834588624, "learning_rate": 1.2661373835001727e-05, "loss": 0.9263, "step": 1385 }, { "epoch": 1.2907735321528424, "loss_cot": 0.47863534092903137, "loss_nocot": 0.4280817210674286, "step": 1385 }, { "epoch": 1.2917054986020502, "grad_norm": 0.7037889079876173, "learning_rate": 1.2654470141525716e-05, "loss": 0.893, "step": 1386 }, { "epoch": 1.2917054986020502, "loss_cot": 0.5116761326789856, "loss_nocot": 0.2663520872592926, "step": 1386 }, { "epoch": 1.2926374650512582, "grad_norm": 0.6009146424107005, "learning_rate": 1.2647566448049708e-05, "loss": 0.81, "step": 1387 }, { "epoch": 1.2926374650512582, "loss_cot": 0.552033543586731, "loss_nocot": 0.3721221685409546, "step": 1387 }, { "epoch": 1.293569431500466, "grad_norm": 0.6665316760482612, "learning_rate": 1.2640662754573699e-05, "loss": 0.892, "step": 1388 }, { "epoch": 1.293569431500466, "loss_cot": 0.5063562393188477, "loss_nocot": 0.3547244966030121, "step": 1388 }, { "epoch": 1.2945013979496738, "grad_norm": 0.6398992642160859, "learning_rate": 1.2633759061097688e-05, "loss": 0.8917, "step": 1389 }, { "epoch": 1.2945013979496738, "loss_cot": 0.5120521783828735, "loss_nocot": 0.40370556712150574, "step": 1389 }, { "epoch": 1.2954333643988816, "grad_norm": 0.6954690965748171, "learning_rate": 1.2626855367621677e-05, "loss": 0.9126, "step": 1390 }, { "epoch": 1.2954333643988816, "loss_cot": 0.4890161156654358, "loss_nocot": 0.47691112756729126, "step": 1390 }, { "epoch": 1.2963653308480896, "grad_norm": 0.676248984633388, "learning_rate": 1.261995167414567e-05, "loss": 0.9121, "step": 1391 }, { "epoch": 1.2963653308480896, "loss_cot": 0.538906455039978, "loss_nocot": 0.2619228661060333, "step": 1391 }, { "epoch": 1.2972972972972974, "grad_norm": 0.5949873266522244, "learning_rate": 1.2613047980669658e-05, "loss": 0.8116, "step": 1392 }, { "epoch": 1.2972972972972974, "loss_cot": 0.4541809558868408, "loss_nocot": 0.38977599143981934, "step": 1392 }, { "epoch": 1.2982292637465052, "grad_norm": 0.6398254024900761, "learning_rate": 1.260614428719365e-05, "loss": 0.9053, "step": 1393 }, { "epoch": 1.2982292637465052, "loss_cot": 0.5053274035453796, "loss_nocot": 0.329694002866745, "step": 1393 }, { "epoch": 1.299161230195713, "grad_norm": 0.6429321969393981, "learning_rate": 1.2599240593717642e-05, "loss": 0.8905, "step": 1394 }, { "epoch": 1.299161230195713, "loss_cot": 0.5216435194015503, "loss_nocot": 0.4217594861984253, "step": 1394 }, { "epoch": 1.3000931966449207, "grad_norm": 0.62742305611142, "learning_rate": 1.259233690024163e-05, "loss": 0.8463, "step": 1395 }, { "epoch": 1.3000931966449207, "loss_cot": 0.5415509343147278, "loss_nocot": 0.33207863569259644, "step": 1395 }, { "epoch": 1.3010251630941285, "grad_norm": 0.765651171080259, "learning_rate": 1.258543320676562e-05, "loss": 0.899, "step": 1396 }, { "epoch": 1.3010251630941285, "loss_cot": 0.524323582649231, "loss_nocot": 0.34958863258361816, "step": 1396 }, { "epoch": 1.3019571295433363, "grad_norm": 0.5855382453525826, "learning_rate": 1.257852951328961e-05, "loss": 0.8406, "step": 1397 }, { "epoch": 1.3019571295433363, "loss_cot": 0.5541163682937622, "loss_nocot": 0.286834716796875, "step": 1397 }, { "epoch": 1.3028890959925443, "grad_norm": 0.6089979051304614, "learning_rate": 1.2571625819813603e-05, "loss": 0.8229, "step": 1398 }, { "epoch": 1.3028890959925443, "loss_cot": 0.4135362505912781, "loss_nocot": 0.42812031507492065, "step": 1398 }, { "epoch": 1.303821062441752, "grad_norm": 0.6619150879509904, "learning_rate": 1.2564722126337592e-05, "loss": 0.8805, "step": 1399 }, { "epoch": 1.303821062441752, "loss_cot": 0.5185832381248474, "loss_nocot": 0.3078351616859436, "step": 1399 }, { "epoch": 1.30475302889096, "grad_norm": 0.6100345013985837, "learning_rate": 1.2557818432861581e-05, "loss": 0.8946, "step": 1400 }, { "epoch": 1.30475302889096, "loss_cot": 0.5159021019935608, "loss_nocot": 0.38237264752388, "step": 1400 }, { "epoch": 1.3056849953401677, "grad_norm": 0.6336489041732465, "learning_rate": 1.2550914739385572e-05, "loss": 0.8896, "step": 1401 }, { "epoch": 1.3056849953401677, "loss_cot": 0.5615895986557007, "loss_nocot": 0.24387289583683014, "step": 1401 }, { "epoch": 1.3066169617893757, "grad_norm": 0.5731939737243918, "learning_rate": 1.2544011045909562e-05, "loss": 0.8406, "step": 1402 }, { "epoch": 1.3066169617893757, "loss_cot": 0.4892243444919586, "loss_nocot": 0.4118140935897827, "step": 1402 }, { "epoch": 1.3075489282385835, "grad_norm": 0.6067937642669439, "learning_rate": 1.2537107352433553e-05, "loss": 0.8337, "step": 1403 }, { "epoch": 1.3075489282385835, "loss_cot": 0.5470215082168579, "loss_nocot": 0.46601414680480957, "step": 1403 }, { "epoch": 1.3084808946877913, "grad_norm": 0.643383297722454, "learning_rate": 1.2530203658957542e-05, "loss": 0.8868, "step": 1404 }, { "epoch": 1.3084808946877913, "loss_cot": 0.4857054352760315, "loss_nocot": 0.41047123074531555, "step": 1404 }, { "epoch": 1.309412861136999, "grad_norm": 0.6442119862105917, "learning_rate": 1.2523299965481535e-05, "loss": 0.8574, "step": 1405 }, { "epoch": 1.309412861136999, "loss_cot": 0.48830413818359375, "loss_nocot": 0.44963955879211426, "step": 1405 }, { "epoch": 1.3103448275862069, "grad_norm": 0.6230234612267191, "learning_rate": 1.2516396272005524e-05, "loss": 0.866, "step": 1406 }, { "epoch": 1.3103448275862069, "loss_cot": 0.51072096824646, "loss_nocot": 0.3243519067764282, "step": 1406 }, { "epoch": 1.3112767940354146, "grad_norm": 0.64446165424758, "learning_rate": 1.2509492578529514e-05, "loss": 0.8725, "step": 1407 }, { "epoch": 1.3112767940354146, "loss_cot": 0.5526655912399292, "loss_nocot": 0.30451178550720215, "step": 1407 }, { "epoch": 1.3122087604846224, "grad_norm": 0.6550412457556861, "learning_rate": 1.2502588885053503e-05, "loss": 0.9279, "step": 1408 }, { "epoch": 1.3122087604846224, "loss_cot": 0.4909244775772095, "loss_nocot": 0.4289897680282593, "step": 1408 }, { "epoch": 1.3131407269338304, "grad_norm": 0.622651098768421, "learning_rate": 1.2495685191577496e-05, "loss": 0.8657, "step": 1409 }, { "epoch": 1.3131407269338304, "loss_cot": 0.5330051183700562, "loss_nocot": 0.5225712656974792, "step": 1409 }, { "epoch": 1.3140726933830382, "grad_norm": 0.6796268818136609, "learning_rate": 1.2488781498101485e-05, "loss": 0.9055, "step": 1410 }, { "epoch": 1.3140726933830382, "loss_cot": 0.4806525707244873, "loss_nocot": 0.44418245553970337, "step": 1410 }, { "epoch": 1.315004659832246, "grad_norm": 0.66439899693985, "learning_rate": 1.2481877804625476e-05, "loss": 0.884, "step": 1411 }, { "epoch": 1.315004659832246, "loss_cot": 0.5042030811309814, "loss_nocot": 0.3683475852012634, "step": 1411 }, { "epoch": 1.3159366262814538, "grad_norm": 0.6649076526739548, "learning_rate": 1.2474974111149465e-05, "loss": 0.8653, "step": 1412 }, { "epoch": 1.3159366262814538, "loss_cot": 0.5113365650177002, "loss_nocot": 0.2947806715965271, "step": 1412 }, { "epoch": 1.3168685927306618, "grad_norm": 0.6182224704027388, "learning_rate": 1.2468070417673457e-05, "loss": 0.8726, "step": 1413 }, { "epoch": 1.3168685927306618, "loss_cot": 0.48054999113082886, "loss_nocot": 0.3180240988731384, "step": 1413 }, { "epoch": 1.3178005591798696, "grad_norm": 0.6610324512295896, "learning_rate": 1.2461166724197446e-05, "loss": 0.9109, "step": 1414 }, { "epoch": 1.3178005591798696, "loss_cot": 0.5520966053009033, "loss_nocot": 0.3073733448982239, "step": 1414 }, { "epoch": 1.3187325256290774, "grad_norm": 0.6296129255525011, "learning_rate": 1.2454263030721437e-05, "loss": 0.8778, "step": 1415 }, { "epoch": 1.3187325256290774, "loss_cot": 0.4826585054397583, "loss_nocot": 0.3789732754230499, "step": 1415 }, { "epoch": 1.3196644920782852, "grad_norm": 0.6434833252575488, "learning_rate": 1.2447359337245428e-05, "loss": 0.8826, "step": 1416 }, { "epoch": 1.3196644920782852, "loss_cot": 0.46674537658691406, "loss_nocot": 0.4050218164920807, "step": 1416 }, { "epoch": 1.320596458527493, "grad_norm": 0.6162018811664703, "learning_rate": 1.2440455643769418e-05, "loss": 0.8328, "step": 1417 }, { "epoch": 1.320596458527493, "loss_cot": 0.5361555814743042, "loss_nocot": 0.3590353727340698, "step": 1417 }, { "epoch": 1.3215284249767008, "grad_norm": 0.7039290223636896, "learning_rate": 1.2433551950293407e-05, "loss": 0.9286, "step": 1418 }, { "epoch": 1.3215284249767008, "loss_cot": 0.47264236211776733, "loss_nocot": 0.3002285063266754, "step": 1418 }, { "epoch": 1.3224603914259085, "grad_norm": 0.5977177021799567, "learning_rate": 1.2426648256817398e-05, "loss": 0.8167, "step": 1419 }, { "epoch": 1.3224603914259085, "loss_cot": 0.4907715320587158, "loss_nocot": 0.3200802206993103, "step": 1419 }, { "epoch": 1.3233923578751166, "grad_norm": 0.6399312295162247, "learning_rate": 1.2419744563341389e-05, "loss": 0.8883, "step": 1420 }, { "epoch": 1.3233923578751166, "loss_cot": 0.46995973587036133, "loss_nocot": 0.4140392243862152, "step": 1420 }, { "epoch": 1.3243243243243243, "grad_norm": 0.6323670430357965, "learning_rate": 1.241284086986538e-05, "loss": 0.8196, "step": 1421 }, { "epoch": 1.3243243243243243, "loss_cot": 0.5262387990951538, "loss_nocot": 0.23671811819076538, "step": 1421 }, { "epoch": 1.3252562907735321, "grad_norm": 0.6482222396999434, "learning_rate": 1.2405937176389369e-05, "loss": 0.8134, "step": 1422 }, { "epoch": 1.3252562907735321, "loss_cot": 0.5152066946029663, "loss_nocot": 0.3151816129684448, "step": 1422 }, { "epoch": 1.32618825722274, "grad_norm": 0.5939076561759671, "learning_rate": 1.2399033482913361e-05, "loss": 0.8386, "step": 1423 }, { "epoch": 1.32618825722274, "loss_cot": 0.5691782236099243, "loss_nocot": 0.35821399092674255, "step": 1423 }, { "epoch": 1.327120223671948, "grad_norm": 0.562763745829405, "learning_rate": 1.239212978943735e-05, "loss": 0.8, "step": 1424 }, { "epoch": 1.327120223671948, "loss_cot": 0.5725752711296082, "loss_nocot": 0.3237033784389496, "step": 1424 }, { "epoch": 1.3280521901211557, "grad_norm": 0.6550249354273385, "learning_rate": 1.238522609596134e-05, "loss": 0.8967, "step": 1425 }, { "epoch": 1.3280521901211557, "loss_cot": 0.5641951560974121, "loss_nocot": 0.27679359912872314, "step": 1425 }, { "epoch": 1.3289841565703635, "grad_norm": 0.5957862660810974, "learning_rate": 1.237832240248533e-05, "loss": 0.8608, "step": 1426 }, { "epoch": 1.3289841565703635, "loss_cot": 0.5172944068908691, "loss_nocot": 0.3742824196815491, "step": 1426 }, { "epoch": 1.3299161230195713, "grad_norm": 0.6792479958049301, "learning_rate": 1.2371418709009322e-05, "loss": 0.9526, "step": 1427 }, { "epoch": 1.3299161230195713, "loss_cot": 0.5067553520202637, "loss_nocot": 0.3680803179740906, "step": 1427 }, { "epoch": 1.330848089468779, "grad_norm": 0.7107354973656121, "learning_rate": 1.2364515015533311e-05, "loss": 0.902, "step": 1428 }, { "epoch": 1.330848089468779, "loss_cot": 0.5204549431800842, "loss_nocot": 0.30174052715301514, "step": 1428 }, { "epoch": 1.3317800559179869, "grad_norm": 0.5885194958629161, "learning_rate": 1.2357611322057302e-05, "loss": 0.8616, "step": 1429 }, { "epoch": 1.3317800559179869, "loss_cot": 0.5221761465072632, "loss_nocot": 0.5275848507881165, "step": 1429 }, { "epoch": 1.3327120223671947, "grad_norm": 0.7226769694575963, "learning_rate": 1.2350707628581291e-05, "loss": 0.9249, "step": 1430 }, { "epoch": 1.3327120223671947, "loss_cot": 0.49084484577178955, "loss_nocot": 0.37909942865371704, "step": 1430 }, { "epoch": 1.3336439888164027, "grad_norm": 0.6560590865849194, "learning_rate": 1.2343803935105284e-05, "loss": 0.9105, "step": 1431 }, { "epoch": 1.3336439888164027, "loss_cot": 0.5484042763710022, "loss_nocot": 0.2650917172431946, "step": 1431 }, { "epoch": 1.3345759552656105, "grad_norm": 0.6251842604136015, "learning_rate": 1.2336900241629273e-05, "loss": 0.8977, "step": 1432 }, { "epoch": 1.3345759552656105, "loss_cot": 0.5118809342384338, "loss_nocot": 0.38674992322921753, "step": 1432 }, { "epoch": 1.3355079217148182, "grad_norm": 0.708774178676971, "learning_rate": 1.2329996548153262e-05, "loss": 0.8855, "step": 1433 }, { "epoch": 1.3355079217148182, "loss_cot": 0.4921954870223999, "loss_nocot": 0.27440571784973145, "step": 1433 }, { "epoch": 1.336439888164026, "grad_norm": 0.5775414739131393, "learning_rate": 1.2323092854677254e-05, "loss": 0.842, "step": 1434 }, { "epoch": 1.336439888164026, "loss_cot": 0.496122270822525, "loss_nocot": 0.24666428565979004, "step": 1434 }, { "epoch": 1.337371854613234, "grad_norm": 0.6209456040742503, "learning_rate": 1.2316189161201245e-05, "loss": 0.8686, "step": 1435 }, { "epoch": 1.337371854613234, "loss_cot": 0.5609090328216553, "loss_nocot": 0.2847304940223694, "step": 1435 }, { "epoch": 1.3383038210624418, "grad_norm": 0.6023139037529058, "learning_rate": 1.2309285467725234e-05, "loss": 0.8766, "step": 1436 }, { "epoch": 1.3383038210624418, "loss_cot": 0.5441983938217163, "loss_nocot": 0.36443841457366943, "step": 1436 }, { "epoch": 1.3392357875116496, "grad_norm": 0.6708929808011762, "learning_rate": 1.2302381774249223e-05, "loss": 0.8879, "step": 1437 }, { "epoch": 1.3392357875116496, "loss_cot": 0.5827527642250061, "loss_nocot": 0.3771449327468872, "step": 1437 }, { "epoch": 1.3401677539608574, "grad_norm": 0.6857570657433402, "learning_rate": 1.2295478080773215e-05, "loss": 0.8682, "step": 1438 }, { "epoch": 1.3401677539608574, "loss_cot": 0.4711613655090332, "loss_nocot": 0.37719792127609253, "step": 1438 }, { "epoch": 1.3410997204100652, "grad_norm": 0.6565791129244187, "learning_rate": 1.2288574387297206e-05, "loss": 0.8799, "step": 1439 }, { "epoch": 1.3410997204100652, "loss_cot": 0.5869454145431519, "loss_nocot": 0.2513231933116913, "step": 1439 }, { "epoch": 1.342031686859273, "grad_norm": 0.6149963803901052, "learning_rate": 1.2281670693821195e-05, "loss": 0.8605, "step": 1440 }, { "epoch": 1.342031686859273, "loss_cot": 0.5329867005348206, "loss_nocot": 0.2833908796310425, "step": 1440 }, { "epoch": 1.3429636533084808, "grad_norm": 0.6370469198829497, "learning_rate": 1.2274767000345184e-05, "loss": 0.8862, "step": 1441 }, { "epoch": 1.3429636533084808, "loss_cot": 0.4551929235458374, "loss_nocot": 0.2949689030647278, "step": 1441 }, { "epoch": 1.3438956197576888, "grad_norm": 0.6016965495510722, "learning_rate": 1.2267863306869176e-05, "loss": 0.8051, "step": 1442 }, { "epoch": 1.3438956197576888, "loss_cot": 0.5162041783332825, "loss_nocot": 0.4649167060852051, "step": 1442 }, { "epoch": 1.3448275862068966, "grad_norm": 0.6553021933590563, "learning_rate": 1.2260959613393166e-05, "loss": 0.9241, "step": 1443 }, { "epoch": 1.3448275862068966, "loss_cot": 0.5612736344337463, "loss_nocot": 0.32128268480300903, "step": 1443 }, { "epoch": 1.3457595526561044, "grad_norm": 0.6541369261632891, "learning_rate": 1.2254055919917156e-05, "loss": 0.9186, "step": 1444 }, { "epoch": 1.3457595526561044, "loss_cot": 0.4864577353000641, "loss_nocot": 0.39322394132614136, "step": 1444 }, { "epoch": 1.3466915191053122, "grad_norm": 0.6298696958427042, "learning_rate": 1.2247152226441149e-05, "loss": 0.8521, "step": 1445 }, { "epoch": 1.3466915191053122, "loss_cot": 0.4700402021408081, "loss_nocot": 0.2573337256908417, "step": 1445 }, { "epoch": 1.3476234855545202, "grad_norm": 0.6219744416138165, "learning_rate": 1.2240248532965138e-05, "loss": 0.8487, "step": 1446 }, { "epoch": 1.3476234855545202, "loss_cot": 0.49745601415634155, "loss_nocot": 0.43882501125335693, "step": 1446 }, { "epoch": 1.348555452003728, "grad_norm": 0.6343116384097355, "learning_rate": 1.2233344839489127e-05, "loss": 0.8604, "step": 1447 }, { "epoch": 1.348555452003728, "loss_cot": 0.5801386833190918, "loss_nocot": 0.4480413496494293, "step": 1447 }, { "epoch": 1.3494874184529357, "grad_norm": 0.5982918115707021, "learning_rate": 1.2226441146013117e-05, "loss": 0.8444, "step": 1448 }, { "epoch": 1.3494874184529357, "loss_cot": 0.5313177108764648, "loss_nocot": 0.3819487690925598, "step": 1448 }, { "epoch": 1.3504193849021435, "grad_norm": 0.64401281354184, "learning_rate": 1.221953745253711e-05, "loss": 0.883, "step": 1449 }, { "epoch": 1.3504193849021435, "loss_cot": 0.5333226323127747, "loss_nocot": 0.36531785130500793, "step": 1449 }, { "epoch": 1.3513513513513513, "grad_norm": 0.6494283909924602, "learning_rate": 1.2212633759061099e-05, "loss": 0.8879, "step": 1450 }, { "epoch": 1.3513513513513513, "loss_cot": 0.5817470550537109, "loss_nocot": 0.3599085807800293, "step": 1450 }, { "epoch": 1.352283317800559, "grad_norm": 0.6325589796771205, "learning_rate": 1.2205730065585088e-05, "loss": 0.8646, "step": 1451 }, { "epoch": 1.352283317800559, "loss_cot": 0.47091448307037354, "loss_nocot": 0.3644961714744568, "step": 1451 }, { "epoch": 1.353215284249767, "grad_norm": 0.6718079122660845, "learning_rate": 1.2198826372109079e-05, "loss": 0.8929, "step": 1452 }, { "epoch": 1.353215284249767, "loss_cot": 0.5253594517707825, "loss_nocot": 0.31295889616012573, "step": 1452 }, { "epoch": 1.354147250698975, "grad_norm": 0.6218084543363531, "learning_rate": 1.219192267863307e-05, "loss": 0.855, "step": 1453 }, { "epoch": 1.354147250698975, "loss_cot": 0.5792482495307922, "loss_nocot": 0.2865665555000305, "step": 1453 }, { "epoch": 1.3550792171481827, "grad_norm": 0.633588028944425, "learning_rate": 1.218501898515706e-05, "loss": 0.811, "step": 1454 }, { "epoch": 1.3550792171481827, "loss_cot": 0.4974004626274109, "loss_nocot": 0.2758229076862335, "step": 1454 }, { "epoch": 1.3560111835973905, "grad_norm": 0.6504266443678398, "learning_rate": 1.217811529168105e-05, "loss": 0.8805, "step": 1455 }, { "epoch": 1.3560111835973905, "loss_cot": 0.5451186299324036, "loss_nocot": 0.24892842769622803, "step": 1455 }, { "epoch": 1.3569431500465983, "grad_norm": 0.6574289407355559, "learning_rate": 1.2171211598205042e-05, "loss": 0.8794, "step": 1456 }, { "epoch": 1.3569431500465983, "loss_cot": 0.5623011589050293, "loss_nocot": 0.3521978259086609, "step": 1456 }, { "epoch": 1.3578751164958063, "grad_norm": 0.6110886004378618, "learning_rate": 1.216430790472903e-05, "loss": 0.8503, "step": 1457 }, { "epoch": 1.3578751164958063, "loss_cot": 0.5921657681465149, "loss_nocot": 0.4422277808189392, "step": 1457 }, { "epoch": 1.358807082945014, "grad_norm": 0.6750500894665655, "learning_rate": 1.2157404211253021e-05, "loss": 0.9179, "step": 1458 }, { "epoch": 1.358807082945014, "loss_cot": 0.5229502320289612, "loss_nocot": 0.2542942762374878, "step": 1458 }, { "epoch": 1.3597390493942219, "grad_norm": 0.6715416647558543, "learning_rate": 1.215050051777701e-05, "loss": 0.9063, "step": 1459 }, { "epoch": 1.3597390493942219, "loss_cot": 0.5061269402503967, "loss_nocot": 0.3491407632827759, "step": 1459 }, { "epoch": 1.3606710158434296, "grad_norm": 0.621437531249243, "learning_rate": 1.2143596824301003e-05, "loss": 0.8329, "step": 1460 }, { "epoch": 1.3606710158434296, "loss_cot": 0.5258932709693909, "loss_nocot": 0.32660794258117676, "step": 1460 }, { "epoch": 1.3616029822926374, "grad_norm": 0.6917972261487201, "learning_rate": 1.2136693130824992e-05, "loss": 0.8765, "step": 1461 }, { "epoch": 1.3616029822926374, "loss_cot": 0.45441102981567383, "loss_nocot": 0.3152180016040802, "step": 1461 }, { "epoch": 1.3625349487418452, "grad_norm": 0.6436041738559862, "learning_rate": 1.2129789437348983e-05, "loss": 0.837, "step": 1462 }, { "epoch": 1.3625349487418452, "loss_cot": 0.488175630569458, "loss_nocot": 0.49791550636291504, "step": 1462 }, { "epoch": 1.363466915191053, "grad_norm": 0.6611306798156916, "learning_rate": 1.2122885743872973e-05, "loss": 0.9203, "step": 1463 }, { "epoch": 1.363466915191053, "loss_cot": 0.541060745716095, "loss_nocot": 0.3488181233406067, "step": 1463 }, { "epoch": 1.364398881640261, "grad_norm": 0.5701252313618992, "learning_rate": 1.2115982050396964e-05, "loss": 0.7917, "step": 1464 }, { "epoch": 1.364398881640261, "loss_cot": 0.5402778387069702, "loss_nocot": 0.29084229469299316, "step": 1464 }, { "epoch": 1.3653308480894688, "grad_norm": 0.5696905287414086, "learning_rate": 1.2109078356920953e-05, "loss": 0.8562, "step": 1465 }, { "epoch": 1.3653308480894688, "loss_cot": 0.5676455497741699, "loss_nocot": 0.4266950488090515, "step": 1465 }, { "epoch": 1.3662628145386766, "grad_norm": 0.648406943611785, "learning_rate": 1.2102174663444944e-05, "loss": 0.9072, "step": 1466 }, { "epoch": 1.3662628145386766, "loss_cot": 0.4930844008922577, "loss_nocot": 0.40383318066596985, "step": 1466 }, { "epoch": 1.3671947809878844, "grad_norm": 0.6419910701207302, "learning_rate": 1.2095270969968935e-05, "loss": 0.8342, "step": 1467 }, { "epoch": 1.3671947809878844, "loss_cot": 0.4596579372882843, "loss_nocot": 0.3786373436450958, "step": 1467 }, { "epoch": 1.3681267474370924, "grad_norm": 0.6711692976382374, "learning_rate": 1.2088367276492925e-05, "loss": 0.8256, "step": 1468 }, { "epoch": 1.3681267474370924, "loss_cot": 0.4698956608772278, "loss_nocot": 0.3898327648639679, "step": 1468 }, { "epoch": 1.3690587138863002, "grad_norm": 0.6105931450401485, "learning_rate": 1.2081463583016914e-05, "loss": 0.8704, "step": 1469 }, { "epoch": 1.3690587138863002, "loss_cot": 0.6107625961303711, "loss_nocot": 0.3992553949356079, "step": 1469 }, { "epoch": 1.369990680335508, "grad_norm": 0.6505611329890929, "learning_rate": 1.2074559889540905e-05, "loss": 0.8968, "step": 1470 }, { "epoch": 1.369990680335508, "loss_cot": 0.49852317571640015, "loss_nocot": 0.3610430359840393, "step": 1470 }, { "epoch": 1.3709226467847158, "grad_norm": 0.6680643657370325, "learning_rate": 1.2067656196064896e-05, "loss": 0.8427, "step": 1471 }, { "epoch": 1.3709226467847158, "loss_cot": 0.5100961327552795, "loss_nocot": 0.3301158547401428, "step": 1471 }, { "epoch": 1.3718546132339235, "grad_norm": 0.6873512246796154, "learning_rate": 1.2060752502588887e-05, "loss": 0.9298, "step": 1472 }, { "epoch": 1.3718546132339235, "loss_cot": 0.5317500233650208, "loss_nocot": 0.2700091600418091, "step": 1472 }, { "epoch": 1.3727865796831313, "grad_norm": 0.6657856641937423, "learning_rate": 1.2053848809112876e-05, "loss": 0.8838, "step": 1473 }, { "epoch": 1.3727865796831313, "loss_cot": 0.530191957950592, "loss_nocot": 0.3167298436164856, "step": 1473 }, { "epoch": 1.3737185461323391, "grad_norm": 0.6064400056785991, "learning_rate": 1.2046945115636868e-05, "loss": 0.8547, "step": 1474 }, { "epoch": 1.3737185461323391, "loss_cot": 0.4782804846763611, "loss_nocot": 0.35730981826782227, "step": 1474 }, { "epoch": 1.3746505125815471, "grad_norm": 0.6439504157604606, "learning_rate": 1.2040041422160857e-05, "loss": 0.8631, "step": 1475 }, { "epoch": 1.3746505125815471, "loss_cot": 0.49890589714050293, "loss_nocot": 0.3120107650756836, "step": 1475 }, { "epoch": 1.375582479030755, "grad_norm": 0.5723351943337982, "learning_rate": 1.2033137728684848e-05, "loss": 0.8061, "step": 1476 }, { "epoch": 1.375582479030755, "loss_cot": 0.47125640511512756, "loss_nocot": 0.3755347430706024, "step": 1476 }, { "epoch": 1.3765144454799627, "grad_norm": 0.623656741781749, "learning_rate": 1.2026234035208837e-05, "loss": 0.8248, "step": 1477 }, { "epoch": 1.3765144454799627, "loss_cot": 0.5313969254493713, "loss_nocot": 0.42869842052459717, "step": 1477 }, { "epoch": 1.3774464119291705, "grad_norm": 0.641747652774656, "learning_rate": 1.201933034173283e-05, "loss": 0.8726, "step": 1478 }, { "epoch": 1.3774464119291705, "loss_cot": 0.4715539216995239, "loss_nocot": 0.3445500433444977, "step": 1478 }, { "epoch": 1.3783783783783785, "grad_norm": 0.5847730924488274, "learning_rate": 1.2012426648256818e-05, "loss": 0.8317, "step": 1479 }, { "epoch": 1.3783783783783785, "loss_cot": 0.46669360995292664, "loss_nocot": 0.3086322844028473, "step": 1479 }, { "epoch": 1.3793103448275863, "grad_norm": 0.6565539572820217, "learning_rate": 1.2005522954780809e-05, "loss": 0.9082, "step": 1480 }, { "epoch": 1.3793103448275863, "loss_cot": 0.46795135736465454, "loss_nocot": 0.42907434701919556, "step": 1480 }, { "epoch": 1.380242311276794, "grad_norm": 0.6145618055165273, "learning_rate": 1.1998619261304798e-05, "loss": 0.8609, "step": 1481 }, { "epoch": 1.380242311276794, "loss_cot": 0.5035405158996582, "loss_nocot": 0.2968636453151703, "step": 1481 }, { "epoch": 1.3811742777260019, "grad_norm": 0.636250699564402, "learning_rate": 1.199171556782879e-05, "loss": 0.8255, "step": 1482 }, { "epoch": 1.3811742777260019, "loss_cot": 0.49614471197128296, "loss_nocot": 0.4551767110824585, "step": 1482 }, { "epoch": 1.3821062441752097, "grad_norm": 0.7358797849605772, "learning_rate": 1.198481187435278e-05, "loss": 0.936, "step": 1483 }, { "epoch": 1.3821062441752097, "loss_cot": 0.5217467546463013, "loss_nocot": 0.30035895109176636, "step": 1483 }, { "epoch": 1.3830382106244175, "grad_norm": 0.6400079752917116, "learning_rate": 1.1977908180876769e-05, "loss": 0.8818, "step": 1484 }, { "epoch": 1.3830382106244175, "loss_cot": 0.5070497989654541, "loss_nocot": 0.42240768671035767, "step": 1484 }, { "epoch": 1.3839701770736252, "grad_norm": 0.6441124100583793, "learning_rate": 1.1971004487400761e-05, "loss": 0.869, "step": 1485 }, { "epoch": 1.3839701770736252, "loss_cot": 0.5516897439956665, "loss_nocot": 0.2499793916940689, "step": 1485 }, { "epoch": 1.3849021435228333, "grad_norm": 0.6119765943464598, "learning_rate": 1.1964100793924752e-05, "loss": 0.8654, "step": 1486 }, { "epoch": 1.3849021435228333, "loss_cot": 0.5911667943000793, "loss_nocot": 0.42030829191207886, "step": 1486 }, { "epoch": 1.385834109972041, "grad_norm": 0.6764459117984043, "learning_rate": 1.195719710044874e-05, "loss": 0.8963, "step": 1487 }, { "epoch": 1.385834109972041, "loss_cot": 0.5138933658599854, "loss_nocot": 0.3691776394844055, "step": 1487 }, { "epoch": 1.3867660764212488, "grad_norm": 0.647083760599687, "learning_rate": 1.195029340697273e-05, "loss": 0.8777, "step": 1488 }, { "epoch": 1.3867660764212488, "loss_cot": 0.5229810476303101, "loss_nocot": 0.4744490385055542, "step": 1488 }, { "epoch": 1.3876980428704566, "grad_norm": 0.6110481841870147, "learning_rate": 1.1943389713496722e-05, "loss": 0.8807, "step": 1489 }, { "epoch": 1.3876980428704566, "loss_cot": 0.510286271572113, "loss_nocot": 0.3958909511566162, "step": 1489 }, { "epoch": 1.3886300093196646, "grad_norm": 0.6006053009956812, "learning_rate": 1.1936486020020713e-05, "loss": 0.8246, "step": 1490 }, { "epoch": 1.3886300093196646, "loss_cot": 0.5365551114082336, "loss_nocot": 0.31348422169685364, "step": 1490 }, { "epoch": 1.3895619757688724, "grad_norm": 0.6392477738200929, "learning_rate": 1.1929582326544702e-05, "loss": 0.8805, "step": 1491 }, { "epoch": 1.3895619757688724, "loss_cot": 0.5215238332748413, "loss_nocot": 0.31497445702552795, "step": 1491 }, { "epoch": 1.3904939422180802, "grad_norm": 0.6366338516994138, "learning_rate": 1.1922678633068691e-05, "loss": 0.8844, "step": 1492 }, { "epoch": 1.3904939422180802, "loss_cot": 0.49720850586891174, "loss_nocot": 0.43359294533729553, "step": 1492 }, { "epoch": 1.391425908667288, "grad_norm": 0.618587343539241, "learning_rate": 1.1915774939592684e-05, "loss": 0.8718, "step": 1493 }, { "epoch": 1.391425908667288, "loss_cot": 0.4907645583152771, "loss_nocot": 0.29015615582466125, "step": 1493 }, { "epoch": 1.3923578751164958, "grad_norm": 0.5832825117021649, "learning_rate": 1.1908871246116673e-05, "loss": 0.8224, "step": 1494 }, { "epoch": 1.3923578751164958, "loss_cot": 0.5454221963882446, "loss_nocot": 0.35123205184936523, "step": 1494 }, { "epoch": 1.3932898415657036, "grad_norm": 0.613879455368707, "learning_rate": 1.1901967552640663e-05, "loss": 0.8955, "step": 1495 }, { "epoch": 1.3932898415657036, "loss_cot": 0.5345032215118408, "loss_nocot": 0.473387211561203, "step": 1495 }, { "epoch": 1.3942218080149114, "grad_norm": 0.7061344607729664, "learning_rate": 1.1895063859164656e-05, "loss": 0.9222, "step": 1496 }, { "epoch": 1.3942218080149114, "loss_cot": 0.5336951017379761, "loss_nocot": 0.3432501256465912, "step": 1496 }, { "epoch": 1.3951537744641194, "grad_norm": 0.6421536022711143, "learning_rate": 1.1888160165688645e-05, "loss": 0.9195, "step": 1497 }, { "epoch": 1.3951537744641194, "loss_cot": 0.5066395998001099, "loss_nocot": 0.2352636605501175, "step": 1497 }, { "epoch": 1.3960857409133272, "grad_norm": 0.5854628087393068, "learning_rate": 1.1881256472212634e-05, "loss": 0.8282, "step": 1498 }, { "epoch": 1.3960857409133272, "loss_cot": 0.5306401252746582, "loss_nocot": 0.3115527331829071, "step": 1498 }, { "epoch": 1.397017707362535, "grad_norm": 0.6963762089772685, "learning_rate": 1.1874352778736625e-05, "loss": 0.8931, "step": 1499 }, { "epoch": 1.397017707362535, "loss_cot": 0.5038857460021973, "loss_nocot": 0.32235288619995117, "step": 1499 }, { "epoch": 1.3979496738117427, "grad_norm": 0.5702924607205678, "learning_rate": 1.1867449085260617e-05, "loss": 0.8689, "step": 1500 }, { "epoch": 1.3979496738117427, "loss_cot": 0.5239932537078857, "loss_nocot": 0.22674202919006348, "step": 1500 }, { "epoch": 1.3988816402609507, "grad_norm": 0.6023031071395974, "learning_rate": 1.1860545391784606e-05, "loss": 0.8686, "step": 1501 }, { "epoch": 1.3988816402609507, "loss_cot": 0.4760107398033142, "loss_nocot": 0.3736807107925415, "step": 1501 }, { "epoch": 1.3998136067101585, "grad_norm": 0.6153836775369967, "learning_rate": 1.1853641698308595e-05, "loss": 0.8407, "step": 1502 }, { "epoch": 1.3998136067101585, "loss_cot": 0.4896371364593506, "loss_nocot": 0.4302816390991211, "step": 1502 }, { "epoch": 1.4007455731593663, "grad_norm": 0.613370687213396, "learning_rate": 1.1846738004832586e-05, "loss": 0.8771, "step": 1503 }, { "epoch": 1.4007455731593663, "loss_cot": 0.5037728548049927, "loss_nocot": 0.324374794960022, "step": 1503 }, { "epoch": 1.401677539608574, "grad_norm": 0.6772214010419745, "learning_rate": 1.1839834311356576e-05, "loss": 0.8916, "step": 1504 }, { "epoch": 1.401677539608574, "loss_cot": 0.5242597460746765, "loss_nocot": 0.3707270622253418, "step": 1504 }, { "epoch": 1.402609506057782, "grad_norm": 0.6329748022385496, "learning_rate": 1.1832930617880567e-05, "loss": 0.901, "step": 1505 }, { "epoch": 1.402609506057782, "loss_cot": 0.49536484479904175, "loss_nocot": 0.3113134503364563, "step": 1505 }, { "epoch": 1.4035414725069897, "grad_norm": 0.6339764769747904, "learning_rate": 1.1826026924404556e-05, "loss": 0.8429, "step": 1506 }, { "epoch": 1.4035414725069897, "loss_cot": 0.4643794298171997, "loss_nocot": 0.41373613476753235, "step": 1506 }, { "epoch": 1.4044734389561975, "grad_norm": 0.6509390773350885, "learning_rate": 1.1819123230928549e-05, "loss": 0.9032, "step": 1507 }, { "epoch": 1.4044734389561975, "loss_cot": 0.5027503371238708, "loss_nocot": 0.49956727027893066, "step": 1507 }, { "epoch": 1.4054054054054055, "grad_norm": 0.6384263554066052, "learning_rate": 1.1812219537452538e-05, "loss": 0.8885, "step": 1508 }, { "epoch": 1.4054054054054055, "loss_cot": 0.4692980647087097, "loss_nocot": 0.3307882845401764, "step": 1508 }, { "epoch": 1.4063373718546133, "grad_norm": 0.7063547986272009, "learning_rate": 1.1805315843976528e-05, "loss": 0.8668, "step": 1509 }, { "epoch": 1.4063373718546133, "loss_cot": 0.5299897193908691, "loss_nocot": 0.34612876176834106, "step": 1509 }, { "epoch": 1.407269338303821, "grad_norm": 0.615402508893725, "learning_rate": 1.1798412150500517e-05, "loss": 0.8259, "step": 1510 }, { "epoch": 1.407269338303821, "loss_cot": 0.5122681856155396, "loss_nocot": 0.2986671030521393, "step": 1510 }, { "epoch": 1.4082013047530288, "grad_norm": 0.6214915813609577, "learning_rate": 1.179150845702451e-05, "loss": 0.8429, "step": 1511 }, { "epoch": 1.4082013047530288, "loss_cot": 0.47248733043670654, "loss_nocot": 0.3290853500366211, "step": 1511 }, { "epoch": 1.4091332712022366, "grad_norm": 0.6245079219944719, "learning_rate": 1.1784604763548499e-05, "loss": 0.8143, "step": 1512 }, { "epoch": 1.4091332712022366, "loss_cot": 0.5187337398529053, "loss_nocot": 0.3529135584831238, "step": 1512 }, { "epoch": 1.4100652376514446, "grad_norm": 0.6394627224644663, "learning_rate": 1.177770107007249e-05, "loss": 0.8716, "step": 1513 }, { "epoch": 1.4100652376514446, "loss_cot": 0.47464892268180847, "loss_nocot": 0.29104912281036377, "step": 1513 }, { "epoch": 1.4109972041006524, "grad_norm": 0.6476794497959217, "learning_rate": 1.177079737659648e-05, "loss": 0.8662, "step": 1514 }, { "epoch": 1.4109972041006524, "loss_cot": 0.5302696228027344, "loss_nocot": 0.30752235651016235, "step": 1514 }, { "epoch": 1.4119291705498602, "grad_norm": 0.6345954682430546, "learning_rate": 1.1763893683120471e-05, "loss": 0.8934, "step": 1515 }, { "epoch": 1.4119291705498602, "loss_cot": 0.5291988849639893, "loss_nocot": 0.4620267152786255, "step": 1515 }, { "epoch": 1.412861136999068, "grad_norm": 0.6775077459477565, "learning_rate": 1.175698998964446e-05, "loss": 0.9158, "step": 1516 }, { "epoch": 1.412861136999068, "loss_cot": 0.5268668532371521, "loss_nocot": 0.3829999566078186, "step": 1516 }, { "epoch": 1.4137931034482758, "grad_norm": 0.6228644146963644, "learning_rate": 1.1750086296168451e-05, "loss": 0.8652, "step": 1517 }, { "epoch": 1.4137931034482758, "loss_cot": 0.5327116847038269, "loss_nocot": 0.3519865572452545, "step": 1517 }, { "epoch": 1.4147250698974836, "grad_norm": 0.650962317500377, "learning_rate": 1.1743182602692442e-05, "loss": 0.9013, "step": 1518 }, { "epoch": 1.4147250698974836, "loss_cot": 0.5237273573875427, "loss_nocot": 0.5629256963729858, "step": 1518 }, { "epoch": 1.4156570363466916, "grad_norm": 0.6422674113392047, "learning_rate": 1.1736278909216432e-05, "loss": 0.9153, "step": 1519 }, { "epoch": 1.4156570363466916, "loss_cot": 0.48976340889930725, "loss_nocot": 0.3805447816848755, "step": 1519 }, { "epoch": 1.4165890027958994, "grad_norm": 0.6161273979081567, "learning_rate": 1.1729375215740421e-05, "loss": 0.8482, "step": 1520 }, { "epoch": 1.4165890027958994, "loss_cot": 0.5435742139816284, "loss_nocot": 0.37025538086891174, "step": 1520 }, { "epoch": 1.4175209692451072, "grad_norm": 0.6452732110761544, "learning_rate": 1.1722471522264412e-05, "loss": 0.8821, "step": 1521 }, { "epoch": 1.4175209692451072, "loss_cot": 0.49140480160713196, "loss_nocot": 0.3282199203968048, "step": 1521 }, { "epoch": 1.418452935694315, "grad_norm": 0.6616415034978796, "learning_rate": 1.1715567828788403e-05, "loss": 0.8747, "step": 1522 }, { "epoch": 1.418452935694315, "loss_cot": 0.5113261938095093, "loss_nocot": 0.2989347577095032, "step": 1522 }, { "epoch": 1.4193849021435228, "grad_norm": 0.639477511247981, "learning_rate": 1.1708664135312394e-05, "loss": 0.8289, "step": 1523 }, { "epoch": 1.4193849021435228, "loss_cot": 0.5320531129837036, "loss_nocot": 0.3064776659011841, "step": 1523 }, { "epoch": 1.4203168685927308, "grad_norm": 0.5933586831330302, "learning_rate": 1.1701760441836383e-05, "loss": 0.8227, "step": 1524 }, { "epoch": 1.4203168685927308, "loss_cot": 0.552302360534668, "loss_nocot": 0.3382855951786041, "step": 1524 }, { "epoch": 1.4212488350419386, "grad_norm": 0.5909843082409013, "learning_rate": 1.1694856748360375e-05, "loss": 0.8608, "step": 1525 }, { "epoch": 1.4212488350419386, "loss_cot": 0.5308902859687805, "loss_nocot": 0.3959514796733856, "step": 1525 }, { "epoch": 1.4221808014911463, "grad_norm": 0.64653945631616, "learning_rate": 1.1687953054884364e-05, "loss": 0.9099, "step": 1526 }, { "epoch": 1.4221808014911463, "loss_cot": 0.5072231292724609, "loss_nocot": 0.3268137574195862, "step": 1526 }, { "epoch": 1.4231127679403541, "grad_norm": 0.6015727845053412, "learning_rate": 1.1681049361408355e-05, "loss": 0.8296, "step": 1527 }, { "epoch": 1.4231127679403541, "loss_cot": 0.5482809543609619, "loss_nocot": 0.28617405891418457, "step": 1527 }, { "epoch": 1.424044734389562, "grad_norm": 0.6057241618096134, "learning_rate": 1.1674145667932344e-05, "loss": 0.8268, "step": 1528 }, { "epoch": 1.424044734389562, "loss_cot": 0.5749603509902954, "loss_nocot": 0.23980526626110077, "step": 1528 }, { "epoch": 1.4249767008387697, "grad_norm": 0.5445665105135501, "learning_rate": 1.1667241974456336e-05, "loss": 0.7868, "step": 1529 }, { "epoch": 1.4249767008387697, "loss_cot": 0.5037042498588562, "loss_nocot": 0.4795365035533905, "step": 1529 }, { "epoch": 1.4259086672879777, "grad_norm": 0.749673700318784, "learning_rate": 1.1660338280980325e-05, "loss": 0.9, "step": 1530 }, { "epoch": 1.4259086672879777, "loss_cot": 0.4699985086917877, "loss_nocot": 0.3308916687965393, "step": 1530 }, { "epoch": 1.4268406337371855, "grad_norm": 0.6582550776316141, "learning_rate": 1.1653434587504316e-05, "loss": 0.8557, "step": 1531 }, { "epoch": 1.4268406337371855, "loss_cot": 0.4856034517288208, "loss_nocot": 0.37973088026046753, "step": 1531 }, { "epoch": 1.4277726001863933, "grad_norm": 0.6358588284141181, "learning_rate": 1.1646530894028305e-05, "loss": 0.8606, "step": 1532 }, { "epoch": 1.4277726001863933, "loss_cot": 0.5544739961624146, "loss_nocot": 0.26438167691230774, "step": 1532 }, { "epoch": 1.428704566635601, "grad_norm": 0.5857446769873668, "learning_rate": 1.1639627200552298e-05, "loss": 0.8543, "step": 1533 }, { "epoch": 1.428704566635601, "loss_cot": 0.4695602059364319, "loss_nocot": 0.4027126133441925, "step": 1533 }, { "epoch": 1.4296365330848089, "grad_norm": 0.6529405863825872, "learning_rate": 1.1632723507076287e-05, "loss": 0.8488, "step": 1534 }, { "epoch": 1.4296365330848089, "loss_cot": 0.5213031768798828, "loss_nocot": 0.30522656440734863, "step": 1534 }, { "epoch": 1.4305684995340169, "grad_norm": 0.6367934000447537, "learning_rate": 1.1625819813600276e-05, "loss": 0.8967, "step": 1535 }, { "epoch": 1.4305684995340169, "loss_cot": 0.5134692788124084, "loss_nocot": 0.30652838945388794, "step": 1535 }, { "epoch": 1.4315004659832247, "grad_norm": 0.6138530064993836, "learning_rate": 1.1618916120124268e-05, "loss": 0.8328, "step": 1536 }, { "epoch": 1.4315004659832247, "loss_cot": 0.5463593006134033, "loss_nocot": 0.36138105392456055, "step": 1536 }, { "epoch": 1.4324324324324325, "grad_norm": 0.6494402868742027, "learning_rate": 1.1612012426648259e-05, "loss": 0.8564, "step": 1537 }, { "epoch": 1.4324324324324325, "loss_cot": 0.5189717411994934, "loss_nocot": 0.34857210516929626, "step": 1537 }, { "epoch": 1.4333643988816402, "grad_norm": 0.640606407869009, "learning_rate": 1.1605108733172248e-05, "loss": 0.9147, "step": 1538 }, { "epoch": 1.4333643988816402, "loss_cot": 0.48373812437057495, "loss_nocot": 0.42762309312820435, "step": 1538 }, { "epoch": 1.434296365330848, "grad_norm": 0.6139413212695608, "learning_rate": 1.1598205039696237e-05, "loss": 0.815, "step": 1539 }, { "epoch": 1.434296365330848, "loss_cot": 0.4358024597167969, "loss_nocot": 0.3340662717819214, "step": 1539 }, { "epoch": 1.4352283317800558, "grad_norm": 0.6129315077140491, "learning_rate": 1.159130134622023e-05, "loss": 0.7968, "step": 1540 }, { "epoch": 1.4352283317800558, "loss_cot": 0.4737004339694977, "loss_nocot": 0.32832032442092896, "step": 1540 }, { "epoch": 1.4361602982292636, "grad_norm": 0.6640677678496733, "learning_rate": 1.158439765274422e-05, "loss": 0.8896, "step": 1541 }, { "epoch": 1.4361602982292636, "loss_cot": 0.5745671391487122, "loss_nocot": 0.36392804980278015, "step": 1541 }, { "epoch": 1.4370922646784716, "grad_norm": 0.6356137605392059, "learning_rate": 1.1577493959268209e-05, "loss": 0.8972, "step": 1542 }, { "epoch": 1.4370922646784716, "loss_cot": 0.537638783454895, "loss_nocot": 0.37733036279678345, "step": 1542 }, { "epoch": 1.4380242311276794, "grad_norm": 0.6500345070026893, "learning_rate": 1.1570590265792198e-05, "loss": 0.8705, "step": 1543 }, { "epoch": 1.4380242311276794, "loss_cot": 0.4685845375061035, "loss_nocot": 0.2975708246231079, "step": 1543 }, { "epoch": 1.4389561975768872, "grad_norm": 0.6319353350731335, "learning_rate": 1.156368657231619e-05, "loss": 0.8526, "step": 1544 }, { "epoch": 1.4389561975768872, "loss_cot": 0.5250259637832642, "loss_nocot": 0.27416613698005676, "step": 1544 }, { "epoch": 1.439888164026095, "grad_norm": 0.6253066257181309, "learning_rate": 1.155678287884018e-05, "loss": 0.8282, "step": 1545 }, { "epoch": 1.439888164026095, "loss_cot": 0.48909202218055725, "loss_nocot": 0.34118759632110596, "step": 1545 }, { "epoch": 1.440820130475303, "grad_norm": 0.6190419526237201, "learning_rate": 1.154987918536417e-05, "loss": 0.8462, "step": 1546 }, { "epoch": 1.440820130475303, "loss_cot": 0.49252668023109436, "loss_nocot": 0.28901243209838867, "step": 1546 }, { "epoch": 1.4417520969245108, "grad_norm": 0.6121403025756278, "learning_rate": 1.1542975491888163e-05, "loss": 0.8397, "step": 1547 }, { "epoch": 1.4417520969245108, "loss_cot": 0.5010069608688354, "loss_nocot": 0.37951868772506714, "step": 1547 }, { "epoch": 1.4426840633737186, "grad_norm": 0.6035587020423214, "learning_rate": 1.1536071798412152e-05, "loss": 0.8264, "step": 1548 }, { "epoch": 1.4426840633737186, "loss_cot": 0.5288543701171875, "loss_nocot": 0.34637200832366943, "step": 1548 }, { "epoch": 1.4436160298229264, "grad_norm": 0.604094761528445, "learning_rate": 1.152916810493614e-05, "loss": 0.8287, "step": 1549 }, { "epoch": 1.4436160298229264, "loss_cot": 0.51288241147995, "loss_nocot": 0.32786327600479126, "step": 1549 }, { "epoch": 1.4445479962721341, "grad_norm": 0.5946823283174355, "learning_rate": 1.1522264411460132e-05, "loss": 0.8201, "step": 1550 }, { "epoch": 1.4445479962721341, "loss_cot": 0.5192646384239197, "loss_nocot": 0.35757654905319214, "step": 1550 }, { "epoch": 1.445479962721342, "grad_norm": 0.67216478309264, "learning_rate": 1.1515360717984124e-05, "loss": 0.8649, "step": 1551 }, { "epoch": 1.445479962721342, "loss_cot": 0.5418472290039062, "loss_nocot": 0.33372750878334045, "step": 1551 }, { "epoch": 1.4464119291705497, "grad_norm": 0.5699705689256722, "learning_rate": 1.1508457024508113e-05, "loss": 0.8227, "step": 1552 }, { "epoch": 1.4464119291705497, "loss_cot": 0.45316579937934875, "loss_nocot": 0.24498015642166138, "step": 1552 }, { "epoch": 1.4473438956197577, "grad_norm": 0.5870978081082255, "learning_rate": 1.1501553331032102e-05, "loss": 0.7865, "step": 1553 }, { "epoch": 1.4473438956197577, "loss_cot": 0.48115870356559753, "loss_nocot": 0.27695581316947937, "step": 1553 }, { "epoch": 1.4482758620689655, "grad_norm": 0.6351100019236402, "learning_rate": 1.1494649637556094e-05, "loss": 0.8415, "step": 1554 }, { "epoch": 1.4482758620689655, "loss_cot": 0.47820669412612915, "loss_nocot": 0.256274938583374, "step": 1554 }, { "epoch": 1.4492078285181733, "grad_norm": 0.6040486907612178, "learning_rate": 1.1487745944080084e-05, "loss": 0.8536, "step": 1555 }, { "epoch": 1.4492078285181733, "loss_cot": 0.472858726978302, "loss_nocot": 0.40105074644088745, "step": 1555 }, { "epoch": 1.450139794967381, "grad_norm": 0.6222165835853718, "learning_rate": 1.1480842250604074e-05, "loss": 0.8825, "step": 1556 }, { "epoch": 1.450139794967381, "loss_cot": 0.4810073971748352, "loss_nocot": 0.44158369302749634, "step": 1556 }, { "epoch": 1.4510717614165891, "grad_norm": 0.6281634183198109, "learning_rate": 1.1473938557128063e-05, "loss": 0.8591, "step": 1557 }, { "epoch": 1.4510717614165891, "loss_cot": 0.48148033022880554, "loss_nocot": 0.32773762941360474, "step": 1557 }, { "epoch": 1.452003727865797, "grad_norm": 0.6040636957325164, "learning_rate": 1.1467034863652056e-05, "loss": 0.7816, "step": 1558 }, { "epoch": 1.452003727865797, "loss_cot": 0.48784273862838745, "loss_nocot": 0.3015124201774597, "step": 1558 }, { "epoch": 1.4529356943150047, "grad_norm": 0.6097416416550682, "learning_rate": 1.1460131170176045e-05, "loss": 0.8283, "step": 1559 }, { "epoch": 1.4529356943150047, "loss_cot": 0.4906691312789917, "loss_nocot": 0.39711228013038635, "step": 1559 }, { "epoch": 1.4538676607642125, "grad_norm": 0.6679936910469766, "learning_rate": 1.1453227476700035e-05, "loss": 0.89, "step": 1560 }, { "epoch": 1.4538676607642125, "loss_cot": 0.4781726002693176, "loss_nocot": 0.37881898880004883, "step": 1560 }, { "epoch": 1.4547996272134203, "grad_norm": 0.6228734334572924, "learning_rate": 1.1446323783224025e-05, "loss": 0.8297, "step": 1561 }, { "epoch": 1.4547996272134203, "loss_cot": 0.5196706056594849, "loss_nocot": 0.34903621673583984, "step": 1561 }, { "epoch": 1.455731593662628, "grad_norm": 0.6295750435755697, "learning_rate": 1.1439420089748017e-05, "loss": 0.8833, "step": 1562 }, { "epoch": 1.455731593662628, "loss_cot": 0.46764618158340454, "loss_nocot": 0.31307151913642883, "step": 1562 }, { "epoch": 1.4566635601118358, "grad_norm": 0.6655642261524773, "learning_rate": 1.1432516396272006e-05, "loss": 0.8776, "step": 1563 }, { "epoch": 1.4566635601118358, "loss_cot": 0.5323315262794495, "loss_nocot": 0.32425975799560547, "step": 1563 }, { "epoch": 1.4575955265610439, "grad_norm": 0.6231619710659712, "learning_rate": 1.1425612702795997e-05, "loss": 0.8524, "step": 1564 }, { "epoch": 1.4575955265610439, "loss_cot": 0.531891405582428, "loss_nocot": 0.36108914017677307, "step": 1564 }, { "epoch": 1.4585274930102516, "grad_norm": 0.7191214494040117, "learning_rate": 1.1418709009319987e-05, "loss": 0.9007, "step": 1565 }, { "epoch": 1.4585274930102516, "loss_cot": 0.5648119449615479, "loss_nocot": 0.24882115423679352, "step": 1565 }, { "epoch": 1.4594594594594594, "grad_norm": 0.6479364947598497, "learning_rate": 1.1411805315843978e-05, "loss": 0.8844, "step": 1566 }, { "epoch": 1.4594594594594594, "loss_cot": 0.4793454110622406, "loss_nocot": 0.32892102003097534, "step": 1566 }, { "epoch": 1.4603914259086672, "grad_norm": 0.5913086586357392, "learning_rate": 1.1404901622367967e-05, "loss": 0.7933, "step": 1567 }, { "epoch": 1.4603914259086672, "loss_cot": 0.47585999965667725, "loss_nocot": 0.38420772552490234, "step": 1567 }, { "epoch": 1.4613233923578752, "grad_norm": 0.6829937425616319, "learning_rate": 1.1397997928891958e-05, "loss": 0.8988, "step": 1568 }, { "epoch": 1.4613233923578752, "loss_cot": 0.5961705446243286, "loss_nocot": 0.37111696600914, "step": 1568 }, { "epoch": 1.462255358807083, "grad_norm": 0.6202669223456468, "learning_rate": 1.1391094235415949e-05, "loss": 0.8651, "step": 1569 }, { "epoch": 1.462255358807083, "loss_cot": 0.47221216559410095, "loss_nocot": 0.3152446448802948, "step": 1569 }, { "epoch": 1.4631873252562908, "grad_norm": 0.6051966759500046, "learning_rate": 1.138419054193994e-05, "loss": 0.8204, "step": 1570 }, { "epoch": 1.4631873252562908, "loss_cot": 0.4899386465549469, "loss_nocot": 0.3118191957473755, "step": 1570 }, { "epoch": 1.4641192917054986, "grad_norm": 0.6479719599851532, "learning_rate": 1.1377286848463928e-05, "loss": 0.8965, "step": 1571 }, { "epoch": 1.4641192917054986, "loss_cot": 0.5651214122772217, "loss_nocot": 0.32971739768981934, "step": 1571 }, { "epoch": 1.4650512581547064, "grad_norm": 0.6175807276476407, "learning_rate": 1.137038315498792e-05, "loss": 0.8677, "step": 1572 }, { "epoch": 1.4650512581547064, "loss_cot": 0.49950480461120605, "loss_nocot": 0.4779810309410095, "step": 1572 }, { "epoch": 1.4659832246039142, "grad_norm": 0.6702715607383971, "learning_rate": 1.136347946151191e-05, "loss": 0.8723, "step": 1573 }, { "epoch": 1.4659832246039142, "loss_cot": 0.5386301279067993, "loss_nocot": 0.36013084650039673, "step": 1573 }, { "epoch": 1.466915191053122, "grad_norm": 0.5945234610945968, "learning_rate": 1.13565757680359e-05, "loss": 0.9018, "step": 1574 }, { "epoch": 1.466915191053122, "loss_cot": 0.4714871942996979, "loss_nocot": 0.32447606325149536, "step": 1574 }, { "epoch": 1.46784715750233, "grad_norm": 0.6271662317024226, "learning_rate": 1.134967207455989e-05, "loss": 0.9008, "step": 1575 }, { "epoch": 1.46784715750233, "loss_cot": 0.449715256690979, "loss_nocot": 0.3003700375556946, "step": 1575 }, { "epoch": 1.4687791239515378, "grad_norm": 0.6583721722742719, "learning_rate": 1.1342768381083882e-05, "loss": 0.8681, "step": 1576 }, { "epoch": 1.4687791239515378, "loss_cot": 0.47969114780426025, "loss_nocot": 0.35764777660369873, "step": 1576 }, { "epoch": 1.4697110904007455, "grad_norm": 0.6305314453214809, "learning_rate": 1.1335864687607871e-05, "loss": 0.8507, "step": 1577 }, { "epoch": 1.4697110904007455, "loss_cot": 0.5175093412399292, "loss_nocot": 0.35602498054504395, "step": 1577 }, { "epoch": 1.4706430568499533, "grad_norm": 0.5570579326571204, "learning_rate": 1.1328960994131862e-05, "loss": 0.8206, "step": 1578 }, { "epoch": 1.4706430568499533, "loss_cot": 0.46447545289993286, "loss_nocot": 0.2891077399253845, "step": 1578 }, { "epoch": 1.4715750232991613, "grad_norm": 0.6040348015921501, "learning_rate": 1.1322057300655851e-05, "loss": 0.8641, "step": 1579 }, { "epoch": 1.4715750232991613, "loss_cot": 0.5224359035491943, "loss_nocot": 0.42374297976493835, "step": 1579 }, { "epoch": 1.4725069897483691, "grad_norm": 0.6195723095470131, "learning_rate": 1.1315153607179843e-05, "loss": 0.8716, "step": 1580 }, { "epoch": 1.4725069897483691, "loss_cot": 0.519640326499939, "loss_nocot": 0.31368350982666016, "step": 1580 }, { "epoch": 1.473438956197577, "grad_norm": 0.6136970933357752, "learning_rate": 1.1308249913703832e-05, "loss": 0.8836, "step": 1581 }, { "epoch": 1.473438956197577, "loss_cot": 0.5112667083740234, "loss_nocot": 0.271115779876709, "step": 1581 }, { "epoch": 1.4743709226467847, "grad_norm": 0.6176866035663048, "learning_rate": 1.1301346220227823e-05, "loss": 0.8194, "step": 1582 }, { "epoch": 1.4743709226467847, "loss_cot": 0.515652060508728, "loss_nocot": 0.3007601499557495, "step": 1582 }, { "epoch": 1.4753028890959925, "grad_norm": 0.6444241549643348, "learning_rate": 1.1294442526751812e-05, "loss": 0.8952, "step": 1583 }, { "epoch": 1.4753028890959925, "loss_cot": 0.527599573135376, "loss_nocot": 0.38854438066482544, "step": 1583 }, { "epoch": 1.4762348555452003, "grad_norm": 0.6202501388789269, "learning_rate": 1.1287538833275805e-05, "loss": 0.8842, "step": 1584 }, { "epoch": 1.4762348555452003, "loss_cot": 0.5571869611740112, "loss_nocot": 0.2601269483566284, "step": 1584 }, { "epoch": 1.477166821994408, "grad_norm": 0.6010168342022237, "learning_rate": 1.1280635139799794e-05, "loss": 0.8588, "step": 1585 }, { "epoch": 1.477166821994408, "loss_cot": 0.634764552116394, "loss_nocot": 0.44120752811431885, "step": 1585 }, { "epoch": 1.478098788443616, "grad_norm": 0.7026267689280274, "learning_rate": 1.1273731446323783e-05, "loss": 0.9333, "step": 1586 }, { "epoch": 1.478098788443616, "loss_cot": 0.524000883102417, "loss_nocot": 0.3288646936416626, "step": 1586 }, { "epoch": 1.4790307548928239, "grad_norm": 0.627711484764803, "learning_rate": 1.1266827752847775e-05, "loss": 0.8582, "step": 1587 }, { "epoch": 1.4790307548928239, "loss_cot": 0.5208145380020142, "loss_nocot": 0.3908464312553406, "step": 1587 }, { "epoch": 1.4799627213420317, "grad_norm": 0.7443710277942256, "learning_rate": 1.1259924059371766e-05, "loss": 0.9211, "step": 1588 }, { "epoch": 1.4799627213420317, "loss_cot": 0.624682605266571, "loss_nocot": 0.35104548931121826, "step": 1588 }, { "epoch": 1.4808946877912395, "grad_norm": 0.6100400992706738, "learning_rate": 1.1253020365895755e-05, "loss": 0.8645, "step": 1589 }, { "epoch": 1.4808946877912395, "loss_cot": 0.4941784739494324, "loss_nocot": 0.43444737792015076, "step": 1589 }, { "epoch": 1.4818266542404475, "grad_norm": 0.6624199634306823, "learning_rate": 1.1246116672419744e-05, "loss": 0.8715, "step": 1590 }, { "epoch": 1.4818266542404475, "loss_cot": 0.49294477701187134, "loss_nocot": 0.25108766555786133, "step": 1590 }, { "epoch": 1.4827586206896552, "grad_norm": 0.588207408813585, "learning_rate": 1.1239212978943736e-05, "loss": 0.8303, "step": 1591 }, { "epoch": 1.4827586206896552, "loss_cot": 0.43869930505752563, "loss_nocot": 0.4612903296947479, "step": 1591 }, { "epoch": 1.483690587138863, "grad_norm": 0.6384400692045267, "learning_rate": 1.1232309285467727e-05, "loss": 0.8443, "step": 1592 }, { "epoch": 1.483690587138863, "loss_cot": 0.47008222341537476, "loss_nocot": 0.26668399572372437, "step": 1592 }, { "epoch": 1.4846225535880708, "grad_norm": 0.6342079443124251, "learning_rate": 1.1225405591991716e-05, "loss": 0.8818, "step": 1593 }, { "epoch": 1.4846225535880708, "loss_cot": 0.4607715606689453, "loss_nocot": 0.4992640018463135, "step": 1593 }, { "epoch": 1.4855545200372786, "grad_norm": 0.5902391283694651, "learning_rate": 1.1218501898515709e-05, "loss": 0.831, "step": 1594 }, { "epoch": 1.4855545200372786, "loss_cot": 0.5114419460296631, "loss_nocot": 0.32402727007865906, "step": 1594 }, { "epoch": 1.4864864864864864, "grad_norm": 0.6396120297581417, "learning_rate": 1.1211598205039698e-05, "loss": 0.8504, "step": 1595 }, { "epoch": 1.4864864864864864, "loss_cot": 0.5327178239822388, "loss_nocot": 0.38146498799324036, "step": 1595 }, { "epoch": 1.4874184529356942, "grad_norm": 0.6407542165007005, "learning_rate": 1.1204694511563687e-05, "loss": 0.8652, "step": 1596 }, { "epoch": 1.4874184529356942, "loss_cot": 0.5394278764724731, "loss_nocot": 0.29179510474205017, "step": 1596 }, { "epoch": 1.4883504193849022, "grad_norm": 0.6454420641073798, "learning_rate": 1.1197790818087677e-05, "loss": 0.8893, "step": 1597 }, { "epoch": 1.4883504193849022, "loss_cot": 0.5251322388648987, "loss_nocot": 0.28059160709381104, "step": 1597 }, { "epoch": 1.48928238583411, "grad_norm": 0.5618587777714067, "learning_rate": 1.119088712461167e-05, "loss": 0.7978, "step": 1598 }, { "epoch": 1.48928238583411, "loss_cot": 0.4607221782207489, "loss_nocot": 0.43680626153945923, "step": 1598 }, { "epoch": 1.4902143522833178, "grad_norm": 0.641154477837722, "learning_rate": 1.1183983431135659e-05, "loss": 0.919, "step": 1599 }, { "epoch": 1.4902143522833178, "loss_cot": 0.4935923218727112, "loss_nocot": 0.31106650829315186, "step": 1599 }, { "epoch": 1.4911463187325256, "grad_norm": 0.6332129232853406, "learning_rate": 1.1177079737659648e-05, "loss": 0.9136, "step": 1600 }, { "epoch": 1.4911463187325256, "loss_cot": 0.5564440488815308, "loss_nocot": 0.4080888032913208, "step": 1600 }, { "epoch": 1.4920782851817336, "grad_norm": 0.6157320084985232, "learning_rate": 1.1170176044183639e-05, "loss": 0.8851, "step": 1601 }, { "epoch": 1.4920782851817336, "loss_cot": 0.556456446647644, "loss_nocot": 0.4745035171508789, "step": 1601 }, { "epoch": 1.4930102516309414, "grad_norm": 0.6493057645657806, "learning_rate": 1.1163272350707631e-05, "loss": 0.8737, "step": 1602 }, { "epoch": 1.4930102516309414, "loss_cot": 0.5406335592269897, "loss_nocot": 0.39354225993156433, "step": 1602 }, { "epoch": 1.4939422180801492, "grad_norm": 0.6134959895388437, "learning_rate": 1.115636865723162e-05, "loss": 0.8671, "step": 1603 }, { "epoch": 1.4939422180801492, "loss_cot": 0.49545255303382874, "loss_nocot": 0.34221330285072327, "step": 1603 }, { "epoch": 1.494874184529357, "grad_norm": 0.638474530745421, "learning_rate": 1.1149464963755609e-05, "loss": 0.9007, "step": 1604 }, { "epoch": 1.494874184529357, "loss_cot": 0.5438896417617798, "loss_nocot": 0.32656049728393555, "step": 1604 }, { "epoch": 1.4958061509785647, "grad_norm": 0.5989442839910156, "learning_rate": 1.1142561270279602e-05, "loss": 0.8578, "step": 1605 }, { "epoch": 1.4958061509785647, "loss_cot": 0.45171013474464417, "loss_nocot": 0.379977285861969, "step": 1605 }, { "epoch": 1.4967381174277725, "grad_norm": 0.6438546939330171, "learning_rate": 1.113565757680359e-05, "loss": 0.8594, "step": 1606 }, { "epoch": 1.4967381174277725, "loss_cot": 0.5178684592247009, "loss_nocot": 0.3242974877357483, "step": 1606 }, { "epoch": 1.4976700838769803, "grad_norm": 0.69926674078632, "learning_rate": 1.1128753883327581e-05, "loss": 0.896, "step": 1607 }, { "epoch": 1.4976700838769803, "loss_cot": 0.5193254947662354, "loss_nocot": 0.35101598501205444, "step": 1607 }, { "epoch": 1.4986020503261883, "grad_norm": 0.5860697868928959, "learning_rate": 1.112185018985157e-05, "loss": 0.8761, "step": 1608 }, { "epoch": 1.4986020503261883, "loss_cot": 0.4997408390045166, "loss_nocot": 0.24109213054180145, "step": 1608 }, { "epoch": 1.499534016775396, "grad_norm": 0.6255931768223065, "learning_rate": 1.1114946496375563e-05, "loss": 0.8328, "step": 1609 }, { "epoch": 1.499534016775396, "loss_cot": 0.5078942775726318, "loss_nocot": 0.3671913146972656, "step": 1609 }, { "epoch": 1.500465983224604, "grad_norm": 0.6405201570000614, "learning_rate": 1.1108042802899552e-05, "loss": 0.8646, "step": 1610 }, { "epoch": 1.500465983224604, "loss_cot": 0.49012184143066406, "loss_nocot": 0.44317638874053955, "step": 1610 }, { "epoch": 1.501397949673812, "grad_norm": 0.6580594312136301, "learning_rate": 1.1101139109423543e-05, "loss": 0.8457, "step": 1611 }, { "epoch": 1.501397949673812, "loss_cot": 0.57097989320755, "loss_nocot": 0.36004638671875, "step": 1611 }, { "epoch": 1.5023299161230197, "grad_norm": 0.6282971798286645, "learning_rate": 1.1094235415947532e-05, "loss": 0.9155, "step": 1612 }, { "epoch": 1.5023299161230197, "loss_cot": 0.4927143156528473, "loss_nocot": 0.37088292837142944, "step": 1612 }, { "epoch": 1.5032618825722275, "grad_norm": 0.6749489361199833, "learning_rate": 1.1087331722471524e-05, "loss": 0.905, "step": 1613 }, { "epoch": 1.5032618825722275, "loss_cot": 0.5691345930099487, "loss_nocot": 0.399288147687912, "step": 1613 }, { "epoch": 1.5041938490214353, "grad_norm": 0.6467332317109808, "learning_rate": 1.1080428028995513e-05, "loss": 0.8635, "step": 1614 }, { "epoch": 1.5041938490214353, "loss_cot": 0.5127969980239868, "loss_nocot": 0.3504588007926941, "step": 1614 }, { "epoch": 1.505125815470643, "grad_norm": 0.6266432854303013, "learning_rate": 1.1073524335519504e-05, "loss": 0.8528, "step": 1615 }, { "epoch": 1.505125815470643, "loss_cot": 0.5171821117401123, "loss_nocot": 0.3080574870109558, "step": 1615 }, { "epoch": 1.5060577819198508, "grad_norm": 0.6033541209909314, "learning_rate": 1.1066620642043494e-05, "loss": 0.7916, "step": 1616 }, { "epoch": 1.5060577819198508, "loss_cot": 0.45575305819511414, "loss_nocot": 0.31009000539779663, "step": 1616 }, { "epoch": 1.5069897483690586, "grad_norm": 0.6166570196195856, "learning_rate": 1.1059716948567485e-05, "loss": 0.8248, "step": 1617 }, { "epoch": 1.5069897483690586, "loss_cot": 0.516715407371521, "loss_nocot": 0.3657051920890808, "step": 1617 }, { "epoch": 1.5079217148182664, "grad_norm": 0.6612804920219115, "learning_rate": 1.1052813255091474e-05, "loss": 0.8615, "step": 1618 }, { "epoch": 1.5079217148182664, "loss_cot": 0.5225139260292053, "loss_nocot": 0.32209640741348267, "step": 1618 }, { "epoch": 1.5088536812674742, "grad_norm": 0.6419607320629727, "learning_rate": 1.1045909561615465e-05, "loss": 0.885, "step": 1619 }, { "epoch": 1.5088536812674742, "loss_cot": 0.4934515357017517, "loss_nocot": 0.2572229206562042, "step": 1619 }, { "epoch": 1.5097856477166822, "grad_norm": 0.632477242979018, "learning_rate": 1.1039005868139456e-05, "loss": 0.8812, "step": 1620 }, { "epoch": 1.5097856477166822, "loss_cot": 0.48269063234329224, "loss_nocot": 0.21853500604629517, "step": 1620 }, { "epoch": 1.51071761416589, "grad_norm": 0.605112514925113, "learning_rate": 1.1032102174663446e-05, "loss": 0.7867, "step": 1621 }, { "epoch": 1.51071761416589, "loss_cot": 0.45401787757873535, "loss_nocot": 0.4042784869670868, "step": 1621 }, { "epoch": 1.511649580615098, "grad_norm": 0.7239882091317622, "learning_rate": 1.1025198481187435e-05, "loss": 0.8715, "step": 1622 }, { "epoch": 1.511649580615098, "loss_cot": 0.5382513999938965, "loss_nocot": 0.2917618453502655, "step": 1622 }, { "epoch": 1.5125815470643058, "grad_norm": 0.6142348310141311, "learning_rate": 1.1018294787711426e-05, "loss": 0.8392, "step": 1623 }, { "epoch": 1.5125815470643058, "loss_cot": 0.4745400547981262, "loss_nocot": 0.3947134017944336, "step": 1623 }, { "epoch": 1.5135135135135136, "grad_norm": 0.6304874906342973, "learning_rate": 1.1011391094235417e-05, "loss": 0.8538, "step": 1624 }, { "epoch": 1.5135135135135136, "loss_cot": 0.5049706697463989, "loss_nocot": 0.2724345326423645, "step": 1624 }, { "epoch": 1.5144454799627214, "grad_norm": 0.6043039766849806, "learning_rate": 1.1004487400759408e-05, "loss": 0.8043, "step": 1625 }, { "epoch": 1.5144454799627214, "loss_cot": 0.47071409225463867, "loss_nocot": 0.3566998541355133, "step": 1625 }, { "epoch": 1.5153774464119292, "grad_norm": 0.642458012262105, "learning_rate": 1.0997583707283397e-05, "loss": 0.876, "step": 1626 }, { "epoch": 1.5153774464119292, "loss_cot": 0.4883268177509308, "loss_nocot": 0.4168166220188141, "step": 1626 }, { "epoch": 1.516309412861137, "grad_norm": 0.6009640301689348, "learning_rate": 1.0990680013807389e-05, "loss": 0.8303, "step": 1627 }, { "epoch": 1.516309412861137, "loss_cot": 0.4449477791786194, "loss_nocot": 0.288529634475708, "step": 1627 }, { "epoch": 1.5172413793103448, "grad_norm": 0.5857435366879903, "learning_rate": 1.0983776320331378e-05, "loss": 0.7947, "step": 1628 }, { "epoch": 1.5172413793103448, "loss_cot": 0.5236310362815857, "loss_nocot": 0.3128177523612976, "step": 1628 }, { "epoch": 1.5181733457595525, "grad_norm": 0.5859438055699984, "learning_rate": 1.0976872626855369e-05, "loss": 0.8116, "step": 1629 }, { "epoch": 1.5181733457595525, "loss_cot": 0.5410380363464355, "loss_nocot": 0.4471524655818939, "step": 1629 }, { "epoch": 1.5191053122087603, "grad_norm": 0.6866547001808044, "learning_rate": 1.0969968933379358e-05, "loss": 0.876, "step": 1630 }, { "epoch": 1.5191053122087603, "loss_cot": 0.42586439847946167, "loss_nocot": 0.2757846415042877, "step": 1630 }, { "epoch": 1.5200372786579683, "grad_norm": 0.6577456819507279, "learning_rate": 1.096306523990335e-05, "loss": 0.8568, "step": 1631 }, { "epoch": 1.5200372786579683, "loss_cot": 0.457981675863266, "loss_nocot": 0.3701005280017853, "step": 1631 }, { "epoch": 1.5209692451071761, "grad_norm": 0.6333598655570986, "learning_rate": 1.095616154642734e-05, "loss": 0.8616, "step": 1632 }, { "epoch": 1.5209692451071761, "loss_cot": 0.6549879312515259, "loss_nocot": 0.37073564529418945, "step": 1632 }, { "epoch": 1.521901211556384, "grad_norm": 0.6541750484770072, "learning_rate": 1.094925785295133e-05, "loss": 0.9211, "step": 1633 }, { "epoch": 1.521901211556384, "loss_cot": 0.5059547424316406, "loss_nocot": 0.321628600358963, "step": 1633 }, { "epoch": 1.522833178005592, "grad_norm": 0.6092969511301464, "learning_rate": 1.094235415947532e-05, "loss": 0.8305, "step": 1634 }, { "epoch": 1.522833178005592, "loss_cot": 0.44460543990135193, "loss_nocot": 0.3181825876235962, "step": 1634 }, { "epoch": 1.5237651444547997, "grad_norm": 0.6256065526740532, "learning_rate": 1.0935450465999312e-05, "loss": 0.8268, "step": 1635 }, { "epoch": 1.5237651444547997, "loss_cot": 0.5316605567932129, "loss_nocot": 0.367942750453949, "step": 1635 }, { "epoch": 1.5246971109040075, "grad_norm": 0.6184791727953403, "learning_rate": 1.09285467725233e-05, "loss": 0.8577, "step": 1636 }, { "epoch": 1.5246971109040075, "loss_cot": 0.46984025835990906, "loss_nocot": 0.2880232036113739, "step": 1636 }, { "epoch": 1.5256290773532153, "grad_norm": 0.614233044329451, "learning_rate": 1.092164307904729e-05, "loss": 0.8347, "step": 1637 }, { "epoch": 1.5256290773532153, "loss_cot": 0.4558633863925934, "loss_nocot": 0.33297085762023926, "step": 1637 }, { "epoch": 1.526561043802423, "grad_norm": 0.709903475021396, "learning_rate": 1.0914739385571282e-05, "loss": 0.9293, "step": 1638 }, { "epoch": 1.526561043802423, "loss_cot": 0.5345921516418457, "loss_nocot": 0.4201798439025879, "step": 1638 }, { "epoch": 1.5274930102516309, "grad_norm": 0.6537958139182103, "learning_rate": 1.0907835692095273e-05, "loss": 0.865, "step": 1639 }, { "epoch": 1.5274930102516309, "loss_cot": 0.5054317116737366, "loss_nocot": 0.4000660181045532, "step": 1639 }, { "epoch": 1.5284249767008387, "grad_norm": 0.6410656777362974, "learning_rate": 1.0900931998619262e-05, "loss": 0.8422, "step": 1640 }, { "epoch": 1.5284249767008387, "loss_cot": 0.47803276777267456, "loss_nocot": 0.4162430465221405, "step": 1640 }, { "epoch": 1.5293569431500464, "grad_norm": 0.653364700013377, "learning_rate": 1.0894028305143251e-05, "loss": 0.9078, "step": 1641 }, { "epoch": 1.5293569431500464, "loss_cot": 0.45122992992401123, "loss_nocot": 0.5002394318580627, "step": 1641 }, { "epoch": 1.5302889095992545, "grad_norm": 0.6359298726960176, "learning_rate": 1.0887124611667243e-05, "loss": 0.8858, "step": 1642 }, { "epoch": 1.5302889095992545, "loss_cot": 0.6304783225059509, "loss_nocot": 0.3642483055591583, "step": 1642 }, { "epoch": 1.5312208760484622, "grad_norm": 0.7017478004073314, "learning_rate": 1.0880220918191234e-05, "loss": 0.9542, "step": 1643 }, { "epoch": 1.5312208760484622, "loss_cot": 0.5990517139434814, "loss_nocot": 0.34021425247192383, "step": 1643 }, { "epoch": 1.53215284249767, "grad_norm": 0.6878857540105031, "learning_rate": 1.0873317224715223e-05, "loss": 0.9394, "step": 1644 }, { "epoch": 1.53215284249767, "loss_cot": 0.5844513773918152, "loss_nocot": 0.3139662742614746, "step": 1644 }, { "epoch": 1.533084808946878, "grad_norm": 0.6193265520523893, "learning_rate": 1.0866413531239216e-05, "loss": 0.869, "step": 1645 }, { "epoch": 1.533084808946878, "loss_cot": 0.593805193901062, "loss_nocot": 0.30177754163742065, "step": 1645 }, { "epoch": 1.5340167753960858, "grad_norm": 0.6359549685572352, "learning_rate": 1.0859509837763205e-05, "loss": 0.8836, "step": 1646 }, { "epoch": 1.5340167753960858, "loss_cot": 0.4641945958137512, "loss_nocot": 0.3548814654350281, "step": 1646 }, { "epoch": 1.5349487418452936, "grad_norm": 0.6203522687491673, "learning_rate": 1.0852606144287194e-05, "loss": 0.85, "step": 1647 }, { "epoch": 1.5349487418452936, "loss_cot": 0.4967983067035675, "loss_nocot": 0.3704187870025635, "step": 1647 }, { "epoch": 1.5358807082945014, "grad_norm": 0.6309921761175173, "learning_rate": 1.0845702450811184e-05, "loss": 0.8691, "step": 1648 }, { "epoch": 1.5358807082945014, "loss_cot": 0.5050678253173828, "loss_nocot": 0.3963215947151184, "step": 1648 }, { "epoch": 1.5368126747437092, "grad_norm": 0.6376913966148382, "learning_rate": 1.0838798757335177e-05, "loss": 0.8555, "step": 1649 }, { "epoch": 1.5368126747437092, "loss_cot": 0.4814673960208893, "loss_nocot": 0.3480869233608246, "step": 1649 }, { "epoch": 1.537744641192917, "grad_norm": 0.6051112155525877, "learning_rate": 1.0831895063859166e-05, "loss": 0.838, "step": 1650 }, { "epoch": 1.537744641192917, "loss_cot": 0.4808972179889679, "loss_nocot": 0.4063337445259094, "step": 1650 }, { "epoch": 1.5386766076421248, "grad_norm": 0.6779818262740973, "learning_rate": 1.0824991370383155e-05, "loss": 0.9051, "step": 1651 }, { "epoch": 1.5386766076421248, "loss_cot": 0.4828760623931885, "loss_nocot": 0.279224157333374, "step": 1651 }, { "epoch": 1.5396085740913326, "grad_norm": 0.6943604620515323, "learning_rate": 1.0818087676907146e-05, "loss": 0.8661, "step": 1652 }, { "epoch": 1.5396085740913326, "loss_cot": 0.4487089514732361, "loss_nocot": 0.327869713306427, "step": 1652 }, { "epoch": 1.5405405405405406, "grad_norm": 0.6769786672951558, "learning_rate": 1.0811183983431136e-05, "loss": 0.9247, "step": 1653 }, { "epoch": 1.5405405405405406, "loss_cot": 0.4706481695175171, "loss_nocot": 0.36050331592559814, "step": 1653 }, { "epoch": 1.5414725069897484, "grad_norm": 0.57531392543024, "learning_rate": 1.0804280289955127e-05, "loss": 0.7943, "step": 1654 }, { "epoch": 1.5414725069897484, "loss_cot": 0.4919778108596802, "loss_nocot": 0.2809531092643738, "step": 1654 }, { "epoch": 1.5424044734389561, "grad_norm": 0.6048262874744668, "learning_rate": 1.0797376596479116e-05, "loss": 0.8407, "step": 1655 }, { "epoch": 1.5424044734389561, "loss_cot": 0.5090801119804382, "loss_nocot": 0.2439233809709549, "step": 1655 }, { "epoch": 1.5433364398881642, "grad_norm": 0.5871013807986577, "learning_rate": 1.0790472903003109e-05, "loss": 0.82, "step": 1656 }, { "epoch": 1.5433364398881642, "loss_cot": 0.438068151473999, "loss_nocot": 0.3333051800727844, "step": 1656 }, { "epoch": 1.544268406337372, "grad_norm": 0.7021256539675672, "learning_rate": 1.0783569209527098e-05, "loss": 0.8868, "step": 1657 }, { "epoch": 1.544268406337372, "loss_cot": 0.5393728017807007, "loss_nocot": 0.38275283575057983, "step": 1657 }, { "epoch": 1.5452003727865797, "grad_norm": 0.6152042920598378, "learning_rate": 1.0776665516051088e-05, "loss": 0.821, "step": 1658 }, { "epoch": 1.5452003727865797, "loss_cot": 0.5496668219566345, "loss_nocot": 0.5142016410827637, "step": 1658 }, { "epoch": 1.5461323392357875, "grad_norm": 0.684421070214081, "learning_rate": 1.0769761822575077e-05, "loss": 0.9517, "step": 1659 }, { "epoch": 1.5461323392357875, "loss_cot": 0.4800419211387634, "loss_nocot": 0.27448946237564087, "step": 1659 }, { "epoch": 1.5470643056849953, "grad_norm": 0.6747088236572529, "learning_rate": 1.076285812909907e-05, "loss": 0.8935, "step": 1660 }, { "epoch": 1.5470643056849953, "loss_cot": 0.5031642913818359, "loss_nocot": 0.2937529385089874, "step": 1660 }, { "epoch": 1.547996272134203, "grad_norm": 0.7407263678133685, "learning_rate": 1.0755954435623059e-05, "loss": 0.9493, "step": 1661 }, { "epoch": 1.547996272134203, "loss_cot": 0.5405120849609375, "loss_nocot": 0.33428460359573364, "step": 1661 }, { "epoch": 1.5489282385834109, "grad_norm": 0.6290624389369399, "learning_rate": 1.074905074214705e-05, "loss": 0.8486, "step": 1662 }, { "epoch": 1.5489282385834109, "loss_cot": 0.4808959662914276, "loss_nocot": 0.32871657609939575, "step": 1662 }, { "epoch": 1.5498602050326187, "grad_norm": 0.6285034169021771, "learning_rate": 1.0742147048671039e-05, "loss": 0.8331, "step": 1663 }, { "epoch": 1.5498602050326187, "loss_cot": 0.5389708280563354, "loss_nocot": 0.4159751534461975, "step": 1663 }, { "epoch": 1.5507921714818267, "grad_norm": 0.6772762522996345, "learning_rate": 1.0735243355195031e-05, "loss": 0.9356, "step": 1664 }, { "epoch": 1.5507921714818267, "loss_cot": 0.45986706018447876, "loss_nocot": 0.29347410798072815, "step": 1664 }, { "epoch": 1.5517241379310345, "grad_norm": 0.6276141893176237, "learning_rate": 1.072833966171902e-05, "loss": 0.8279, "step": 1665 }, { "epoch": 1.5517241379310345, "loss_cot": 0.43261075019836426, "loss_nocot": 0.4143577218055725, "step": 1665 }, { "epoch": 1.5526561043802423, "grad_norm": 0.6406386965075, "learning_rate": 1.072143596824301e-05, "loss": 0.8546, "step": 1666 }, { "epoch": 1.5526561043802423, "loss_cot": 0.5208892822265625, "loss_nocot": 0.3135748505592346, "step": 1666 }, { "epoch": 1.5535880708294503, "grad_norm": 0.6537097738027875, "learning_rate": 1.0714532274767002e-05, "loss": 0.8405, "step": 1667 }, { "epoch": 1.5535880708294503, "loss_cot": 0.483306348323822, "loss_nocot": 0.3452461361885071, "step": 1667 }, { "epoch": 1.554520037278658, "grad_norm": 0.5767204601768777, "learning_rate": 1.0707628581290992e-05, "loss": 0.8185, "step": 1668 }, { "epoch": 1.554520037278658, "loss_cot": 0.5363765358924866, "loss_nocot": 0.3236507773399353, "step": 1668 }, { "epoch": 1.5554520037278659, "grad_norm": 0.5951060557299294, "learning_rate": 1.0700724887814981e-05, "loss": 0.8343, "step": 1669 }, { "epoch": 1.5554520037278659, "loss_cot": 0.5375430583953857, "loss_nocot": 0.37383681535720825, "step": 1669 }, { "epoch": 1.5563839701770736, "grad_norm": 0.635309479883647, "learning_rate": 1.0693821194338972e-05, "loss": 0.8691, "step": 1670 }, { "epoch": 1.5563839701770736, "loss_cot": 0.4845775365829468, "loss_nocot": 0.5418167114257812, "step": 1670 }, { "epoch": 1.5573159366262814, "grad_norm": 0.6790601693955615, "learning_rate": 1.0686917500862963e-05, "loss": 0.8896, "step": 1671 }, { "epoch": 1.5573159366262814, "loss_cot": 0.5542194843292236, "loss_nocot": 0.3705540895462036, "step": 1671 }, { "epoch": 1.5582479030754892, "grad_norm": 0.6432216151883782, "learning_rate": 1.0680013807386953e-05, "loss": 0.9141, "step": 1672 }, { "epoch": 1.5582479030754892, "loss_cot": 0.588895320892334, "loss_nocot": 0.3494681417942047, "step": 1672 }, { "epoch": 1.559179869524697, "grad_norm": 0.6015058840526093, "learning_rate": 1.0673110113910943e-05, "loss": 0.8742, "step": 1673 }, { "epoch": 1.559179869524697, "loss_cot": 0.46199744939804077, "loss_nocot": 0.4650207757949829, "step": 1673 }, { "epoch": 1.5601118359739048, "grad_norm": 0.6531250409067583, "learning_rate": 1.0666206420434933e-05, "loss": 0.8442, "step": 1674 }, { "epoch": 1.5601118359739048, "loss_cot": 0.5317034721374512, "loss_nocot": 0.3474102020263672, "step": 1674 }, { "epoch": 1.5610438024231128, "grad_norm": 0.6225827708485826, "learning_rate": 1.0659302726958924e-05, "loss": 0.8978, "step": 1675 }, { "epoch": 1.5610438024231128, "loss_cot": 0.5219936370849609, "loss_nocot": 0.35885047912597656, "step": 1675 }, { "epoch": 1.5619757688723206, "grad_norm": 0.6587432918098031, "learning_rate": 1.0652399033482915e-05, "loss": 0.8816, "step": 1676 }, { "epoch": 1.5619757688723206, "loss_cot": 0.4573380947113037, "loss_nocot": 0.4280986189842224, "step": 1676 }, { "epoch": 1.5629077353215284, "grad_norm": 0.6485584215603062, "learning_rate": 1.0645495340006904e-05, "loss": 0.8865, "step": 1677 }, { "epoch": 1.5629077353215284, "loss_cot": 0.48065054416656494, "loss_nocot": 0.32069262862205505, "step": 1677 }, { "epoch": 1.5638397017707364, "grad_norm": 0.6421404722711417, "learning_rate": 1.0638591646530896e-05, "loss": 0.8552, "step": 1678 }, { "epoch": 1.5638397017707364, "loss_cot": 0.5159881711006165, "loss_nocot": 0.37884241342544556, "step": 1678 }, { "epoch": 1.5647716682199442, "grad_norm": 0.6486298053033939, "learning_rate": 1.0631687953054885e-05, "loss": 0.8137, "step": 1679 }, { "epoch": 1.5647716682199442, "loss_cot": 0.5552141666412354, "loss_nocot": 0.4824533760547638, "step": 1679 }, { "epoch": 1.565703634669152, "grad_norm": 0.6141992382126046, "learning_rate": 1.0624784259578876e-05, "loss": 0.8889, "step": 1680 }, { "epoch": 1.565703634669152, "loss_cot": 0.5087778568267822, "loss_nocot": 0.3506010174751282, "step": 1680 }, { "epoch": 1.5666356011183598, "grad_norm": 0.6315993025328295, "learning_rate": 1.0617880566102865e-05, "loss": 0.8222, "step": 1681 }, { "epoch": 1.5666356011183598, "loss_cot": 0.5430723428726196, "loss_nocot": 0.37734004855155945, "step": 1681 }, { "epoch": 1.5675675675675675, "grad_norm": 0.6549470806958778, "learning_rate": 1.0610976872626857e-05, "loss": 0.8301, "step": 1682 }, { "epoch": 1.5675675675675675, "loss_cot": 0.47657084465026855, "loss_nocot": 0.36065322160720825, "step": 1682 }, { "epoch": 1.5684995340167753, "grad_norm": 0.6078221634806271, "learning_rate": 1.0604073179150846e-05, "loss": 0.8386, "step": 1683 }, { "epoch": 1.5684995340167753, "loss_cot": 0.4579724967479706, "loss_nocot": 0.3266468048095703, "step": 1683 }, { "epoch": 1.5694315004659831, "grad_norm": 0.6185538372526275, "learning_rate": 1.0597169485674837e-05, "loss": 0.8612, "step": 1684 }, { "epoch": 1.5694315004659831, "loss_cot": 0.5035451650619507, "loss_nocot": 0.46309518814086914, "step": 1684 }, { "epoch": 1.570363466915191, "grad_norm": 0.6083786368010288, "learning_rate": 1.0590265792198828e-05, "loss": 0.866, "step": 1685 }, { "epoch": 1.570363466915191, "loss_cot": 0.454046368598938, "loss_nocot": 0.2530980706214905, "step": 1685 }, { "epoch": 1.571295433364399, "grad_norm": 0.673830666827696, "learning_rate": 1.0583362098722819e-05, "loss": 0.8731, "step": 1686 }, { "epoch": 1.571295433364399, "loss_cot": 0.46532678604125977, "loss_nocot": 0.24207621812820435, "step": 1686 }, { "epoch": 1.5722273998136067, "grad_norm": 0.6162226821484545, "learning_rate": 1.0576458405246808e-05, "loss": 0.8176, "step": 1687 }, { "epoch": 1.5722273998136067, "loss_cot": 0.5191173553466797, "loss_nocot": 0.26024430990219116, "step": 1687 }, { "epoch": 1.5731593662628145, "grad_norm": 0.64492837247049, "learning_rate": 1.0569554711770797e-05, "loss": 0.9111, "step": 1688 }, { "epoch": 1.5731593662628145, "loss_cot": 0.47072017192840576, "loss_nocot": 0.487080842256546, "step": 1688 }, { "epoch": 1.5740913327120225, "grad_norm": 0.6241061097280067, "learning_rate": 1.056265101829479e-05, "loss": 0.9126, "step": 1689 }, { "epoch": 1.5740913327120225, "loss_cot": 0.5641820430755615, "loss_nocot": 0.3235694169998169, "step": 1689 }, { "epoch": 1.5750232991612303, "grad_norm": 0.6646503816246608, "learning_rate": 1.055574732481878e-05, "loss": 0.883, "step": 1690 }, { "epoch": 1.5750232991612303, "loss_cot": 0.500015139579773, "loss_nocot": 0.2776659429073334, "step": 1690 }, { "epoch": 1.575955265610438, "grad_norm": 0.5991226698645734, "learning_rate": 1.0548843631342769e-05, "loss": 0.8568, "step": 1691 }, { "epoch": 1.575955265610438, "loss_cot": 0.535699725151062, "loss_nocot": 0.28515133261680603, "step": 1691 }, { "epoch": 1.5768872320596459, "grad_norm": 0.6564447494381219, "learning_rate": 1.0541939937866758e-05, "loss": 0.8592, "step": 1692 }, { "epoch": 1.5768872320596459, "loss_cot": 0.5185387134552002, "loss_nocot": 0.3056071996688843, "step": 1692 }, { "epoch": 1.5778191985088537, "grad_norm": 0.6290386055060054, "learning_rate": 1.053503624439075e-05, "loss": 0.8826, "step": 1693 }, { "epoch": 1.5778191985088537, "loss_cot": 0.47622835636138916, "loss_nocot": 0.3134312629699707, "step": 1693 }, { "epoch": 1.5787511649580614, "grad_norm": 0.6331836196430386, "learning_rate": 1.0528132550914741e-05, "loss": 0.8531, "step": 1694 }, { "epoch": 1.5787511649580614, "loss_cot": 0.572240948677063, "loss_nocot": 0.3708643317222595, "step": 1694 }, { "epoch": 1.5796831314072692, "grad_norm": 0.6413281766954805, "learning_rate": 1.052122885743873e-05, "loss": 0.9163, "step": 1695 }, { "epoch": 1.5796831314072692, "loss_cot": 0.5437593460083008, "loss_nocot": 0.38135480880737305, "step": 1695 }, { "epoch": 1.580615097856477, "grad_norm": 0.5901301369091168, "learning_rate": 1.0514325163962723e-05, "loss": 0.8308, "step": 1696 }, { "epoch": 1.580615097856477, "loss_cot": 0.4963034987449646, "loss_nocot": 0.332390159368515, "step": 1696 }, { "epoch": 1.581547064305685, "grad_norm": 0.6195201275444192, "learning_rate": 1.0507421470486712e-05, "loss": 0.8566, "step": 1697 }, { "epoch": 1.581547064305685, "loss_cot": 0.4905191659927368, "loss_nocot": 0.38519835472106934, "step": 1697 }, { "epoch": 1.5824790307548928, "grad_norm": 0.612565568987491, "learning_rate": 1.05005177770107e-05, "loss": 0.8525, "step": 1698 }, { "epoch": 1.5824790307548928, "loss_cot": 0.46413958072662354, "loss_nocot": 0.2980695366859436, "step": 1698 }, { "epoch": 1.5834109972041006, "grad_norm": 0.6673778699929166, "learning_rate": 1.0493614083534691e-05, "loss": 0.8298, "step": 1699 }, { "epoch": 1.5834109972041006, "loss_cot": 0.5046391487121582, "loss_nocot": 0.37046143412590027, "step": 1699 }, { "epoch": 1.5843429636533086, "grad_norm": 0.6697533532927605, "learning_rate": 1.0486710390058684e-05, "loss": 0.8993, "step": 1700 }, { "epoch": 1.5843429636533086, "loss_cot": 0.5023947954177856, "loss_nocot": 0.25037819147109985, "step": 1700 }, { "epoch": 1.5852749301025164, "grad_norm": 0.5775529688289044, "learning_rate": 1.0479806696582673e-05, "loss": 0.8022, "step": 1701 }, { "epoch": 1.5852749301025164, "loss_cot": 0.5598706007003784, "loss_nocot": 0.4147469401359558, "step": 1701 }, { "epoch": 1.5862068965517242, "grad_norm": 0.5973426217537342, "learning_rate": 1.0472903003106662e-05, "loss": 0.8371, "step": 1702 }, { "epoch": 1.5862068965517242, "loss_cot": 0.4243565499782562, "loss_nocot": 0.4054730534553528, "step": 1702 }, { "epoch": 1.587138863000932, "grad_norm": 0.6476842276969612, "learning_rate": 1.0465999309630653e-05, "loss": 0.8723, "step": 1703 }, { "epoch": 1.587138863000932, "loss_cot": 0.5361880660057068, "loss_nocot": 0.40063488483428955, "step": 1703 }, { "epoch": 1.5880708294501398, "grad_norm": 0.6171135054467458, "learning_rate": 1.0459095616154643e-05, "loss": 0.8813, "step": 1704 }, { "epoch": 1.5880708294501398, "loss_cot": 0.4886944890022278, "loss_nocot": 0.3765333294868469, "step": 1704 }, { "epoch": 1.5890027958993476, "grad_norm": 0.6944752783162371, "learning_rate": 1.0452191922678634e-05, "loss": 0.8551, "step": 1705 }, { "epoch": 1.5890027958993476, "loss_cot": 0.5101243853569031, "loss_nocot": 0.4464907646179199, "step": 1705 }, { "epoch": 1.5899347623485554, "grad_norm": 0.6860475162200753, "learning_rate": 1.0445288229202623e-05, "loss": 0.8679, "step": 1706 }, { "epoch": 1.5899347623485554, "loss_cot": 0.4587276577949524, "loss_nocot": 0.3516753017902374, "step": 1706 }, { "epoch": 1.5908667287977631, "grad_norm": 0.6216793850849804, "learning_rate": 1.0438384535726616e-05, "loss": 0.8488, "step": 1707 }, { "epoch": 1.5908667287977631, "loss_cot": 0.46233856678009033, "loss_nocot": 0.3764572739601135, "step": 1707 }, { "epoch": 1.5917986952469712, "grad_norm": 0.8540554055151324, "learning_rate": 1.0431480842250605e-05, "loss": 0.8613, "step": 1708 }, { "epoch": 1.5917986952469712, "loss_cot": 0.5312057733535767, "loss_nocot": 0.2902611494064331, "step": 1708 }, { "epoch": 1.592730661696179, "grad_norm": 0.6170055752149173, "learning_rate": 1.0424577148774595e-05, "loss": 0.837, "step": 1709 }, { "epoch": 1.592730661696179, "loss_cot": 0.550002932548523, "loss_nocot": 0.3358704447746277, "step": 1709 }, { "epoch": 1.5936626281453867, "grad_norm": 0.6609732160344687, "learning_rate": 1.0417673455298584e-05, "loss": 0.8658, "step": 1710 }, { "epoch": 1.5936626281453867, "loss_cot": 0.5517463684082031, "loss_nocot": 0.31517794728279114, "step": 1710 }, { "epoch": 1.5945945945945947, "grad_norm": 0.5867907912770023, "learning_rate": 1.0410769761822577e-05, "loss": 0.835, "step": 1711 }, { "epoch": 1.5945945945945947, "loss_cot": 0.5805023312568665, "loss_nocot": 0.2638630270957947, "step": 1711 }, { "epoch": 1.5955265610438025, "grad_norm": 0.5953373526701042, "learning_rate": 1.0403866068346566e-05, "loss": 0.8101, "step": 1712 }, { "epoch": 1.5955265610438025, "loss_cot": 0.5384802222251892, "loss_nocot": 0.35415536165237427, "step": 1712 }, { "epoch": 1.5964585274930103, "grad_norm": 0.615127660311752, "learning_rate": 1.0396962374870557e-05, "loss": 0.8699, "step": 1713 }, { "epoch": 1.5964585274930103, "loss_cot": 0.4498322606086731, "loss_nocot": 0.3458295166492462, "step": 1713 }, { "epoch": 1.597390493942218, "grad_norm": 0.6389896708738069, "learning_rate": 1.0390058681394546e-05, "loss": 0.8547, "step": 1714 }, { "epoch": 1.597390493942218, "loss_cot": 0.43839389085769653, "loss_nocot": 0.3301970362663269, "step": 1714 }, { "epoch": 1.598322460391426, "grad_norm": 0.5838463714660188, "learning_rate": 1.0383154987918538e-05, "loss": 0.8134, "step": 1715 }, { "epoch": 1.598322460391426, "loss_cot": 0.49273109436035156, "loss_nocot": 0.27981138229370117, "step": 1715 }, { "epoch": 1.5992544268406337, "grad_norm": 0.641521529708199, "learning_rate": 1.0376251294442527e-05, "loss": 0.8519, "step": 1716 }, { "epoch": 1.5992544268406337, "loss_cot": 0.5074852705001831, "loss_nocot": 0.385647714138031, "step": 1716 }, { "epoch": 1.6001863932898415, "grad_norm": 0.6477604556651575, "learning_rate": 1.0369347600966518e-05, "loss": 0.8718, "step": 1717 }, { "epoch": 1.6001863932898415, "loss_cot": 0.5399183034896851, "loss_nocot": 0.29433950781822205, "step": 1717 }, { "epoch": 1.6011183597390493, "grad_norm": 0.6306981977876236, "learning_rate": 1.0362443907490509e-05, "loss": 0.8453, "step": 1718 }, { "epoch": 1.6011183597390493, "loss_cot": 0.5003615617752075, "loss_nocot": 0.3430209159851074, "step": 1718 }, { "epoch": 1.6020503261882573, "grad_norm": 0.6481273314124754, "learning_rate": 1.03555402140145e-05, "loss": 0.901, "step": 1719 }, { "epoch": 1.6020503261882573, "loss_cot": 0.5220375061035156, "loss_nocot": 0.27719977498054504, "step": 1719 }, { "epoch": 1.602982292637465, "grad_norm": 0.6194640325787392, "learning_rate": 1.0348636520538488e-05, "loss": 0.8916, "step": 1720 }, { "epoch": 1.602982292637465, "loss_cot": 0.5291519165039062, "loss_nocot": 0.37209028005599976, "step": 1720 }, { "epoch": 1.6039142590866728, "grad_norm": 0.7383726743712696, "learning_rate": 1.0341732827062479e-05, "loss": 0.9447, "step": 1721 }, { "epoch": 1.6039142590866728, "loss_cot": 0.44330844283103943, "loss_nocot": 0.3566659390926361, "step": 1721 }, { "epoch": 1.6048462255358809, "grad_norm": 0.596527328215474, "learning_rate": 1.033482913358647e-05, "loss": 0.8052, "step": 1722 }, { "epoch": 1.6048462255358809, "loss_cot": 0.4921649098396301, "loss_nocot": 0.34260445833206177, "step": 1722 }, { "epoch": 1.6057781919850886, "grad_norm": 0.6001286218062564, "learning_rate": 1.032792544011046e-05, "loss": 0.8664, "step": 1723 }, { "epoch": 1.6057781919850886, "loss_cot": 0.5369458794593811, "loss_nocot": 0.289498895406723, "step": 1723 }, { "epoch": 1.6067101584342964, "grad_norm": 0.636507579533501, "learning_rate": 1.032102174663445e-05, "loss": 0.8761, "step": 1724 }, { "epoch": 1.6067101584342964, "loss_cot": 0.5362993478775024, "loss_nocot": 0.3217214047908783, "step": 1724 }, { "epoch": 1.6076421248835042, "grad_norm": 0.5994605247221174, "learning_rate": 1.031411805315844e-05, "loss": 0.8117, "step": 1725 }, { "epoch": 1.6076421248835042, "loss_cot": 0.45135483145713806, "loss_nocot": 0.49653226137161255, "step": 1725 }, { "epoch": 1.608574091332712, "grad_norm": 0.6227747630277176, "learning_rate": 1.0307214359682431e-05, "loss": 0.8577, "step": 1726 }, { "epoch": 1.608574091332712, "loss_cot": 0.47718650102615356, "loss_nocot": 0.42532771825790405, "step": 1726 }, { "epoch": 1.6095060577819198, "grad_norm": 0.7187348725362844, "learning_rate": 1.0300310666206422e-05, "loss": 0.8754, "step": 1727 }, { "epoch": 1.6095060577819198, "loss_cot": 0.5532369613647461, "loss_nocot": 0.43948689103126526, "step": 1727 }, { "epoch": 1.6104380242311276, "grad_norm": 0.6603920607052473, "learning_rate": 1.029340697273041e-05, "loss": 0.9058, "step": 1728 }, { "epoch": 1.6104380242311276, "loss_cot": 0.539958119392395, "loss_nocot": 0.3216264247894287, "step": 1728 }, { "epoch": 1.6113699906803354, "grad_norm": 0.6273555172427332, "learning_rate": 1.0286503279254403e-05, "loss": 0.8463, "step": 1729 }, { "epoch": 1.6113699906803354, "loss_cot": 0.542619526386261, "loss_nocot": 0.4165526032447815, "step": 1729 }, { "epoch": 1.6123019571295434, "grad_norm": 0.6480797615954957, "learning_rate": 1.0279599585778392e-05, "loss": 0.8651, "step": 1730 }, { "epoch": 1.6123019571295434, "loss_cot": 0.4940071702003479, "loss_nocot": 0.4351385831832886, "step": 1730 }, { "epoch": 1.6132339235787512, "grad_norm": 0.6331164488497927, "learning_rate": 1.0272695892302383e-05, "loss": 0.8641, "step": 1731 }, { "epoch": 1.6132339235787512, "loss_cot": 0.5485959053039551, "loss_nocot": 0.3187260031700134, "step": 1731 }, { "epoch": 1.614165890027959, "grad_norm": 0.670057586778813, "learning_rate": 1.0265792198826372e-05, "loss": 0.8763, "step": 1732 }, { "epoch": 1.614165890027959, "loss_cot": 0.5078606605529785, "loss_nocot": 0.35569891333580017, "step": 1732 }, { "epoch": 1.615097856477167, "grad_norm": 0.6309727051794904, "learning_rate": 1.0258888505350364e-05, "loss": 0.8624, "step": 1733 }, { "epoch": 1.615097856477167, "loss_cot": 0.48495203256607056, "loss_nocot": 0.24472908675670624, "step": 1733 }, { "epoch": 1.6160298229263748, "grad_norm": 0.6094916694286064, "learning_rate": 1.0251984811874353e-05, "loss": 0.8201, "step": 1734 }, { "epoch": 1.6160298229263748, "loss_cot": 0.5033906698226929, "loss_nocot": 0.3950091302394867, "step": 1734 }, { "epoch": 1.6169617893755825, "grad_norm": 0.6054308841217253, "learning_rate": 1.0245081118398344e-05, "loss": 0.8337, "step": 1735 }, { "epoch": 1.6169617893755825, "loss_cot": 0.4420512318611145, "loss_nocot": 0.39721232652664185, "step": 1735 }, { "epoch": 1.6178937558247903, "grad_norm": 0.6253063259130347, "learning_rate": 1.0238177424922335e-05, "loss": 0.8234, "step": 1736 }, { "epoch": 1.6178937558247903, "loss_cot": 0.5468615293502808, "loss_nocot": 0.3180249035358429, "step": 1736 }, { "epoch": 1.6188257222739981, "grad_norm": 0.5919136121866068, "learning_rate": 1.0231273731446326e-05, "loss": 0.8278, "step": 1737 }, { "epoch": 1.6188257222739981, "loss_cot": 0.47032496333122253, "loss_nocot": 0.3814482092857361, "step": 1737 }, { "epoch": 1.619757688723206, "grad_norm": 0.6109039511220127, "learning_rate": 1.0224370037970315e-05, "loss": 0.8399, "step": 1738 }, { "epoch": 1.619757688723206, "loss_cot": 0.4470192790031433, "loss_nocot": 0.4135515093803406, "step": 1738 }, { "epoch": 1.6206896551724137, "grad_norm": 0.6541678992034057, "learning_rate": 1.0217466344494304e-05, "loss": 0.8998, "step": 1739 }, { "epoch": 1.6206896551724137, "loss_cot": 0.5147205591201782, "loss_nocot": 0.3783837556838989, "step": 1739 }, { "epoch": 1.6216216216216215, "grad_norm": 0.6533385034609599, "learning_rate": 1.0210562651018296e-05, "loss": 0.9559, "step": 1740 }, { "epoch": 1.6216216216216215, "loss_cot": 0.555456280708313, "loss_nocot": 0.2789958715438843, "step": 1740 }, { "epoch": 1.6225535880708295, "grad_norm": 0.6252179243932647, "learning_rate": 1.0203658957542287e-05, "loss": 0.8568, "step": 1741 }, { "epoch": 1.6225535880708295, "loss_cot": 0.465770423412323, "loss_nocot": 0.4029736816883087, "step": 1741 }, { "epoch": 1.6234855545200373, "grad_norm": 0.6410691608116572, "learning_rate": 1.0196755264066276e-05, "loss": 0.9053, "step": 1742 }, { "epoch": 1.6234855545200373, "loss_cot": 0.5221333503723145, "loss_nocot": 0.34623798727989197, "step": 1742 }, { "epoch": 1.624417520969245, "grad_norm": 0.6448041813025664, "learning_rate": 1.0189851570590265e-05, "loss": 0.8979, "step": 1743 }, { "epoch": 1.624417520969245, "loss_cot": 0.5205262899398804, "loss_nocot": 0.382495641708374, "step": 1743 }, { "epoch": 1.625349487418453, "grad_norm": 0.6670417314520144, "learning_rate": 1.0182947877114257e-05, "loss": 0.9391, "step": 1744 }, { "epoch": 1.625349487418453, "loss_cot": 0.4848615527153015, "loss_nocot": 0.4102969765663147, "step": 1744 }, { "epoch": 1.6262814538676609, "grad_norm": 0.673408418142251, "learning_rate": 1.0176044183638248e-05, "loss": 0.924, "step": 1745 }, { "epoch": 1.6262814538676609, "loss_cot": 0.5382353663444519, "loss_nocot": 0.3003155291080475, "step": 1745 }, { "epoch": 1.6272134203168687, "grad_norm": 0.5973701227533998, "learning_rate": 1.0169140490162237e-05, "loss": 0.8526, "step": 1746 }, { "epoch": 1.6272134203168687, "loss_cot": 0.5007916688919067, "loss_nocot": 0.28799790143966675, "step": 1746 }, { "epoch": 1.6281453867660765, "grad_norm": 0.6211436824740567, "learning_rate": 1.016223679668623e-05, "loss": 0.8404, "step": 1747 }, { "epoch": 1.6281453867660765, "loss_cot": 0.5724890232086182, "loss_nocot": 0.459868460893631, "step": 1747 }, { "epoch": 1.6290773532152842, "grad_norm": 0.6935322649485042, "learning_rate": 1.0155333103210219e-05, "loss": 0.9409, "step": 1748 }, { "epoch": 1.6290773532152842, "loss_cot": 0.5347653031349182, "loss_nocot": 0.3193473219871521, "step": 1748 }, { "epoch": 1.630009319664492, "grad_norm": 0.6287567201811298, "learning_rate": 1.0148429409734208e-05, "loss": 0.8235, "step": 1749 }, { "epoch": 1.630009319664492, "loss_cot": 0.5576008558273315, "loss_nocot": 0.4065510034561157, "step": 1749 }, { "epoch": 1.6309412861136998, "grad_norm": 0.671058680613206, "learning_rate": 1.0141525716258198e-05, "loss": 0.8562, "step": 1750 }, { "epoch": 1.6309412861136998, "loss_cot": 0.4911854863166809, "loss_nocot": 0.3701513409614563, "step": 1750 }, { "epoch": 1.6318732525629076, "grad_norm": 0.6388977303415985, "learning_rate": 1.0134622022782191e-05, "loss": 0.8966, "step": 1751 }, { "epoch": 1.6318732525629076, "loss_cot": 0.4535139799118042, "loss_nocot": 0.2835211157798767, "step": 1751 }, { "epoch": 1.6328052190121156, "grad_norm": 0.6132526427295036, "learning_rate": 1.012771832930618e-05, "loss": 0.8293, "step": 1752 }, { "epoch": 1.6328052190121156, "loss_cot": 0.49367037415504456, "loss_nocot": 0.3593413233757019, "step": 1752 }, { "epoch": 1.6337371854613234, "grad_norm": 0.6560967700712109, "learning_rate": 1.0120814635830169e-05, "loss": 0.8994, "step": 1753 }, { "epoch": 1.6337371854613234, "loss_cot": 0.4564165771007538, "loss_nocot": 0.27290281653404236, "step": 1753 }, { "epoch": 1.6346691519105312, "grad_norm": 0.5955277431792098, "learning_rate": 1.011391094235416e-05, "loss": 0.8096, "step": 1754 }, { "epoch": 1.6346691519105312, "loss_cot": 0.5453699827194214, "loss_nocot": 0.273671954870224, "step": 1754 }, { "epoch": 1.6356011183597392, "grad_norm": 0.6078189458321036, "learning_rate": 1.010700724887815e-05, "loss": 0.8085, "step": 1755 }, { "epoch": 1.6356011183597392, "loss_cot": 0.5252864360809326, "loss_nocot": 0.31940335035324097, "step": 1755 }, { "epoch": 1.636533084808947, "grad_norm": 0.5884365680999488, "learning_rate": 1.0100103555402141e-05, "loss": 0.8115, "step": 1756 }, { "epoch": 1.636533084808947, "loss_cot": 0.5151607990264893, "loss_nocot": 0.3686828911304474, "step": 1756 }, { "epoch": 1.6374650512581548, "grad_norm": 0.5926538962867273, "learning_rate": 1.009319986192613e-05, "loss": 0.8283, "step": 1757 }, { "epoch": 1.6374650512581548, "loss_cot": 0.5679875612258911, "loss_nocot": 0.4237788915634155, "step": 1757 }, { "epoch": 1.6383970177073626, "grad_norm": 0.6165522313908335, "learning_rate": 1.0086296168450123e-05, "loss": 0.8549, "step": 1758 }, { "epoch": 1.6383970177073626, "loss_cot": 0.4594220221042633, "loss_nocot": 0.2995157241821289, "step": 1758 }, { "epoch": 1.6393289841565704, "grad_norm": 0.5886681158201326, "learning_rate": 1.0079392474974112e-05, "loss": 0.8156, "step": 1759 }, { "epoch": 1.6393289841565704, "loss_cot": 0.49983295798301697, "loss_nocot": 0.34816110134124756, "step": 1759 }, { "epoch": 1.6402609506057781, "grad_norm": 0.6381816078467982, "learning_rate": 1.0072488781498102e-05, "loss": 0.8717, "step": 1760 }, { "epoch": 1.6402609506057781, "loss_cot": 0.5565766096115112, "loss_nocot": 0.289800763130188, "step": 1760 }, { "epoch": 1.641192917054986, "grad_norm": 0.6894178121673238, "learning_rate": 1.0065585088022091e-05, "loss": 0.8438, "step": 1761 }, { "epoch": 1.641192917054986, "loss_cot": 0.5005894899368286, "loss_nocot": 0.3122454285621643, "step": 1761 }, { "epoch": 1.6421248835041937, "grad_norm": 0.632096204270641, "learning_rate": 1.0058681394546084e-05, "loss": 0.821, "step": 1762 }, { "epoch": 1.6421248835041937, "loss_cot": 0.5039812326431274, "loss_nocot": 0.3291740119457245, "step": 1762 }, { "epoch": 1.6430568499534017, "grad_norm": 0.629554239685036, "learning_rate": 1.0051777701070073e-05, "loss": 0.8346, "step": 1763 }, { "epoch": 1.6430568499534017, "loss_cot": 0.5155237913131714, "loss_nocot": 0.3721364736557007, "step": 1763 }, { "epoch": 1.6439888164026095, "grad_norm": 0.5753327770185073, "learning_rate": 1.0044874007594064e-05, "loss": 0.8335, "step": 1764 }, { "epoch": 1.6439888164026095, "loss_cot": 0.5393873453140259, "loss_nocot": 0.27375176548957825, "step": 1764 }, { "epoch": 1.6449207828518173, "grad_norm": 0.598769075173567, "learning_rate": 1.0037970314118053e-05, "loss": 0.8284, "step": 1765 }, { "epoch": 1.6449207828518173, "loss_cot": 0.510338544845581, "loss_nocot": 0.28255942463874817, "step": 1765 }, { "epoch": 1.6458527493010253, "grad_norm": 0.5859243056723309, "learning_rate": 1.0031066620642045e-05, "loss": 0.8078, "step": 1766 }, { "epoch": 1.6458527493010253, "loss_cot": 0.44099438190460205, "loss_nocot": 0.4998970031738281, "step": 1766 }, { "epoch": 1.646784715750233, "grad_norm": 0.6932144711958884, "learning_rate": 1.0024162927166034e-05, "loss": 0.908, "step": 1767 }, { "epoch": 1.646784715750233, "loss_cot": 0.5054455995559692, "loss_nocot": 0.41069090366363525, "step": 1767 }, { "epoch": 1.647716682199441, "grad_norm": 0.673286353403486, "learning_rate": 1.0017259233690025e-05, "loss": 0.8941, "step": 1768 }, { "epoch": 1.647716682199441, "loss_cot": 0.48990267515182495, "loss_nocot": 0.35483622550964355, "step": 1768 }, { "epoch": 1.6486486486486487, "grad_norm": 0.6267794325727695, "learning_rate": 1.0010355540214016e-05, "loss": 0.8871, "step": 1769 }, { "epoch": 1.6486486486486487, "loss_cot": 0.524389386177063, "loss_nocot": 0.3908592462539673, "step": 1769 }, { "epoch": 1.6495806150978565, "grad_norm": 0.6567914401328302, "learning_rate": 1.0003451846738006e-05, "loss": 0.8879, "step": 1770 }, { "epoch": 1.6495806150978565, "loss_cot": 0.48397502303123474, "loss_nocot": 0.2951161861419678, "step": 1770 }, { "epoch": 1.6505125815470643, "grad_norm": 0.5857528277460602, "learning_rate": 9.996548153261995e-06, "loss": 0.7878, "step": 1771 }, { "epoch": 1.6505125815470643, "loss_cot": 0.4765109419822693, "loss_nocot": 0.3592328429222107, "step": 1771 }, { "epoch": 1.651444547996272, "grad_norm": 0.6176600931198108, "learning_rate": 9.989644459785986e-06, "loss": 0.8212, "step": 1772 }, { "epoch": 1.651444547996272, "loss_cot": 0.47852036356925964, "loss_nocot": 0.22102931141853333, "step": 1772 }, { "epoch": 1.6523765144454798, "grad_norm": 0.6005026678779953, "learning_rate": 9.982740766309977e-06, "loss": 0.8389, "step": 1773 }, { "epoch": 1.6523765144454798, "loss_cot": 0.47619667649269104, "loss_nocot": 0.29693603515625, "step": 1773 }, { "epoch": 1.6533084808946876, "grad_norm": 0.5841492260261438, "learning_rate": 9.975837072833968e-06, "loss": 0.8159, "step": 1774 }, { "epoch": 1.6533084808946876, "loss_cot": 0.4791331887245178, "loss_nocot": 0.4146839678287506, "step": 1774 }, { "epoch": 1.6542404473438956, "grad_norm": 0.6480473824668879, "learning_rate": 9.968933379357957e-06, "loss": 0.8946, "step": 1775 }, { "epoch": 1.6542404473438956, "loss_cot": 0.5605065822601318, "loss_nocot": 0.3371042311191559, "step": 1775 }, { "epoch": 1.6551724137931034, "grad_norm": 0.615015709411091, "learning_rate": 9.962029685881947e-06, "loss": 0.8343, "step": 1776 }, { "epoch": 1.6551724137931034, "loss_cot": 0.5025014877319336, "loss_nocot": 0.2831104099750519, "step": 1776 }, { "epoch": 1.6561043802423114, "grad_norm": 0.6338001230062853, "learning_rate": 9.955125992405938e-06, "loss": 0.8284, "step": 1777 }, { "epoch": 1.6561043802423114, "loss_cot": 0.4898627996444702, "loss_nocot": 0.3917662799358368, "step": 1777 }, { "epoch": 1.6570363466915192, "grad_norm": 0.6212871818377633, "learning_rate": 9.948222298929929e-06, "loss": 0.8408, "step": 1778 }, { "epoch": 1.6570363466915192, "loss_cot": 0.513185441493988, "loss_nocot": 0.27283552289009094, "step": 1778 }, { "epoch": 1.657968313140727, "grad_norm": 0.6321012613884546, "learning_rate": 9.94131860545392e-06, "loss": 0.8912, "step": 1779 }, { "epoch": 1.657968313140727, "loss_cot": 0.41616591811180115, "loss_nocot": 0.27811282873153687, "step": 1779 }, { "epoch": 1.6589002795899348, "grad_norm": 0.6039357595794032, "learning_rate": 9.934414911977909e-06, "loss": 0.8131, "step": 1780 }, { "epoch": 1.6589002795899348, "loss_cot": 0.5371106863021851, "loss_nocot": 0.37972384691238403, "step": 1780 }, { "epoch": 1.6598322460391426, "grad_norm": 0.6760460093008761, "learning_rate": 9.9275112185019e-06, "loss": 0.9144, "step": 1781 }, { "epoch": 1.6598322460391426, "loss_cot": 0.5044912099838257, "loss_nocot": 0.29374241828918457, "step": 1781 }, { "epoch": 1.6607642124883504, "grad_norm": 0.5824729071143304, "learning_rate": 9.92060752502589e-06, "loss": 0.8412, "step": 1782 }, { "epoch": 1.6607642124883504, "loss_cot": 0.4627910852432251, "loss_nocot": 0.24919000267982483, "step": 1782 }, { "epoch": 1.6616961789375582, "grad_norm": 0.6382532492991967, "learning_rate": 9.91370383154988e-06, "loss": 0.8541, "step": 1783 }, { "epoch": 1.6616961789375582, "loss_cot": 0.5037863850593567, "loss_nocot": 0.40002456307411194, "step": 1783 }, { "epoch": 1.662628145386766, "grad_norm": 0.690489784925376, "learning_rate": 9.90680013807387e-06, "loss": 0.9182, "step": 1784 }, { "epoch": 1.662628145386766, "loss_cot": 0.5269054174423218, "loss_nocot": 0.3658807575702667, "step": 1784 }, { "epoch": 1.6635601118359737, "grad_norm": 0.6394967364765901, "learning_rate": 9.89989644459786e-06, "loss": 0.8421, "step": 1785 }, { "epoch": 1.6635601118359737, "loss_cot": 0.47609415650367737, "loss_nocot": 0.3154330849647522, "step": 1785 }, { "epoch": 1.6644920782851818, "grad_norm": 0.6121183584669342, "learning_rate": 9.892992751121851e-06, "loss": 0.8647, "step": 1786 }, { "epoch": 1.6644920782851818, "loss_cot": 0.4926243722438812, "loss_nocot": 0.35881075263023376, "step": 1786 }, { "epoch": 1.6654240447343895, "grad_norm": 0.6190790428972174, "learning_rate": 9.886089057645842e-06, "loss": 0.8067, "step": 1787 }, { "epoch": 1.6654240447343895, "loss_cot": 0.4912736415863037, "loss_nocot": 0.37258851528167725, "step": 1787 }, { "epoch": 1.6663560111835976, "grad_norm": 0.6481539150250372, "learning_rate": 9.879185364169833e-06, "loss": 0.9025, "step": 1788 }, { "epoch": 1.6663560111835976, "loss_cot": 0.4874351918697357, "loss_nocot": 0.39738374948501587, "step": 1788 }, { "epoch": 1.6672879776328053, "grad_norm": 0.6250595285914621, "learning_rate": 9.872281670693822e-06, "loss": 0.865, "step": 1789 }, { "epoch": 1.6672879776328053, "loss_cot": 0.5550485849380493, "loss_nocot": 0.3688907325267792, "step": 1789 }, { "epoch": 1.6682199440820131, "grad_norm": 0.6347328876150226, "learning_rate": 9.865377977217812e-06, "loss": 0.8558, "step": 1790 }, { "epoch": 1.6682199440820131, "loss_cot": 0.5435519814491272, "loss_nocot": 0.413491427898407, "step": 1790 }, { "epoch": 1.669151910531221, "grad_norm": 0.627215315132677, "learning_rate": 9.858474283741803e-06, "loss": 0.8478, "step": 1791 }, { "epoch": 1.669151910531221, "loss_cot": 0.48190051317214966, "loss_nocot": 0.42624330520629883, "step": 1791 }, { "epoch": 1.6700838769804287, "grad_norm": 0.6267508893779251, "learning_rate": 9.851570590265794e-06, "loss": 0.8477, "step": 1792 }, { "epoch": 1.6700838769804287, "loss_cot": 0.5606746673583984, "loss_nocot": 0.33814847469329834, "step": 1792 }, { "epoch": 1.6710158434296365, "grad_norm": 0.6668150758066749, "learning_rate": 9.844666896789783e-06, "loss": 0.8376, "step": 1793 }, { "epoch": 1.6710158434296365, "loss_cot": 0.4963832199573517, "loss_nocot": 0.3236166834831238, "step": 1793 }, { "epoch": 1.6719478098788443, "grad_norm": 0.6091914998696648, "learning_rate": 9.837763203313774e-06, "loss": 0.8295, "step": 1794 }, { "epoch": 1.6719478098788443, "loss_cot": 0.4994649887084961, "loss_nocot": 0.2704545855522156, "step": 1794 }, { "epoch": 1.672879776328052, "grad_norm": 0.6193851316324531, "learning_rate": 9.830859509837763e-06, "loss": 0.8042, "step": 1795 }, { "epoch": 1.672879776328052, "loss_cot": 0.47939932346343994, "loss_nocot": 0.2768048048019409, "step": 1795 }, { "epoch": 1.6738117427772599, "grad_norm": 0.6038519372424328, "learning_rate": 9.823955816361753e-06, "loss": 0.8174, "step": 1796 }, { "epoch": 1.6738117427772599, "loss_cot": 0.48600631952285767, "loss_nocot": 0.5109339952468872, "step": 1796 }, { "epoch": 1.6747437092264679, "grad_norm": 0.6601588016319504, "learning_rate": 9.817052122885746e-06, "loss": 0.8706, "step": 1797 }, { "epoch": 1.6747437092264679, "loss_cot": 0.5204295516014099, "loss_nocot": 0.2870781719684601, "step": 1797 }, { "epoch": 1.6756756756756757, "grad_norm": 0.6355418040367059, "learning_rate": 9.810148429409735e-06, "loss": 0.8938, "step": 1798 }, { "epoch": 1.6756756756756757, "loss_cot": 0.4250098168849945, "loss_nocot": 0.3421754240989685, "step": 1798 }, { "epoch": 1.6766076421248837, "grad_norm": 0.6164344067353908, "learning_rate": 9.803244735933726e-06, "loss": 0.8221, "step": 1799 }, { "epoch": 1.6766076421248837, "loss_cot": 0.520286500453949, "loss_nocot": 0.40381333231925964, "step": 1799 }, { "epoch": 1.6775396085740915, "grad_norm": 0.6307073736694677, "learning_rate": 9.796341042457715e-06, "loss": 0.8469, "step": 1800 }, { "epoch": 1.6775396085740915, "loss_cot": 0.5515111684799194, "loss_nocot": 0.292427122592926, "step": 1800 }, { "epoch": 1.6784715750232992, "grad_norm": 0.62881065753235, "learning_rate": 9.789437348981705e-06, "loss": 0.8512, "step": 1801 }, { "epoch": 1.6784715750232992, "loss_cot": 0.4755861163139343, "loss_nocot": 0.2588130533695221, "step": 1801 }, { "epoch": 1.679403541472507, "grad_norm": 0.5619813347053167, "learning_rate": 9.782533655505696e-06, "loss": 0.7856, "step": 1802 }, { "epoch": 1.679403541472507, "loss_cot": 0.5833297967910767, "loss_nocot": 0.457576185464859, "step": 1802 }, { "epoch": 1.6803355079217148, "grad_norm": 0.6431287186153201, "learning_rate": 9.775629962029687e-06, "loss": 0.8943, "step": 1803 }, { "epoch": 1.6803355079217148, "loss_cot": 0.4422867000102997, "loss_nocot": 0.38079923391342163, "step": 1803 }, { "epoch": 1.6812674743709226, "grad_norm": 0.613274863293938, "learning_rate": 9.768726268553676e-06, "loss": 0.8157, "step": 1804 }, { "epoch": 1.6812674743709226, "loss_cot": 0.43187767267227173, "loss_nocot": 0.31934040784835815, "step": 1804 }, { "epoch": 1.6821994408201304, "grad_norm": 0.6043272984724387, "learning_rate": 9.761822575077667e-06, "loss": 0.8193, "step": 1805 }, { "epoch": 1.6821994408201304, "loss_cot": 0.4877026379108429, "loss_nocot": 0.3842540681362152, "step": 1805 }, { "epoch": 1.6831314072693382, "grad_norm": 0.6618575900380816, "learning_rate": 9.754918881601657e-06, "loss": 0.9074, "step": 1806 }, { "epoch": 1.6831314072693382, "loss_cot": 0.5131644606590271, "loss_nocot": 0.24496451020240784, "step": 1806 }, { "epoch": 1.684063373718546, "grad_norm": 0.6658860863384607, "learning_rate": 9.748015188125648e-06, "loss": 0.8707, "step": 1807 }, { "epoch": 1.684063373718546, "loss_cot": 0.5488492250442505, "loss_nocot": 0.4089408218860626, "step": 1807 }, { "epoch": 1.684995340167754, "grad_norm": 0.6406943412302574, "learning_rate": 9.741111494649639e-06, "loss": 0.8783, "step": 1808 }, { "epoch": 1.684995340167754, "loss_cot": 0.47417235374450684, "loss_nocot": 0.45936331152915955, "step": 1808 }, { "epoch": 1.6859273066169618, "grad_norm": 0.6416746683957032, "learning_rate": 9.734207801173628e-06, "loss": 0.8816, "step": 1809 }, { "epoch": 1.6859273066169618, "loss_cot": 0.4592587947845459, "loss_nocot": 0.37738969922065735, "step": 1809 }, { "epoch": 1.6868592730661698, "grad_norm": 0.6131994496878398, "learning_rate": 9.727304107697619e-06, "loss": 0.8498, "step": 1810 }, { "epoch": 1.6868592730661698, "loss_cot": 0.48528844118118286, "loss_nocot": 0.34106481075286865, "step": 1810 }, { "epoch": 1.6877912395153776, "grad_norm": 0.6474501511985762, "learning_rate": 9.72040041422161e-06, "loss": 0.8843, "step": 1811 }, { "epoch": 1.6877912395153776, "loss_cot": 0.451041579246521, "loss_nocot": 0.34862881898880005, "step": 1811 }, { "epoch": 1.6887232059645854, "grad_norm": 0.622054220941651, "learning_rate": 9.7134967207456e-06, "loss": 0.8148, "step": 1812 }, { "epoch": 1.6887232059645854, "loss_cot": 0.47781771421432495, "loss_nocot": 0.3390803337097168, "step": 1812 }, { "epoch": 1.6896551724137931, "grad_norm": 0.6127414606491745, "learning_rate": 9.70659302726959e-06, "loss": 0.8467, "step": 1813 }, { "epoch": 1.6896551724137931, "loss_cot": 0.5315871238708496, "loss_nocot": 0.2843374013900757, "step": 1813 }, { "epoch": 1.690587138863001, "grad_norm": 0.6063982471568913, "learning_rate": 9.69968933379358e-06, "loss": 0.793, "step": 1814 }, { "epoch": 1.690587138863001, "loss_cot": 0.4939311146736145, "loss_nocot": 0.4199727475643158, "step": 1814 }, { "epoch": 1.6915191053122087, "grad_norm": 0.685810244424568, "learning_rate": 9.69278564031757e-06, "loss": 0.8847, "step": 1815 }, { "epoch": 1.6915191053122087, "loss_cot": 0.503646194934845, "loss_nocot": 0.2669753432273865, "step": 1815 }, { "epoch": 1.6924510717614165, "grad_norm": 0.604238104302692, "learning_rate": 9.685881946841561e-06, "loss": 0.8416, "step": 1816 }, { "epoch": 1.6924510717614165, "loss_cot": 0.5274202823638916, "loss_nocot": 0.3919685184955597, "step": 1816 }, { "epoch": 1.6933830382106243, "grad_norm": 0.6250772550556475, "learning_rate": 9.678978253365552e-06, "loss": 0.859, "step": 1817 }, { "epoch": 1.6933830382106243, "loss_cot": 0.5347141027450562, "loss_nocot": 0.41565561294555664, "step": 1817 }, { "epoch": 1.694315004659832, "grad_norm": 0.613630715090565, "learning_rate": 9.672074559889541e-06, "loss": 0.8804, "step": 1818 }, { "epoch": 1.694315004659832, "loss_cot": 0.508823812007904, "loss_nocot": 0.35230115056037903, "step": 1818 }, { "epoch": 1.69524697110904, "grad_norm": 0.6352513442077717, "learning_rate": 9.665170866413532e-06, "loss": 0.8461, "step": 1819 }, { "epoch": 1.69524697110904, "loss_cot": 0.47683995962142944, "loss_nocot": 0.3829001784324646, "step": 1819 }, { "epoch": 1.696178937558248, "grad_norm": 0.6599866672671343, "learning_rate": 9.658267172937523e-06, "loss": 0.844, "step": 1820 }, { "epoch": 1.696178937558248, "loss_cot": 0.5187855958938599, "loss_nocot": 0.36566877365112305, "step": 1820 }, { "epoch": 1.6971109040074557, "grad_norm": 0.6325177503829696, "learning_rate": 9.651363479461513e-06, "loss": 0.8604, "step": 1821 }, { "epoch": 1.6971109040074557, "loss_cot": 0.458687961101532, "loss_nocot": 0.3280775845050812, "step": 1821 }, { "epoch": 1.6980428704566637, "grad_norm": 0.6491677079941123, "learning_rate": 9.644459785985502e-06, "loss": 0.8866, "step": 1822 }, { "epoch": 1.6980428704566637, "loss_cot": 0.4998032748699188, "loss_nocot": 0.3438255190849304, "step": 1822 }, { "epoch": 1.6989748369058715, "grad_norm": 0.6754254713973592, "learning_rate": 9.637556092509493e-06, "loss": 0.892, "step": 1823 }, { "epoch": 1.6989748369058715, "loss_cot": 0.4731868803501129, "loss_nocot": 0.4696166515350342, "step": 1823 }, { "epoch": 1.6999068033550793, "grad_norm": 0.6478351248470645, "learning_rate": 9.630652399033484e-06, "loss": 0.8755, "step": 1824 }, { "epoch": 1.6999068033550793, "loss_cot": 0.5026775002479553, "loss_nocot": 0.43185827136039734, "step": 1824 }, { "epoch": 1.700838769804287, "grad_norm": 0.5965576405856738, "learning_rate": 9.623748705557475e-06, "loss": 0.8302, "step": 1825 }, { "epoch": 1.700838769804287, "loss_cot": 0.46393147110939026, "loss_nocot": 0.5045245289802551, "step": 1825 }, { "epoch": 1.7017707362534948, "grad_norm": 0.6379984217630162, "learning_rate": 9.616845012081464e-06, "loss": 0.8719, "step": 1826 }, { "epoch": 1.7017707362534948, "loss_cot": 0.5426092147827148, "loss_nocot": 0.3040408492088318, "step": 1826 }, { "epoch": 1.7027027027027026, "grad_norm": 0.6606807715376687, "learning_rate": 9.609941318605454e-06, "loss": 0.9019, "step": 1827 }, { "epoch": 1.7027027027027026, "loss_cot": 0.49666598439216614, "loss_nocot": 0.34632688760757446, "step": 1827 }, { "epoch": 1.7036346691519104, "grad_norm": 0.6309363343206598, "learning_rate": 9.603037625129445e-06, "loss": 0.8193, "step": 1828 }, { "epoch": 1.7036346691519104, "loss_cot": 0.5413763523101807, "loss_nocot": 0.24978363513946533, "step": 1828 }, { "epoch": 1.7045666356011182, "grad_norm": 0.6475112178699043, "learning_rate": 9.596133931653436e-06, "loss": 0.8516, "step": 1829 }, { "epoch": 1.7045666356011182, "loss_cot": 0.541010856628418, "loss_nocot": 0.37165582180023193, "step": 1829 }, { "epoch": 1.7054986020503262, "grad_norm": 0.6226011162458721, "learning_rate": 9.589230238177427e-06, "loss": 0.8773, "step": 1830 }, { "epoch": 1.7054986020503262, "loss_cot": 0.4834240972995758, "loss_nocot": 0.3551456034183502, "step": 1830 }, { "epoch": 1.706430568499534, "grad_norm": 0.5685649393279997, "learning_rate": 9.582326544701416e-06, "loss": 0.7874, "step": 1831 }, { "epoch": 1.706430568499534, "loss_cot": 0.4639764428138733, "loss_nocot": 0.26302361488342285, "step": 1831 }, { "epoch": 1.7073625349487418, "grad_norm": 0.6478109222885319, "learning_rate": 9.575422851225406e-06, "loss": 0.8922, "step": 1832 }, { "epoch": 1.7073625349487418, "loss_cot": 0.5714231729507446, "loss_nocot": 0.31250137090682983, "step": 1832 }, { "epoch": 1.7082945013979498, "grad_norm": 0.6949293683659324, "learning_rate": 9.568519157749397e-06, "loss": 0.8858, "step": 1833 }, { "epoch": 1.7082945013979498, "loss_cot": 0.47313952445983887, "loss_nocot": 0.3126246929168701, "step": 1833 }, { "epoch": 1.7092264678471576, "grad_norm": 1.1563550910024516, "learning_rate": 9.561615464273388e-06, "loss": 0.8645, "step": 1834 }, { "epoch": 1.7092264678471576, "loss_cot": 0.5485520362854004, "loss_nocot": 0.29137593507766724, "step": 1834 }, { "epoch": 1.7101584342963654, "grad_norm": 0.5916724531700102, "learning_rate": 9.554711770797377e-06, "loss": 0.8484, "step": 1835 }, { "epoch": 1.7101584342963654, "loss_cot": 0.5306259989738464, "loss_nocot": 0.2827690541744232, "step": 1835 }, { "epoch": 1.7110904007455732, "grad_norm": 0.6566577057724182, "learning_rate": 9.547808077321368e-06, "loss": 0.8327, "step": 1836 }, { "epoch": 1.7110904007455732, "loss_cot": 0.5461187958717346, "loss_nocot": 0.4274751543998718, "step": 1836 }, { "epoch": 1.712022367194781, "grad_norm": 0.6635315432188696, "learning_rate": 9.540904383845358e-06, "loss": 0.9353, "step": 1837 }, { "epoch": 1.712022367194781, "loss_cot": 0.4666977524757385, "loss_nocot": 0.35490068793296814, "step": 1837 }, { "epoch": 1.7129543336439887, "grad_norm": 0.6286073755360834, "learning_rate": 9.534000690369349e-06, "loss": 0.8121, "step": 1838 }, { "epoch": 1.7129543336439887, "loss_cot": 0.48349860310554504, "loss_nocot": 0.29369768500328064, "step": 1838 }, { "epoch": 1.7138863000931965, "grad_norm": 0.6248315798697799, "learning_rate": 9.52709699689334e-06, "loss": 0.8416, "step": 1839 }, { "epoch": 1.7138863000931965, "loss_cot": 0.5815779566764832, "loss_nocot": 0.3043854534626007, "step": 1839 }, { "epoch": 1.7148182665424043, "grad_norm": 0.6193247016495194, "learning_rate": 9.520193303417329e-06, "loss": 0.8561, "step": 1840 }, { "epoch": 1.7148182665424043, "loss_cot": 0.5569974184036255, "loss_nocot": 0.46619248390197754, "step": 1840 }, { "epoch": 1.7157502329916123, "grad_norm": 0.7097431292309907, "learning_rate": 9.51328960994132e-06, "loss": 0.9437, "step": 1841 }, { "epoch": 1.7157502329916123, "loss_cot": 0.5654630064964294, "loss_nocot": 0.3290860056877136, "step": 1841 }, { "epoch": 1.7166821994408201, "grad_norm": 0.6599953824441709, "learning_rate": 9.50638591646531e-06, "loss": 0.8749, "step": 1842 }, { "epoch": 1.7166821994408201, "loss_cot": 0.49255022406578064, "loss_nocot": 0.2346706986427307, "step": 1842 }, { "epoch": 1.717614165890028, "grad_norm": 0.6453231543765833, "learning_rate": 9.499482222989301e-06, "loss": 0.8913, "step": 1843 }, { "epoch": 1.717614165890028, "loss_cot": 0.4887968599796295, "loss_nocot": 0.3070695400238037, "step": 1843 }, { "epoch": 1.718546132339236, "grad_norm": 0.6533025422849192, "learning_rate": 9.49257852951329e-06, "loss": 0.8486, "step": 1844 }, { "epoch": 1.718546132339236, "loss_cot": 0.49027031660079956, "loss_nocot": 0.3560435175895691, "step": 1844 }, { "epoch": 1.7194780987884437, "grad_norm": 0.6696532138131376, "learning_rate": 9.48567483603728e-06, "loss": 0.8747, "step": 1845 }, { "epoch": 1.7194780987884437, "loss_cot": 0.544359564781189, "loss_nocot": 0.3253358006477356, "step": 1845 }, { "epoch": 1.7204100652376515, "grad_norm": 0.6487881473752343, "learning_rate": 9.47877114256127e-06, "loss": 0.9231, "step": 1846 }, { "epoch": 1.7204100652376515, "loss_cot": 0.548730731010437, "loss_nocot": 0.3585537075996399, "step": 1846 }, { "epoch": 1.7213420316868593, "grad_norm": 0.6319529340628608, "learning_rate": 9.47186744908526e-06, "loss": 0.8454, "step": 1847 }, { "epoch": 1.7213420316868593, "loss_cot": 0.4322194457054138, "loss_nocot": 0.3427288830280304, "step": 1847 }, { "epoch": 1.722273998136067, "grad_norm": 0.6329878381167394, "learning_rate": 9.464963755609253e-06, "loss": 0.8235, "step": 1848 }, { "epoch": 1.722273998136067, "loss_cot": 0.4838959276676178, "loss_nocot": 0.34897297620773315, "step": 1848 }, { "epoch": 1.7232059645852749, "grad_norm": 0.6516815742851988, "learning_rate": 9.458060062133242e-06, "loss": 0.8635, "step": 1849 }, { "epoch": 1.7232059645852749, "loss_cot": 0.5399793386459351, "loss_nocot": 0.3518793284893036, "step": 1849 }, { "epoch": 1.7241379310344827, "grad_norm": 0.619026996077567, "learning_rate": 9.451156368657233e-06, "loss": 0.8532, "step": 1850 }, { "epoch": 1.7241379310344827, "loss_cot": 0.5024577379226685, "loss_nocot": 0.38766583800315857, "step": 1850 }, { "epoch": 1.7250698974836904, "grad_norm": 0.6831868189915751, "learning_rate": 9.444252675181222e-06, "loss": 0.8591, "step": 1851 }, { "epoch": 1.7250698974836904, "loss_cot": 0.5488886833190918, "loss_nocot": 0.4502057433128357, "step": 1851 }, { "epoch": 1.7260018639328985, "grad_norm": 0.6760788937384968, "learning_rate": 9.437348981705212e-06, "loss": 0.9338, "step": 1852 }, { "epoch": 1.7260018639328985, "loss_cot": 0.5453476309776306, "loss_nocot": 0.27566614747047424, "step": 1852 }, { "epoch": 1.7269338303821062, "grad_norm": 0.6152061555165176, "learning_rate": 9.430445288229203e-06, "loss": 0.8254, "step": 1853 }, { "epoch": 1.7269338303821062, "loss_cot": 0.4888828694820404, "loss_nocot": 0.3836287260055542, "step": 1853 }, { "epoch": 1.727865796831314, "grad_norm": 0.6323589399579712, "learning_rate": 9.423541594753194e-06, "loss": 0.829, "step": 1854 }, { "epoch": 1.727865796831314, "loss_cot": 0.45671170949935913, "loss_nocot": 0.3331918716430664, "step": 1854 }, { "epoch": 1.728797763280522, "grad_norm": 0.632063583016332, "learning_rate": 9.416637901277183e-06, "loss": 0.841, "step": 1855 }, { "epoch": 1.728797763280522, "loss_cot": 0.5000285506248474, "loss_nocot": 0.490761399269104, "step": 1855 }, { "epoch": 1.7297297297297298, "grad_norm": 0.6531630217728361, "learning_rate": 9.409734207801174e-06, "loss": 0.8649, "step": 1856 }, { "epoch": 1.7297297297297298, "loss_cot": 0.5055080056190491, "loss_nocot": 0.44397351145744324, "step": 1856 }, { "epoch": 1.7306616961789376, "grad_norm": 29.884611197503986, "learning_rate": 9.402830514325164e-06, "loss": 1.0947, "step": 1857 }, { "epoch": 1.7306616961789376, "loss_cot": 0.4865955710411072, "loss_nocot": 0.27896106243133545, "step": 1857 }, { "epoch": 1.7315936626281454, "grad_norm": 0.5969309618704539, "learning_rate": 9.395926820849155e-06, "loss": 0.8218, "step": 1858 }, { "epoch": 1.7315936626281454, "loss_cot": 0.4805174767971039, "loss_nocot": 0.22559458017349243, "step": 1858 }, { "epoch": 1.7325256290773532, "grad_norm": 0.646294260849829, "learning_rate": 9.389023127373146e-06, "loss": 0.8275, "step": 1859 }, { "epoch": 1.7325256290773532, "loss_cot": 0.43788567185401917, "loss_nocot": 0.34841784834861755, "step": 1859 }, { "epoch": 1.733457595526561, "grad_norm": 0.6139721939700311, "learning_rate": 9.382119433897135e-06, "loss": 0.8435, "step": 1860 }, { "epoch": 1.733457595526561, "loss_cot": 0.487164169549942, "loss_nocot": 0.33727502822875977, "step": 1860 }, { "epoch": 1.7343895619757688, "grad_norm": 0.6725855246565545, "learning_rate": 9.375215740421126e-06, "loss": 0.8602, "step": 1861 }, { "epoch": 1.7343895619757688, "loss_cot": 0.46811559796333313, "loss_nocot": 0.5138239860534668, "step": 1861 }, { "epoch": 1.7353215284249766, "grad_norm": 0.6525205253395655, "learning_rate": 9.368312046945116e-06, "loss": 0.8315, "step": 1862 }, { "epoch": 1.7353215284249766, "loss_cot": 0.483162522315979, "loss_nocot": 0.29243630170822144, "step": 1862 }, { "epoch": 1.7362534948741846, "grad_norm": 0.5970948555674881, "learning_rate": 9.361408353469107e-06, "loss": 0.8148, "step": 1863 }, { "epoch": 1.7362534948741846, "loss_cot": 0.4465581774711609, "loss_nocot": 0.437447190284729, "step": 1863 }, { "epoch": 1.7371854613233924, "grad_norm": 0.65299051450606, "learning_rate": 9.354504659993096e-06, "loss": 0.9111, "step": 1864 }, { "epoch": 1.7371854613233924, "loss_cot": 0.499201238155365, "loss_nocot": 0.42199277877807617, "step": 1864 }, { "epoch": 1.7381174277726001, "grad_norm": 0.6071361401078598, "learning_rate": 9.347600966517087e-06, "loss": 0.8477, "step": 1865 }, { "epoch": 1.7381174277726001, "loss_cot": 0.5064412355422974, "loss_nocot": 0.38712477684020996, "step": 1865 }, { "epoch": 1.7390493942218082, "grad_norm": 0.6550072108095498, "learning_rate": 9.340697273041078e-06, "loss": 0.8715, "step": 1866 }, { "epoch": 1.7390493942218082, "loss_cot": 0.4530993700027466, "loss_nocot": 0.34749728441238403, "step": 1866 }, { "epoch": 1.739981360671016, "grad_norm": 0.6362043131657718, "learning_rate": 9.333793579565068e-06, "loss": 0.8694, "step": 1867 }, { "epoch": 1.739981360671016, "loss_cot": 0.547781765460968, "loss_nocot": 0.2945132851600647, "step": 1867 }, { "epoch": 1.7409133271202237, "grad_norm": 0.6104456379295304, "learning_rate": 9.326889886089059e-06, "loss": 0.8359, "step": 1868 }, { "epoch": 1.7409133271202237, "loss_cot": 0.517152726650238, "loss_nocot": 0.37430399656295776, "step": 1868 }, { "epoch": 1.7418452935694315, "grad_norm": 0.6442071181994808, "learning_rate": 9.319986192613048e-06, "loss": 0.8387, "step": 1869 }, { "epoch": 1.7418452935694315, "loss_cot": 0.4907989799976349, "loss_nocot": 0.3999594449996948, "step": 1869 }, { "epoch": 1.7427772600186393, "grad_norm": 0.6641575449421521, "learning_rate": 9.313082499137039e-06, "loss": 0.904, "step": 1870 }, { "epoch": 1.7427772600186393, "loss_cot": 0.537218451499939, "loss_nocot": 0.40476101636886597, "step": 1870 }, { "epoch": 1.743709226467847, "grad_norm": 0.6666000574991785, "learning_rate": 9.30617880566103e-06, "loss": 0.9283, "step": 1871 }, { "epoch": 1.743709226467847, "loss_cot": 0.5178643465042114, "loss_nocot": 0.3265748620033264, "step": 1871 }, { "epoch": 1.7446411929170549, "grad_norm": 0.6371870257946267, "learning_rate": 9.29927511218502e-06, "loss": 0.8562, "step": 1872 }, { "epoch": 1.7446411929170549, "loss_cot": 0.500652551651001, "loss_nocot": 0.3103841543197632, "step": 1872 }, { "epoch": 1.7455731593662627, "grad_norm": 0.6421749741704987, "learning_rate": 9.29237141870901e-06, "loss": 0.8425, "step": 1873 }, { "epoch": 1.7455731593662627, "loss_cot": 0.547286331653595, "loss_nocot": 0.4228558838367462, "step": 1873 }, { "epoch": 1.7465051258154707, "grad_norm": 0.6754280202804632, "learning_rate": 9.285467725233e-06, "loss": 0.8498, "step": 1874 }, { "epoch": 1.7465051258154707, "loss_cot": 0.4864629805088043, "loss_nocot": 0.3482094407081604, "step": 1874 }, { "epoch": 1.7474370922646785, "grad_norm": 0.6216325998123826, "learning_rate": 9.278564031756991e-06, "loss": 0.8412, "step": 1875 }, { "epoch": 1.7474370922646785, "loss_cot": 0.4698575437068939, "loss_nocot": 0.3445858359336853, "step": 1875 }, { "epoch": 1.7483690587138863, "grad_norm": 0.7047127357355644, "learning_rate": 9.271660338280982e-06, "loss": 0.9493, "step": 1876 }, { "epoch": 1.7483690587138863, "loss_cot": 0.4371516704559326, "loss_nocot": 0.43898606300354004, "step": 1876 }, { "epoch": 1.7493010251630943, "grad_norm": 0.6233176928406576, "learning_rate": 9.264756644804972e-06, "loss": 0.8507, "step": 1877 }, { "epoch": 1.7493010251630943, "loss_cot": 0.4918961524963379, "loss_nocot": 0.2768062651157379, "step": 1877 }, { "epoch": 1.750232991612302, "grad_norm": 0.6685579138071657, "learning_rate": 9.257852951328961e-06, "loss": 0.8078, "step": 1878 }, { "epoch": 1.750232991612302, "loss_cot": 0.55003821849823, "loss_nocot": 0.32430946826934814, "step": 1878 }, { "epoch": 1.7511649580615098, "grad_norm": 0.5926776896290733, "learning_rate": 9.250949257852952e-06, "loss": 0.837, "step": 1879 }, { "epoch": 1.7511649580615098, "loss_cot": 0.4833371639251709, "loss_nocot": 0.3311230540275574, "step": 1879 }, { "epoch": 1.7520969245107176, "grad_norm": 0.5953879201395383, "learning_rate": 9.244045564376943e-06, "loss": 0.8627, "step": 1880 }, { "epoch": 1.7520969245107176, "loss_cot": 0.5660068988800049, "loss_nocot": 0.2926253378391266, "step": 1880 }, { "epoch": 1.7530288909599254, "grad_norm": 0.6357177862710739, "learning_rate": 9.237141870900934e-06, "loss": 0.8766, "step": 1881 }, { "epoch": 1.7530288909599254, "loss_cot": 0.4947383999824524, "loss_nocot": 0.30557528138160706, "step": 1881 }, { "epoch": 1.7539608574091332, "grad_norm": 0.6011003676334711, "learning_rate": 9.230238177424923e-06, "loss": 0.8129, "step": 1882 }, { "epoch": 1.7539608574091332, "loss_cot": 0.5403282046318054, "loss_nocot": 0.33750078082084656, "step": 1882 }, { "epoch": 1.754892823858341, "grad_norm": 0.6721697473502896, "learning_rate": 9.223334483948913e-06, "loss": 0.8985, "step": 1883 }, { "epoch": 1.754892823858341, "loss_cot": 0.4877316951751709, "loss_nocot": 0.3711652159690857, "step": 1883 }, { "epoch": 1.7558247903075488, "grad_norm": 0.6658219929166, "learning_rate": 9.216430790472904e-06, "loss": 0.9036, "step": 1884 }, { "epoch": 1.7558247903075488, "loss_cot": 0.4825432300567627, "loss_nocot": 0.5128358602523804, "step": 1884 }, { "epoch": 1.7567567567567568, "grad_norm": 0.651691019373018, "learning_rate": 9.209527096996895e-06, "loss": 0.9224, "step": 1885 }, { "epoch": 1.7567567567567568, "loss_cot": 0.5701940655708313, "loss_nocot": 0.501583993434906, "step": 1885 }, { "epoch": 1.7576887232059646, "grad_norm": 0.6422325300448439, "learning_rate": 9.202623403520884e-06, "loss": 0.8584, "step": 1886 }, { "epoch": 1.7576887232059646, "loss_cot": 0.5365310907363892, "loss_nocot": 0.441432386636734, "step": 1886 }, { "epoch": 1.7586206896551724, "grad_norm": 0.6438844355356995, "learning_rate": 9.195719710044875e-06, "loss": 0.8966, "step": 1887 }, { "epoch": 1.7586206896551724, "loss_cot": 0.4608169198036194, "loss_nocot": 0.46057337522506714, "step": 1887 }, { "epoch": 1.7595526561043804, "grad_norm": 0.6704862081057579, "learning_rate": 9.188816016568865e-06, "loss": 0.9063, "step": 1888 }, { "epoch": 1.7595526561043804, "loss_cot": 0.4143863618373871, "loss_nocot": 0.33598634600639343, "step": 1888 }, { "epoch": 1.7604846225535882, "grad_norm": 0.6606271262040155, "learning_rate": 9.181912323092856e-06, "loss": 0.8684, "step": 1889 }, { "epoch": 1.7604846225535882, "loss_cot": 0.5131177306175232, "loss_nocot": 0.3251646161079407, "step": 1889 }, { "epoch": 1.761416589002796, "grad_norm": 0.6898935940023315, "learning_rate": 9.175008629616847e-06, "loss": 0.8876, "step": 1890 }, { "epoch": 1.761416589002796, "loss_cot": 0.4567452073097229, "loss_nocot": 0.35789740085601807, "step": 1890 }, { "epoch": 1.7623485554520038, "grad_norm": 0.6285003134606736, "learning_rate": 9.168104936140836e-06, "loss": 0.8481, "step": 1891 }, { "epoch": 1.7623485554520038, "loss_cot": 0.4996051788330078, "loss_nocot": 0.4656461179256439, "step": 1891 }, { "epoch": 1.7632805219012115, "grad_norm": 0.6502211530525166, "learning_rate": 9.161201242664827e-06, "loss": 0.8984, "step": 1892 }, { "epoch": 1.7632805219012115, "loss_cot": 0.4809637665748596, "loss_nocot": 0.27232417464256287, "step": 1892 }, { "epoch": 1.7642124883504193, "grad_norm": 0.6056899157119192, "learning_rate": 9.154297549188816e-06, "loss": 0.8235, "step": 1893 }, { "epoch": 1.7642124883504193, "loss_cot": 0.44702768325805664, "loss_nocot": 0.28503966331481934, "step": 1893 }, { "epoch": 1.7651444547996271, "grad_norm": 0.6528038901571247, "learning_rate": 9.147393855712808e-06, "loss": 0.8557, "step": 1894 }, { "epoch": 1.7651444547996271, "loss_cot": 0.5248178839683533, "loss_nocot": 0.46857523918151855, "step": 1894 }, { "epoch": 1.766076421248835, "grad_norm": 0.677308796784325, "learning_rate": 9.140490162236797e-06, "loss": 0.9326, "step": 1895 }, { "epoch": 1.766076421248835, "loss_cot": 0.42700862884521484, "loss_nocot": 0.26889568567276, "step": 1895 }, { "epoch": 1.767008387698043, "grad_norm": 0.682504235655883, "learning_rate": 9.133586468760788e-06, "loss": 0.904, "step": 1896 }, { "epoch": 1.767008387698043, "loss_cot": 0.41610920429229736, "loss_nocot": 0.2758018374443054, "step": 1896 }, { "epoch": 1.7679403541472507, "grad_norm": 0.6274316299809646, "learning_rate": 9.126682775284779e-06, "loss": 0.8425, "step": 1897 }, { "epoch": 1.7679403541472507, "loss_cot": 0.5366356372833252, "loss_nocot": 0.31134575605392456, "step": 1897 }, { "epoch": 1.7688723205964585, "grad_norm": 0.6059258454907189, "learning_rate": 9.119779081808768e-06, "loss": 0.8302, "step": 1898 }, { "epoch": 1.7688723205964585, "loss_cot": 0.4522448480129242, "loss_nocot": 0.40160176157951355, "step": 1898 }, { "epoch": 1.7698042870456665, "grad_norm": 0.6427170840198843, "learning_rate": 9.11287538833276e-06, "loss": 0.8444, "step": 1899 }, { "epoch": 1.7698042870456665, "loss_cot": 0.47178661823272705, "loss_nocot": 0.24942687153816223, "step": 1899 }, { "epoch": 1.7707362534948743, "grad_norm": 0.6175090855689671, "learning_rate": 9.105971694856749e-06, "loss": 0.8235, "step": 1900 }, { "epoch": 1.7707362534948743, "loss_cot": 0.4731425940990448, "loss_nocot": 0.29653221368789673, "step": 1900 }, { "epoch": 1.771668219944082, "grad_norm": 0.5757047307395692, "learning_rate": 9.09906800138074e-06, "loss": 0.7986, "step": 1901 }, { "epoch": 1.771668219944082, "loss_cot": 0.4749593138694763, "loss_nocot": 0.5091695785522461, "step": 1901 }, { "epoch": 1.7726001863932899, "grad_norm": 0.7034264726553098, "learning_rate": 9.092164307904729e-06, "loss": 0.8936, "step": 1902 }, { "epoch": 1.7726001863932899, "loss_cot": 0.45021066069602966, "loss_nocot": 0.2677255868911743, "step": 1902 }, { "epoch": 1.7735321528424977, "grad_norm": 0.614907059376139, "learning_rate": 9.08526061442872e-06, "loss": 0.7801, "step": 1903 }, { "epoch": 1.7735321528424977, "loss_cot": 0.531499981880188, "loss_nocot": 0.3765038251876831, "step": 1903 }, { "epoch": 1.7744641192917054, "grad_norm": 0.6141495519069157, "learning_rate": 9.07835692095271e-06, "loss": 0.8623, "step": 1904 }, { "epoch": 1.7744641192917054, "loss_cot": 0.47492390871047974, "loss_nocot": 0.4094277322292328, "step": 1904 }, { "epoch": 1.7753960857409132, "grad_norm": 0.6830138511314815, "learning_rate": 9.071453227476701e-06, "loss": 0.9106, "step": 1905 }, { "epoch": 1.7753960857409132, "loss_cot": 0.507995069026947, "loss_nocot": 0.5029286742210388, "step": 1905 }, { "epoch": 1.776328052190121, "grad_norm": 0.7050143046144011, "learning_rate": 9.06454953400069e-06, "loss": 0.9292, "step": 1906 }, { "epoch": 1.776328052190121, "loss_cot": 0.5037256479263306, "loss_nocot": 0.2661689519882202, "step": 1906 }, { "epoch": 1.777260018639329, "grad_norm": 0.6488139795780725, "learning_rate": 9.05764584052468e-06, "loss": 0.8864, "step": 1907 }, { "epoch": 1.777260018639329, "loss_cot": 0.4919053912162781, "loss_nocot": 0.3487585783004761, "step": 1907 }, { "epoch": 1.7781919850885368, "grad_norm": 0.637392988310117, "learning_rate": 9.050742147048671e-06, "loss": 0.8527, "step": 1908 }, { "epoch": 1.7781919850885368, "loss_cot": 0.5176666378974915, "loss_nocot": 0.31523576378822327, "step": 1908 }, { "epoch": 1.7791239515377446, "grad_norm": 0.8036717174067327, "learning_rate": 9.043838453572662e-06, "loss": 0.8288, "step": 1909 }, { "epoch": 1.7791239515377446, "loss_cot": 0.5098395943641663, "loss_nocot": 0.2947964668273926, "step": 1909 }, { "epoch": 1.7800559179869526, "grad_norm": 0.6228584432336596, "learning_rate": 9.036934760096653e-06, "loss": 0.8663, "step": 1910 }, { "epoch": 1.7800559179869526, "loss_cot": 0.5377389788627625, "loss_nocot": 0.22616617381572723, "step": 1910 }, { "epoch": 1.7809878844361604, "grad_norm": 0.5942680610606311, "learning_rate": 9.030031066620642e-06, "loss": 0.7995, "step": 1911 }, { "epoch": 1.7809878844361604, "loss_cot": 0.4497060477733612, "loss_nocot": 0.39905816316604614, "step": 1911 }, { "epoch": 1.7819198508853682, "grad_norm": 0.6329853617547908, "learning_rate": 9.023127373144633e-06, "loss": 0.8171, "step": 1912 }, { "epoch": 1.7819198508853682, "loss_cot": 0.5100679993629456, "loss_nocot": 0.31320714950561523, "step": 1912 }, { "epoch": 1.782851817334576, "grad_norm": 0.5803330390827692, "learning_rate": 9.016223679668623e-06, "loss": 0.7951, "step": 1913 }, { "epoch": 1.782851817334576, "loss_cot": 0.5463463068008423, "loss_nocot": 0.31221073865890503, "step": 1913 }, { "epoch": 1.7837837837837838, "grad_norm": 0.6253994816060746, "learning_rate": 9.009319986192614e-06, "loss": 0.8787, "step": 1914 }, { "epoch": 1.7837837837837838, "loss_cot": 0.5106476545333862, "loss_nocot": 0.339901864528656, "step": 1914 }, { "epoch": 1.7847157502329916, "grad_norm": 0.5720779230190558, "learning_rate": 9.002416292716603e-06, "loss": 0.759, "step": 1915 }, { "epoch": 1.7847157502329916, "loss_cot": 0.5134953856468201, "loss_nocot": 0.2838011384010315, "step": 1915 }, { "epoch": 1.7856477166821993, "grad_norm": 0.5811891699683353, "learning_rate": 8.995512599240594e-06, "loss": 0.8053, "step": 1916 }, { "epoch": 1.7856477166821993, "loss_cot": 0.5317533016204834, "loss_nocot": 0.28183913230895996, "step": 1916 }, { "epoch": 1.7865796831314071, "grad_norm": 0.5921350366679812, "learning_rate": 8.988608905764585e-06, "loss": 0.8102, "step": 1917 }, { "epoch": 1.7865796831314071, "loss_cot": 0.5434988737106323, "loss_nocot": 0.2939693331718445, "step": 1917 }, { "epoch": 1.7875116495806151, "grad_norm": 0.6101677657931166, "learning_rate": 8.981705212288575e-06, "loss": 0.8332, "step": 1918 }, { "epoch": 1.7875116495806151, "loss_cot": 0.5053204298019409, "loss_nocot": 0.30334725975990295, "step": 1918 }, { "epoch": 1.788443616029823, "grad_norm": 0.593911222356254, "learning_rate": 8.974801518812566e-06, "loss": 0.7863, "step": 1919 }, { "epoch": 1.788443616029823, "loss_cot": 0.4996594786643982, "loss_nocot": 0.40764671564102173, "step": 1919 }, { "epoch": 1.7893755824790307, "grad_norm": 0.6455494424599585, "learning_rate": 8.967897825336555e-06, "loss": 0.8924, "step": 1920 }, { "epoch": 1.7893755824790307, "loss_cot": 0.5003921389579773, "loss_nocot": 0.32494455575942993, "step": 1920 }, { "epoch": 1.7903075489282387, "grad_norm": 0.6237578282648825, "learning_rate": 8.960994131860546e-06, "loss": 0.8534, "step": 1921 }, { "epoch": 1.7903075489282387, "loss_cot": 0.4533507227897644, "loss_nocot": 0.34128451347351074, "step": 1921 }, { "epoch": 1.7912395153774465, "grad_norm": 0.6066157099945575, "learning_rate": 8.954090438384537e-06, "loss": 0.8181, "step": 1922 }, { "epoch": 1.7912395153774465, "loss_cot": 0.499899685382843, "loss_nocot": 0.28330379724502563, "step": 1922 }, { "epoch": 1.7921714818266543, "grad_norm": 0.6267955204586094, "learning_rate": 8.947186744908527e-06, "loss": 0.8599, "step": 1923 }, { "epoch": 1.7921714818266543, "loss_cot": 0.4491257667541504, "loss_nocot": 0.28499895334243774, "step": 1923 }, { "epoch": 1.793103448275862, "grad_norm": 0.6242369389663338, "learning_rate": 8.940283051432516e-06, "loss": 0.8359, "step": 1924 }, { "epoch": 1.793103448275862, "loss_cot": 0.4639565646648407, "loss_nocot": 0.3513292670249939, "step": 1924 }, { "epoch": 1.7940354147250699, "grad_norm": 0.6823473019326218, "learning_rate": 8.933379357956507e-06, "loss": 0.8657, "step": 1925 }, { "epoch": 1.7940354147250699, "loss_cot": 0.49430570006370544, "loss_nocot": 0.3189905285835266, "step": 1925 }, { "epoch": 1.7949673811742777, "grad_norm": 0.6500839136906355, "learning_rate": 8.926475664480498e-06, "loss": 0.8552, "step": 1926 }, { "epoch": 1.7949673811742777, "loss_cot": 0.4865546226501465, "loss_nocot": 0.31712156534194946, "step": 1926 }, { "epoch": 1.7958993476234855, "grad_norm": 0.5783361885936706, "learning_rate": 8.919571971004489e-06, "loss": 0.778, "step": 1927 }, { "epoch": 1.7958993476234855, "loss_cot": 0.4924514591693878, "loss_nocot": 0.38147473335266113, "step": 1927 }, { "epoch": 1.7968313140726933, "grad_norm": 0.7591051683171969, "learning_rate": 8.91266827752848e-06, "loss": 0.9819, "step": 1928 }, { "epoch": 1.7968313140726933, "loss_cot": 0.4129188656806946, "loss_nocot": 0.28373152017593384, "step": 1928 }, { "epoch": 1.7977632805219013, "grad_norm": 0.6631109727247612, "learning_rate": 8.905764584052468e-06, "loss": 0.9016, "step": 1929 }, { "epoch": 1.7977632805219013, "loss_cot": 0.5682408213615417, "loss_nocot": 0.2951918840408325, "step": 1929 }, { "epoch": 1.798695246971109, "grad_norm": 0.6006261323164674, "learning_rate": 8.898860890576459e-06, "loss": 0.8123, "step": 1930 }, { "epoch": 1.798695246971109, "loss_cot": 0.5047540664672852, "loss_nocot": 0.3691943883895874, "step": 1930 }, { "epoch": 1.7996272134203168, "grad_norm": 0.6412139199886207, "learning_rate": 8.89195719710045e-06, "loss": 0.8739, "step": 1931 }, { "epoch": 1.7996272134203168, "loss_cot": 0.49185627698898315, "loss_nocot": 0.24459469318389893, "step": 1931 }, { "epoch": 1.8005591798695249, "grad_norm": 0.6391104606147889, "learning_rate": 8.88505350362444e-06, "loss": 0.8667, "step": 1932 }, { "epoch": 1.8005591798695249, "loss_cot": 0.48378145694732666, "loss_nocot": 0.3945789933204651, "step": 1932 }, { "epoch": 1.8014911463187326, "grad_norm": 0.6429900214486169, "learning_rate": 8.87814981014843e-06, "loss": 0.8297, "step": 1933 }, { "epoch": 1.8014911463187326, "loss_cot": 0.45182377099990845, "loss_nocot": 0.32819050550460815, "step": 1933 }, { "epoch": 1.8024231127679404, "grad_norm": 0.5829405412669787, "learning_rate": 8.87124611667242e-06, "loss": 0.7983, "step": 1934 }, { "epoch": 1.8024231127679404, "loss_cot": 0.5685917735099792, "loss_nocot": 0.30467456579208374, "step": 1934 }, { "epoch": 1.8033550792171482, "grad_norm": 0.6410253241167324, "learning_rate": 8.864342423196411e-06, "loss": 0.8676, "step": 1935 }, { "epoch": 1.8033550792171482, "loss_cot": 0.5483964681625366, "loss_nocot": 0.4412686824798584, "step": 1935 }, { "epoch": 1.804287045666356, "grad_norm": 0.630195138575236, "learning_rate": 8.857438729720402e-06, "loss": 0.882, "step": 1936 }, { "epoch": 1.804287045666356, "loss_cot": 0.5473320484161377, "loss_nocot": 0.26340851187705994, "step": 1936 }, { "epoch": 1.8052190121155638, "grad_norm": 0.5763895574413594, "learning_rate": 8.850535036244391e-06, "loss": 0.785, "step": 1937 }, { "epoch": 1.8052190121155638, "loss_cot": 0.44016313552856445, "loss_nocot": 0.3968822658061981, "step": 1937 }, { "epoch": 1.8061509785647716, "grad_norm": 0.6093338627227182, "learning_rate": 8.843631342768382e-06, "loss": 0.8347, "step": 1938 }, { "epoch": 1.8061509785647716, "loss_cot": 0.5035642385482788, "loss_nocot": 0.32195496559143066, "step": 1938 }, { "epoch": 1.8070829450139794, "grad_norm": 0.6200044026437779, "learning_rate": 8.836727649292372e-06, "loss": 0.8327, "step": 1939 }, { "epoch": 1.8070829450139794, "loss_cot": 0.49087849259376526, "loss_nocot": 0.2940055727958679, "step": 1939 }, { "epoch": 1.8080149114631874, "grad_norm": 0.59319935494536, "learning_rate": 8.829823955816363e-06, "loss": 0.816, "step": 1940 }, { "epoch": 1.8080149114631874, "loss_cot": 0.4994451105594635, "loss_nocot": 0.26217588782310486, "step": 1940 }, { "epoch": 1.8089468779123952, "grad_norm": 0.5858913483997454, "learning_rate": 8.822920262340354e-06, "loss": 0.8153, "step": 1941 }, { "epoch": 1.8089468779123952, "loss_cot": 0.5558319091796875, "loss_nocot": 0.31586501002311707, "step": 1941 }, { "epoch": 1.809878844361603, "grad_norm": 0.6188307393258042, "learning_rate": 8.816016568864343e-06, "loss": 0.8488, "step": 1942 }, { "epoch": 1.809878844361603, "loss_cot": 0.46273985505104065, "loss_nocot": 0.31562235951423645, "step": 1942 }, { "epoch": 1.810810810810811, "grad_norm": 0.6208745979874076, "learning_rate": 8.809112875388334e-06, "loss": 0.8661, "step": 1943 }, { "epoch": 1.810810810810811, "loss_cot": 0.5243733525276184, "loss_nocot": 0.4110437333583832, "step": 1943 }, { "epoch": 1.8117427772600188, "grad_norm": 0.6749694656165631, "learning_rate": 8.802209181912323e-06, "loss": 0.9234, "step": 1944 }, { "epoch": 1.8117427772600188, "loss_cot": 0.5524942874908447, "loss_nocot": 0.26949769258499146, "step": 1944 }, { "epoch": 1.8126747437092265, "grad_norm": 0.5798953033610298, "learning_rate": 8.795305488436315e-06, "loss": 0.8096, "step": 1945 }, { "epoch": 1.8126747437092265, "loss_cot": 0.5009356737136841, "loss_nocot": 0.30688172578811646, "step": 1945 }, { "epoch": 1.8136067101584343, "grad_norm": 0.6489964413844436, "learning_rate": 8.788401794960304e-06, "loss": 0.8694, "step": 1946 }, { "epoch": 1.8136067101584343, "loss_cot": 0.4508588910102844, "loss_nocot": 0.306732177734375, "step": 1946 }, { "epoch": 1.8145386766076421, "grad_norm": 0.6045663377061963, "learning_rate": 8.781498101484295e-06, "loss": 0.8043, "step": 1947 }, { "epoch": 1.8145386766076421, "loss_cot": 0.47769057750701904, "loss_nocot": 0.3906221091747284, "step": 1947 }, { "epoch": 1.81547064305685, "grad_norm": 0.6665191001980544, "learning_rate": 8.774594408008286e-06, "loss": 0.8363, "step": 1948 }, { "epoch": 1.81547064305685, "loss_cot": 0.48179808259010315, "loss_nocot": 0.23383836448192596, "step": 1948 }, { "epoch": 1.8164026095060577, "grad_norm": 4.29323059720035, "learning_rate": 8.767690714532275e-06, "loss": 0.834, "step": 1949 }, { "epoch": 1.8164026095060577, "loss_cot": 0.49642279744148254, "loss_nocot": 0.4167264997959137, "step": 1949 }, { "epoch": 1.8173345759552655, "grad_norm": 0.6332983132638484, "learning_rate": 8.760787021056267e-06, "loss": 0.8616, "step": 1950 }, { "epoch": 1.8173345759552655, "loss_cot": 0.4624137282371521, "loss_nocot": 0.48797526955604553, "step": 1950 }, { "epoch": 1.8182665424044733, "grad_norm": 0.7307905163912025, "learning_rate": 8.753883327580256e-06, "loss": 0.9005, "step": 1951 }, { "epoch": 1.8182665424044733, "loss_cot": 0.5356826782226562, "loss_nocot": 0.3776467740535736, "step": 1951 }, { "epoch": 1.8191985088536813, "grad_norm": 0.6383367170800032, "learning_rate": 8.746979634104247e-06, "loss": 0.8494, "step": 1952 }, { "epoch": 1.8191985088536813, "loss_cot": 0.5030456185340881, "loss_nocot": 0.34832361340522766, "step": 1952 }, { "epoch": 1.820130475302889, "grad_norm": 0.6270433567929746, "learning_rate": 8.740075940628236e-06, "loss": 0.8414, "step": 1953 }, { "epoch": 1.820130475302889, "loss_cot": 0.46515029668807983, "loss_nocot": 0.39685946702957153, "step": 1953 }, { "epoch": 1.821062441752097, "grad_norm": 0.6430092299535912, "learning_rate": 8.733172247152227e-06, "loss": 0.8329, "step": 1954 }, { "epoch": 1.821062441752097, "loss_cot": 0.48762601613998413, "loss_nocot": 0.36294883489608765, "step": 1954 }, { "epoch": 1.8219944082013049, "grad_norm": 0.6224975325831515, "learning_rate": 8.726268553676217e-06, "loss": 0.8678, "step": 1955 }, { "epoch": 1.8219944082013049, "loss_cot": 0.5023339986801147, "loss_nocot": 0.3295021653175354, "step": 1955 }, { "epoch": 1.8229263746505127, "grad_norm": 0.6473398337960969, "learning_rate": 8.719364860200208e-06, "loss": 0.8708, "step": 1956 }, { "epoch": 1.8229263746505127, "loss_cot": 0.4939478635787964, "loss_nocot": 0.31873852014541626, "step": 1956 }, { "epoch": 1.8238583410997204, "grad_norm": 0.6295357734845324, "learning_rate": 8.712461166724197e-06, "loss": 0.8563, "step": 1957 }, { "epoch": 1.8238583410997204, "loss_cot": 0.49776795506477356, "loss_nocot": 0.351848840713501, "step": 1957 }, { "epoch": 1.8247903075489282, "grad_norm": 0.6445570183278125, "learning_rate": 8.705557473248188e-06, "loss": 0.8295, "step": 1958 }, { "epoch": 1.8247903075489282, "loss_cot": 0.48414868116378784, "loss_nocot": 0.318733811378479, "step": 1958 }, { "epoch": 1.825722273998136, "grad_norm": 0.6267480949873521, "learning_rate": 8.698653779772179e-06, "loss": 0.8065, "step": 1959 }, { "epoch": 1.825722273998136, "loss_cot": 0.5630999207496643, "loss_nocot": 0.4112100601196289, "step": 1959 }, { "epoch": 1.8266542404473438, "grad_norm": 0.6644863017229165, "learning_rate": 8.69175008629617e-06, "loss": 0.8441, "step": 1960 }, { "epoch": 1.8266542404473438, "loss_cot": 0.47875598073005676, "loss_nocot": 0.2868834435939789, "step": 1960 }, { "epoch": 1.8275862068965516, "grad_norm": 0.6430318288271722, "learning_rate": 8.68484639282016e-06, "loss": 0.8391, "step": 1961 }, { "epoch": 1.8275862068965516, "loss_cot": 0.4991472065448761, "loss_nocot": 0.363969087600708, "step": 1961 }, { "epoch": 1.8285181733457594, "grad_norm": 0.6353545848094355, "learning_rate": 8.677942699344149e-06, "loss": 0.8586, "step": 1962 }, { "epoch": 1.8285181733457594, "loss_cot": 0.4606162905693054, "loss_nocot": 0.4046189785003662, "step": 1962 }, { "epoch": 1.8294501397949674, "grad_norm": 0.623219972590572, "learning_rate": 8.67103900586814e-06, "loss": 0.847, "step": 1963 }, { "epoch": 1.8294501397949674, "loss_cot": 0.5480108857154846, "loss_nocot": 0.33053815364837646, "step": 1963 }, { "epoch": 1.8303821062441752, "grad_norm": 0.6117858326548895, "learning_rate": 8.66413531239213e-06, "loss": 0.8687, "step": 1964 }, { "epoch": 1.8303821062441752, "loss_cot": 0.5332138538360596, "loss_nocot": 0.3460772633552551, "step": 1964 }, { "epoch": 1.8313140726933832, "grad_norm": 0.6018540546735756, "learning_rate": 8.657231618916121e-06, "loss": 0.8508, "step": 1965 }, { "epoch": 1.8313140726933832, "loss_cot": 0.42600303888320923, "loss_nocot": 0.43159186840057373, "step": 1965 }, { "epoch": 1.832246039142591, "grad_norm": 0.6615019245191922, "learning_rate": 8.65032792544011e-06, "loss": 0.8638, "step": 1966 }, { "epoch": 1.832246039142591, "loss_cot": 0.50992351770401, "loss_nocot": 0.2390168011188507, "step": 1966 }, { "epoch": 1.8331780055917988, "grad_norm": 0.6042421791269766, "learning_rate": 8.643424231964101e-06, "loss": 0.8008, "step": 1967 }, { "epoch": 1.8331780055917988, "loss_cot": 0.4840773344039917, "loss_nocot": 0.32825905084609985, "step": 1967 }, { "epoch": 1.8341099720410066, "grad_norm": 0.6339848862619096, "learning_rate": 8.636520538488092e-06, "loss": 0.8478, "step": 1968 }, { "epoch": 1.8341099720410066, "loss_cot": 0.494363397359848, "loss_nocot": 0.3924843668937683, "step": 1968 }, { "epoch": 1.8350419384902144, "grad_norm": 0.6012827614339067, "learning_rate": 8.629616845012082e-06, "loss": 0.8612, "step": 1969 }, { "epoch": 1.8350419384902144, "loss_cot": 0.4794406294822693, "loss_nocot": 0.44813230633735657, "step": 1969 }, { "epoch": 1.8359739049394221, "grad_norm": 0.6012239644743005, "learning_rate": 8.622713151536073e-06, "loss": 0.8483, "step": 1970 }, { "epoch": 1.8359739049394221, "loss_cot": 0.5270139575004578, "loss_nocot": 0.34607961773872375, "step": 1970 }, { "epoch": 1.83690587138863, "grad_norm": 0.6306921885551133, "learning_rate": 8.615809458060062e-06, "loss": 0.8458, "step": 1971 }, { "epoch": 1.83690587138863, "loss_cot": 0.5966315865516663, "loss_nocot": 0.3595001697540283, "step": 1971 }, { "epoch": 1.8378378378378377, "grad_norm": 0.5912870560953732, "learning_rate": 8.608905764584053e-06, "loss": 0.8275, "step": 1972 }, { "epoch": 1.8378378378378377, "loss_cot": 0.4996401071548462, "loss_nocot": 0.30146461725234985, "step": 1972 }, { "epoch": 1.8387698042870455, "grad_norm": 0.5938463279523849, "learning_rate": 8.602002071108044e-06, "loss": 0.8195, "step": 1973 }, { "epoch": 1.8387698042870455, "loss_cot": 0.5734319090843201, "loss_nocot": 0.32530513405799866, "step": 1973 }, { "epoch": 1.8397017707362535, "grad_norm": 0.657094659476301, "learning_rate": 8.595098377632034e-06, "loss": 0.8858, "step": 1974 }, { "epoch": 1.8397017707362535, "loss_cot": 0.5403739809989929, "loss_nocot": 0.3669961094856262, "step": 1974 }, { "epoch": 1.8406337371854613, "grad_norm": 0.64562805557292, "learning_rate": 8.588194684156023e-06, "loss": 0.8947, "step": 1975 }, { "epoch": 1.8406337371854613, "loss_cot": 0.4917239546775818, "loss_nocot": 0.38529062271118164, "step": 1975 }, { "epoch": 1.8415657036346693, "grad_norm": 0.6268338028094573, "learning_rate": 8.581290990680014e-06, "loss": 0.854, "step": 1976 }, { "epoch": 1.8415657036346693, "loss_cot": 0.5019299983978271, "loss_nocot": 0.4174058437347412, "step": 1976 }, { "epoch": 1.842497670083877, "grad_norm": 0.6271718949128874, "learning_rate": 8.574387297204005e-06, "loss": 0.8502, "step": 1977 }, { "epoch": 1.842497670083877, "loss_cot": 0.5294705629348755, "loss_nocot": 0.5766762495040894, "step": 1977 }, { "epoch": 1.843429636533085, "grad_norm": 0.6504922439048587, "learning_rate": 8.567483603727996e-06, "loss": 0.8605, "step": 1978 }, { "epoch": 1.843429636533085, "loss_cot": 0.5080305337905884, "loss_nocot": 0.29512733221054077, "step": 1978 }, { "epoch": 1.8443616029822927, "grad_norm": 0.5817849883518286, "learning_rate": 8.560579910251986e-06, "loss": 0.7673, "step": 1979 }, { "epoch": 1.8443616029822927, "loss_cot": 0.4354182779788971, "loss_nocot": 0.44749683141708374, "step": 1979 }, { "epoch": 1.8452935694315005, "grad_norm": 0.6343988969589004, "learning_rate": 8.553676216775975e-06, "loss": 0.8452, "step": 1980 }, { "epoch": 1.8452935694315005, "loss_cot": 0.4588318467140198, "loss_nocot": 0.3312544822692871, "step": 1980 }, { "epoch": 1.8462255358807083, "grad_norm": 0.6323743583127311, "learning_rate": 8.546772523299966e-06, "loss": 0.8414, "step": 1981 }, { "epoch": 1.8462255358807083, "loss_cot": 0.4849143624305725, "loss_nocot": 0.3435366749763489, "step": 1981 }, { "epoch": 1.847157502329916, "grad_norm": 0.627909638663626, "learning_rate": 8.539868829823957e-06, "loss": 0.8207, "step": 1982 }, { "epoch": 1.847157502329916, "loss_cot": 0.48693615198135376, "loss_nocot": 0.3990522027015686, "step": 1982 }, { "epoch": 1.8480894687791238, "grad_norm": 0.6352371994966926, "learning_rate": 8.532965136347948e-06, "loss": 0.8526, "step": 1983 }, { "epoch": 1.8480894687791238, "loss_cot": 0.5012303590774536, "loss_nocot": 0.5194368958473206, "step": 1983 }, { "epoch": 1.8490214352283316, "grad_norm": 0.6066021707454761, "learning_rate": 8.526061442871937e-06, "loss": 0.864, "step": 1984 }, { "epoch": 1.8490214352283316, "loss_cot": 0.5001641511917114, "loss_nocot": 0.2822972238063812, "step": 1984 }, { "epoch": 1.8499534016775396, "grad_norm": 0.5814277891269043, "learning_rate": 8.519157749395927e-06, "loss": 0.7885, "step": 1985 }, { "epoch": 1.8499534016775396, "loss_cot": 0.5621853470802307, "loss_nocot": 0.4569670557975769, "step": 1985 }, { "epoch": 1.8508853681267474, "grad_norm": 0.6656167416664476, "learning_rate": 8.512254055919918e-06, "loss": 0.9073, "step": 1986 }, { "epoch": 1.8508853681267474, "loss_cot": 0.45516666769981384, "loss_nocot": 0.4180383086204529, "step": 1986 }, { "epoch": 1.8518173345759554, "grad_norm": 0.6652470922847448, "learning_rate": 8.505350362443909e-06, "loss": 0.9052, "step": 1987 }, { "epoch": 1.8518173345759554, "loss_cot": 0.525891125202179, "loss_nocot": 0.5299369096755981, "step": 1987 }, { "epoch": 1.8527493010251632, "grad_norm": 0.6745241795664771, "learning_rate": 8.4984466689679e-06, "loss": 0.9028, "step": 1988 }, { "epoch": 1.8527493010251632, "loss_cot": 0.5513885021209717, "loss_nocot": 0.2655333876609802, "step": 1988 }, { "epoch": 1.853681267474371, "grad_norm": 0.6223306781885085, "learning_rate": 8.491542975491889e-06, "loss": 0.8917, "step": 1989 }, { "epoch": 1.853681267474371, "loss_cot": 0.5015556216239929, "loss_nocot": 0.37461888790130615, "step": 1989 }, { "epoch": 1.8546132339235788, "grad_norm": 0.694988291600045, "learning_rate": 8.48463928201588e-06, "loss": 0.9031, "step": 1990 }, { "epoch": 1.8546132339235788, "loss_cot": 0.4664653241634369, "loss_nocot": 0.3342287540435791, "step": 1990 }, { "epoch": 1.8555452003727866, "grad_norm": 0.6865622331864624, "learning_rate": 8.47773558853987e-06, "loss": 0.8463, "step": 1991 }, { "epoch": 1.8555452003727866, "loss_cot": 0.5315546989440918, "loss_nocot": 0.3235520124435425, "step": 1991 }, { "epoch": 1.8564771668219944, "grad_norm": 0.5944903900434142, "learning_rate": 8.47083189506386e-06, "loss": 0.8371, "step": 1992 }, { "epoch": 1.8564771668219944, "loss_cot": 0.44356244802474976, "loss_nocot": 0.3638620674610138, "step": 1992 }, { "epoch": 1.8574091332712022, "grad_norm": 0.6221323783705802, "learning_rate": 8.46392820158785e-06, "loss": 0.8186, "step": 1993 }, { "epoch": 1.8574091332712022, "loss_cot": 0.49413469433784485, "loss_nocot": 0.25312256813049316, "step": 1993 }, { "epoch": 1.85834109972041, "grad_norm": 0.6188093659344758, "learning_rate": 8.45702450811184e-06, "loss": 0.831, "step": 1994 }, { "epoch": 1.85834109972041, "loss_cot": 0.5207901000976562, "loss_nocot": 0.30963361263275146, "step": 1994 }, { "epoch": 1.8592730661696177, "grad_norm": 0.6235560532407901, "learning_rate": 8.45012081463583e-06, "loss": 0.8649, "step": 1995 }, { "epoch": 1.8592730661696177, "loss_cot": 0.47782087326049805, "loss_nocot": 0.3443242907524109, "step": 1995 }, { "epoch": 1.8602050326188257, "grad_norm": 0.6136897179642015, "learning_rate": 8.443217121159822e-06, "loss": 0.8589, "step": 1996 }, { "epoch": 1.8602050326188257, "loss_cot": 0.4813151955604553, "loss_nocot": 0.8694993257522583, "step": 1996 }, { "epoch": 1.8611369990680335, "grad_norm": 0.6773865143112148, "learning_rate": 8.436313427683811e-06, "loss": 0.9406, "step": 1997 }, { "epoch": 1.8611369990680335, "loss_cot": 0.5003006458282471, "loss_nocot": 0.3474632501602173, "step": 1997 }, { "epoch": 1.8620689655172413, "grad_norm": 0.5922159250127534, "learning_rate": 8.429409734207802e-06, "loss": 0.7393, "step": 1998 }, { "epoch": 1.8620689655172413, "loss_cot": 0.48190394043922424, "loss_nocot": 0.39300036430358887, "step": 1998 }, { "epoch": 1.8630009319664493, "grad_norm": 0.6141228488494456, "learning_rate": 8.422506040731793e-06, "loss": 0.8938, "step": 1999 }, { "epoch": 1.8630009319664493, "loss_cot": 0.44365209341049194, "loss_nocot": 0.31259626150131226, "step": 1999 }, { "epoch": 1.8639328984156571, "grad_norm": 0.6032731338738185, "learning_rate": 8.415602347255782e-06, "loss": 0.837, "step": 2000 }, { "epoch": 1.8639328984156571, "loss_cot": 0.5164836049079895, "loss_nocot": 0.40285345911979675, "step": 2000 }, { "epoch": 1.864864864864865, "grad_norm": 0.6385669645089257, "learning_rate": 8.408698653779774e-06, "loss": 0.8518, "step": 2001 }, { "epoch": 1.864864864864865, "loss_cot": 0.5343964099884033, "loss_nocot": 0.32733142375946045, "step": 2001 }, { "epoch": 1.8657968313140727, "grad_norm": 0.5862291741634611, "learning_rate": 8.401794960303763e-06, "loss": 0.8468, "step": 2002 }, { "epoch": 1.8657968313140727, "loss_cot": 0.5002894997596741, "loss_nocot": 0.23074860870838165, "step": 2002 }, { "epoch": 1.8667287977632805, "grad_norm": 0.5689011234112641, "learning_rate": 8.394891266827754e-06, "loss": 0.7689, "step": 2003 }, { "epoch": 1.8667287977632805, "loss_cot": 0.5499538779258728, "loss_nocot": 0.33670440316200256, "step": 2003 }, { "epoch": 1.8676607642124883, "grad_norm": 0.6202570843010228, "learning_rate": 8.387987573351743e-06, "loss": 0.8291, "step": 2004 }, { "epoch": 1.8676607642124883, "loss_cot": 0.5005818605422974, "loss_nocot": 0.2645407021045685, "step": 2004 }, { "epoch": 1.868592730661696, "grad_norm": 0.6111532354782084, "learning_rate": 8.381083879875734e-06, "loss": 0.8098, "step": 2005 }, { "epoch": 1.868592730661696, "loss_cot": 0.5805943012237549, "loss_nocot": 0.3538999557495117, "step": 2005 }, { "epoch": 1.8695246971109039, "grad_norm": 0.6581118331645341, "learning_rate": 8.374180186399724e-06, "loss": 0.8864, "step": 2006 }, { "epoch": 1.8695246971109039, "loss_cot": 0.4903167188167572, "loss_nocot": 0.4490519165992737, "step": 2006 }, { "epoch": 1.8704566635601119, "grad_norm": 0.6815981662663967, "learning_rate": 8.367276492923715e-06, "loss": 0.9333, "step": 2007 }, { "epoch": 1.8704566635601119, "loss_cot": 0.5227430462837219, "loss_nocot": 0.29568082094192505, "step": 2007 }, { "epoch": 1.8713886300093197, "grad_norm": 0.5871356686549338, "learning_rate": 8.360372799447706e-06, "loss": 0.8175, "step": 2008 }, { "epoch": 1.8713886300093197, "loss_cot": 0.5184348225593567, "loss_nocot": 0.29021114110946655, "step": 2008 }, { "epoch": 1.8723205964585274, "grad_norm": 0.5934162284951883, "learning_rate": 8.353469105971695e-06, "loss": 0.8142, "step": 2009 }, { "epoch": 1.8723205964585274, "loss_cot": 0.5146243572235107, "loss_nocot": 0.2810909152030945, "step": 2009 }, { "epoch": 1.8732525629077355, "grad_norm": 0.6246668761587957, "learning_rate": 8.346565412495686e-06, "loss": 0.8132, "step": 2010 }, { "epoch": 1.8732525629077355, "loss_cot": 0.42504751682281494, "loss_nocot": 0.46382248401641846, "step": 2010 }, { "epoch": 1.8741845293569432, "grad_norm": 0.6666623328954211, "learning_rate": 8.339661719019676e-06, "loss": 0.9088, "step": 2011 }, { "epoch": 1.8741845293569432, "loss_cot": 0.43837952613830566, "loss_nocot": 0.4658997654914856, "step": 2011 }, { "epoch": 1.875116495806151, "grad_norm": 0.6282046164905238, "learning_rate": 8.332758025543667e-06, "loss": 0.8078, "step": 2012 }, { "epoch": 1.875116495806151, "loss_cot": 0.5442121624946594, "loss_nocot": 0.3144034147262573, "step": 2012 }, { "epoch": 1.8760484622553588, "grad_norm": 0.6047647817312766, "learning_rate": 8.325854332067656e-06, "loss": 0.8723, "step": 2013 }, { "epoch": 1.8760484622553588, "loss_cot": 0.4846448302268982, "loss_nocot": 0.3059348464012146, "step": 2013 }, { "epoch": 1.8769804287045666, "grad_norm": 0.6102188504717656, "learning_rate": 8.318950638591647e-06, "loss": 0.8433, "step": 2014 }, { "epoch": 1.8769804287045666, "loss_cot": 0.4792432487010956, "loss_nocot": 0.3298290967941284, "step": 2014 }, { "epoch": 1.8779123951537744, "grad_norm": 0.6705092940527333, "learning_rate": 8.312046945115638e-06, "loss": 0.8851, "step": 2015 }, { "epoch": 1.8779123951537744, "loss_cot": 0.5364319086074829, "loss_nocot": 0.41997450590133667, "step": 2015 }, { "epoch": 1.8788443616029822, "grad_norm": 0.6853572430676735, "learning_rate": 8.305143251639628e-06, "loss": 0.8851, "step": 2016 }, { "epoch": 1.8788443616029822, "loss_cot": 0.44656527042388916, "loss_nocot": 0.29471784830093384, "step": 2016 }, { "epoch": 1.87977632805219, "grad_norm": 0.5420484544375992, "learning_rate": 8.298239558163617e-06, "loss": 0.7487, "step": 2017 }, { "epoch": 1.87977632805219, "loss_cot": 0.47668343782424927, "loss_nocot": 0.3950924575328827, "step": 2017 }, { "epoch": 1.880708294501398, "grad_norm": 0.5736849408484344, "learning_rate": 8.291335864687608e-06, "loss": 0.7849, "step": 2018 }, { "epoch": 1.880708294501398, "loss_cot": 0.5095851421356201, "loss_nocot": 0.3576497435569763, "step": 2018 }, { "epoch": 1.8816402609506058, "grad_norm": 0.6072322524395762, "learning_rate": 8.284432171211599e-06, "loss": 0.8355, "step": 2019 }, { "epoch": 1.8816402609506058, "loss_cot": 0.486294686794281, "loss_nocot": 0.2707009017467499, "step": 2019 }, { "epoch": 1.8825722273998136, "grad_norm": 0.6408783508773543, "learning_rate": 8.27752847773559e-06, "loss": 0.8458, "step": 2020 }, { "epoch": 1.8825722273998136, "loss_cot": 0.46036016941070557, "loss_nocot": 0.2273777574300766, "step": 2020 }, { "epoch": 1.8835041938490216, "grad_norm": 0.639847228222015, "learning_rate": 8.27062478425958e-06, "loss": 0.8567, "step": 2021 }, { "epoch": 1.8835041938490216, "loss_cot": 0.504082202911377, "loss_nocot": 0.3726673722267151, "step": 2021 }, { "epoch": 1.8844361602982294, "grad_norm": 0.6502156075395592, "learning_rate": 8.26372109078357e-06, "loss": 0.8284, "step": 2022 }, { "epoch": 1.8844361602982294, "loss_cot": 0.5205886363983154, "loss_nocot": 0.30542290210723877, "step": 2022 }, { "epoch": 1.8853681267474371, "grad_norm": 0.5900591275920992, "learning_rate": 8.25681739730756e-06, "loss": 0.8026, "step": 2023 }, { "epoch": 1.8853681267474371, "loss_cot": 0.4406711161136627, "loss_nocot": 0.2929460406303406, "step": 2023 }, { "epoch": 1.886300093196645, "grad_norm": 0.617335269098046, "learning_rate": 8.24991370383155e-06, "loss": 0.8442, "step": 2024 }, { "epoch": 1.886300093196645, "loss_cot": 0.44666361808776855, "loss_nocot": 0.35794487595558167, "step": 2024 }, { "epoch": 1.8872320596458527, "grad_norm": 0.6837479325036855, "learning_rate": 8.243010010355541e-06, "loss": 0.858, "step": 2025 }, { "epoch": 1.8872320596458527, "loss_cot": 0.4796784520149231, "loss_nocot": 0.3406989872455597, "step": 2025 }, { "epoch": 1.8881640260950605, "grad_norm": 0.6478737194167231, "learning_rate": 8.23610631687953e-06, "loss": 0.9105, "step": 2026 }, { "epoch": 1.8881640260950605, "loss_cot": 0.5317674279212952, "loss_nocot": 0.29867023229599, "step": 2026 }, { "epoch": 1.8890959925442683, "grad_norm": 0.6504931948238267, "learning_rate": 8.229202623403521e-06, "loss": 0.8789, "step": 2027 }, { "epoch": 1.8890959925442683, "loss_cot": 0.4807576537132263, "loss_nocot": 0.35098063945770264, "step": 2027 }, { "epoch": 1.890027958993476, "grad_norm": 0.6119467599954553, "learning_rate": 8.222298929927512e-06, "loss": 0.8402, "step": 2028 }, { "epoch": 1.890027958993476, "loss_cot": 0.5224674940109253, "loss_nocot": 0.3096997141838074, "step": 2028 }, { "epoch": 1.890959925442684, "grad_norm": 0.6194858484458108, "learning_rate": 8.215395236451503e-06, "loss": 0.8549, "step": 2029 }, { "epoch": 1.890959925442684, "loss_cot": 0.5371150374412537, "loss_nocot": 0.4387308955192566, "step": 2029 }, { "epoch": 1.8918918918918919, "grad_norm": 0.7007989914388613, "learning_rate": 8.208491542975493e-06, "loss": 0.9095, "step": 2030 }, { "epoch": 1.8918918918918919, "loss_cot": 0.4725334346294403, "loss_nocot": 0.25660082697868347, "step": 2030 }, { "epoch": 1.8928238583410997, "grad_norm": 0.6386609460491494, "learning_rate": 8.201587849499482e-06, "loss": 0.8736, "step": 2031 }, { "epoch": 1.8928238583410997, "loss_cot": 0.5153689384460449, "loss_nocot": 0.37555205821990967, "step": 2031 }, { "epoch": 1.8937558247903077, "grad_norm": 0.6748282037576092, "learning_rate": 8.194684156023473e-06, "loss": 0.867, "step": 2032 }, { "epoch": 1.8937558247903077, "loss_cot": 0.4832794666290283, "loss_nocot": 0.33801764249801636, "step": 2032 }, { "epoch": 1.8946877912395155, "grad_norm": 0.6090225344065949, "learning_rate": 8.187780462547464e-06, "loss": 0.821, "step": 2033 }, { "epoch": 1.8946877912395155, "loss_cot": 0.48238301277160645, "loss_nocot": 0.2927137613296509, "step": 2033 }, { "epoch": 1.8956197576887233, "grad_norm": 0.6048075790426567, "learning_rate": 8.180876769071455e-06, "loss": 0.8088, "step": 2034 }, { "epoch": 1.8956197576887233, "loss_cot": 0.5046960115432739, "loss_nocot": 0.46270665526390076, "step": 2034 }, { "epoch": 1.896551724137931, "grad_norm": 0.6253916375151896, "learning_rate": 8.173973075595444e-06, "loss": 0.8439, "step": 2035 }, { "epoch": 1.896551724137931, "loss_cot": 0.5259193181991577, "loss_nocot": 0.371090829372406, "step": 2035 }, { "epoch": 1.8974836905871388, "grad_norm": 0.6205248175198078, "learning_rate": 8.167069382119434e-06, "loss": 0.8525, "step": 2036 }, { "epoch": 1.8974836905871388, "loss_cot": 0.46829846501350403, "loss_nocot": 0.45492756366729736, "step": 2036 }, { "epoch": 1.8984156570363466, "grad_norm": 0.6371856617899488, "learning_rate": 8.160165688643425e-06, "loss": 0.8173, "step": 2037 }, { "epoch": 1.8984156570363466, "loss_cot": 0.5026023387908936, "loss_nocot": 0.3624235987663269, "step": 2037 }, { "epoch": 1.8993476234855544, "grad_norm": 0.5991693065227353, "learning_rate": 8.153261995167416e-06, "loss": 0.8446, "step": 2038 }, { "epoch": 1.8993476234855544, "loss_cot": 0.5766792297363281, "loss_nocot": 0.3084465265274048, "step": 2038 }, { "epoch": 1.9002795899347622, "grad_norm": 0.5937231327025193, "learning_rate": 8.146358301691407e-06, "loss": 0.8273, "step": 2039 }, { "epoch": 1.9002795899347622, "loss_cot": 0.4614488482475281, "loss_nocot": 0.3378732204437256, "step": 2039 }, { "epoch": 1.9012115563839702, "grad_norm": 0.640800843125174, "learning_rate": 8.139454608215396e-06, "loss": 0.8513, "step": 2040 }, { "epoch": 1.9012115563839702, "loss_cot": 0.4990823268890381, "loss_nocot": 0.3531523048877716, "step": 2040 }, { "epoch": 1.902143522833178, "grad_norm": 0.668806671555644, "learning_rate": 8.132550914739386e-06, "loss": 0.8509, "step": 2041 }, { "epoch": 1.902143522833178, "loss_cot": 0.5646624565124512, "loss_nocot": 0.38934653997421265, "step": 2041 }, { "epoch": 1.9030754892823858, "grad_norm": 0.5969057194876468, "learning_rate": 8.125647221263377e-06, "loss": 0.8764, "step": 2042 }, { "epoch": 1.9030754892823858, "loss_cot": 0.5707693099975586, "loss_nocot": 0.33041417598724365, "step": 2042 }, { "epoch": 1.9040074557315938, "grad_norm": 0.5929407524751938, "learning_rate": 8.118743527787368e-06, "loss": 0.8614, "step": 2043 }, { "epoch": 1.9040074557315938, "loss_cot": 0.5344445109367371, "loss_nocot": 0.30108875036239624, "step": 2043 }, { "epoch": 1.9049394221808016, "grad_norm": 0.6123270353498989, "learning_rate": 8.111839834311357e-06, "loss": 0.8557, "step": 2044 }, { "epoch": 1.9049394221808016, "loss_cot": 0.47979438304901123, "loss_nocot": 0.3566235303878784, "step": 2044 }, { "epoch": 1.9058713886300094, "grad_norm": 0.5887450207570093, "learning_rate": 8.104936140835348e-06, "loss": 0.8157, "step": 2045 }, { "epoch": 1.9058713886300094, "loss_cot": 0.5161126852035522, "loss_nocot": 0.2863880395889282, "step": 2045 }, { "epoch": 1.9068033550792172, "grad_norm": 0.6346928376257415, "learning_rate": 8.098032447359337e-06, "loss": 0.858, "step": 2046 }, { "epoch": 1.9068033550792172, "loss_cot": 0.5209556221961975, "loss_nocot": 0.35843250155448914, "step": 2046 }, { "epoch": 1.907735321528425, "grad_norm": 0.6244629805419032, "learning_rate": 8.091128753883329e-06, "loss": 0.8526, "step": 2047 }, { "epoch": 1.907735321528425, "loss_cot": 0.5729550123214722, "loss_nocot": 0.46104511618614197, "step": 2047 }, { "epoch": 1.9086672879776327, "grad_norm": 0.656393214270875, "learning_rate": 8.084225060407318e-06, "loss": 0.9365, "step": 2048 }, { "epoch": 1.9086672879776327, "loss_cot": 0.46667253971099854, "loss_nocot": 0.31711938977241516, "step": 2048 }, { "epoch": 1.9095992544268405, "grad_norm": 0.6311098006371928, "learning_rate": 8.077321366931309e-06, "loss": 0.8182, "step": 2049 }, { "epoch": 1.9095992544268405, "loss_cot": 0.47301819920539856, "loss_nocot": 0.30714908242225647, "step": 2049 }, { "epoch": 1.9105312208760483, "grad_norm": 0.6262596375449974, "learning_rate": 8.0704176734553e-06, "loss": 0.8633, "step": 2050 }, { "epoch": 1.9105312208760483, "loss_cot": 0.4856705665588379, "loss_nocot": 0.4665341079235077, "step": 2050 }, { "epoch": 1.9114631873252563, "grad_norm": 0.6203787904101584, "learning_rate": 8.063513979979289e-06, "loss": 0.8959, "step": 2051 }, { "epoch": 1.9114631873252563, "loss_cot": 0.451529324054718, "loss_nocot": 0.34860706329345703, "step": 2051 }, { "epoch": 1.9123951537744641, "grad_norm": 0.6629101396408921, "learning_rate": 8.056610286503281e-06, "loss": 0.8564, "step": 2052 }, { "epoch": 1.9123951537744641, "loss_cot": 0.5166168212890625, "loss_nocot": 0.37264201045036316, "step": 2052 }, { "epoch": 1.913327120223672, "grad_norm": 0.6171043579778521, "learning_rate": 8.04970659302727e-06, "loss": 0.8185, "step": 2053 }, { "epoch": 1.913327120223672, "loss_cot": 0.5627045631408691, "loss_nocot": 0.35001009702682495, "step": 2053 }, { "epoch": 1.91425908667288, "grad_norm": 0.6362789398182972, "learning_rate": 8.04280289955126e-06, "loss": 0.8355, "step": 2054 }, { "epoch": 1.91425908667288, "loss_cot": 0.4843675494194031, "loss_nocot": 0.41550764441490173, "step": 2054 }, { "epoch": 1.9151910531220877, "grad_norm": 0.6947909935425751, "learning_rate": 8.03589920607525e-06, "loss": 0.8693, "step": 2055 }, { "epoch": 1.9151910531220877, "loss_cot": 0.4921994209289551, "loss_nocot": 0.318636417388916, "step": 2055 }, { "epoch": 1.9161230195712955, "grad_norm": 0.6109045625852956, "learning_rate": 8.02899551259924e-06, "loss": 0.8202, "step": 2056 }, { "epoch": 1.9161230195712955, "loss_cot": 0.47741642594337463, "loss_nocot": 0.4234481453895569, "step": 2056 }, { "epoch": 1.9170549860205033, "grad_norm": 0.6470355550808928, "learning_rate": 8.022091819123231e-06, "loss": 0.8498, "step": 2057 }, { "epoch": 1.9170549860205033, "loss_cot": 0.5407685041427612, "loss_nocot": 0.6118972301483154, "step": 2057 }, { "epoch": 1.917986952469711, "grad_norm": 0.6769964825513555, "learning_rate": 8.015188125647222e-06, "loss": 0.9614, "step": 2058 }, { "epoch": 1.917986952469711, "loss_cot": 0.5745893716812134, "loss_nocot": 0.362246572971344, "step": 2058 }, { "epoch": 1.9189189189189189, "grad_norm": 0.6206683625099755, "learning_rate": 8.008284432171213e-06, "loss": 0.8755, "step": 2059 }, { "epoch": 1.9189189189189189, "loss_cot": 0.5041406154632568, "loss_nocot": 0.40280982851982117, "step": 2059 }, { "epoch": 1.9198508853681266, "grad_norm": 0.65207442659292, "learning_rate": 8.001380738695202e-06, "loss": 0.883, "step": 2060 }, { "epoch": 1.9198508853681266, "loss_cot": 0.5153560638427734, "loss_nocot": 0.31485089659690857, "step": 2060 }, { "epoch": 1.9207828518173344, "grad_norm": 0.6277961103881093, "learning_rate": 7.994477045219193e-06, "loss": 0.8564, "step": 2061 }, { "epoch": 1.9207828518173344, "loss_cot": 0.4773968458175659, "loss_nocot": 0.28790026903152466, "step": 2061 }, { "epoch": 1.9217148182665424, "grad_norm": 0.6725061394789767, "learning_rate": 7.987573351743183e-06, "loss": 0.8385, "step": 2062 }, { "epoch": 1.9217148182665424, "loss_cot": 0.4813857674598694, "loss_nocot": 0.2241538166999817, "step": 2062 }, { "epoch": 1.9226467847157502, "grad_norm": 0.5695291508777006, "learning_rate": 7.980669658267174e-06, "loss": 0.8001, "step": 2063 }, { "epoch": 1.9226467847157502, "loss_cot": 0.4994824230670929, "loss_nocot": 0.3283475637435913, "step": 2063 }, { "epoch": 1.923578751164958, "grad_norm": 0.6269034162612068, "learning_rate": 7.973765964791163e-06, "loss": 0.8394, "step": 2064 }, { "epoch": 1.923578751164958, "loss_cot": 0.49586668610572815, "loss_nocot": 0.27381432056427, "step": 2064 }, { "epoch": 1.924510717614166, "grad_norm": 0.6492246466060889, "learning_rate": 7.966862271315154e-06, "loss": 0.8645, "step": 2065 }, { "epoch": 1.924510717614166, "loss_cot": 0.5400963425636292, "loss_nocot": 0.3530155420303345, "step": 2065 }, { "epoch": 1.9254426840633738, "grad_norm": 0.6146929708639131, "learning_rate": 7.959958577839145e-06, "loss": 0.8243, "step": 2066 }, { "epoch": 1.9254426840633738, "loss_cot": 0.515828549861908, "loss_nocot": 0.3690018653869629, "step": 2066 }, { "epoch": 1.9263746505125816, "grad_norm": 0.629078832477731, "learning_rate": 7.953054884363135e-06, "loss": 0.8426, "step": 2067 }, { "epoch": 1.9263746505125816, "loss_cot": 0.5758670568466187, "loss_nocot": 0.436129093170166, "step": 2067 }, { "epoch": 1.9273066169617894, "grad_norm": 0.6593660646776206, "learning_rate": 7.946151190887124e-06, "loss": 0.9229, "step": 2068 }, { "epoch": 1.9273066169617894, "loss_cot": 0.510246992111206, "loss_nocot": 0.452919602394104, "step": 2068 }, { "epoch": 1.9282385834109972, "grad_norm": 0.6379741993945675, "learning_rate": 7.939247497411115e-06, "loss": 0.8338, "step": 2069 }, { "epoch": 1.9282385834109972, "loss_cot": 0.4913330078125, "loss_nocot": 0.35029035806655884, "step": 2069 }, { "epoch": 1.929170549860205, "grad_norm": 0.6408896706934927, "learning_rate": 7.932343803935106e-06, "loss": 0.8784, "step": 2070 }, { "epoch": 1.929170549860205, "loss_cot": 0.5105400681495667, "loss_nocot": 0.3255529999732971, "step": 2070 }, { "epoch": 1.9301025163094128, "grad_norm": 0.609251523088376, "learning_rate": 7.925440110459096e-06, "loss": 0.8511, "step": 2071 }, { "epoch": 1.9301025163094128, "loss_cot": 0.5041637420654297, "loss_nocot": 0.3284984827041626, "step": 2071 }, { "epoch": 1.9310344827586206, "grad_norm": 0.6248325648577235, "learning_rate": 7.918536416983087e-06, "loss": 0.8552, "step": 2072 }, { "epoch": 1.9310344827586206, "loss_cot": 0.4901331961154938, "loss_nocot": 0.2927844524383545, "step": 2072 }, { "epoch": 1.9319664492078286, "grad_norm": 0.6021437013717081, "learning_rate": 7.911632723507076e-06, "loss": 0.8132, "step": 2073 }, { "epoch": 1.9319664492078286, "loss_cot": 0.4955785274505615, "loss_nocot": 0.4297159016132355, "step": 2073 }, { "epoch": 1.9328984156570364, "grad_norm": 0.6398398405485808, "learning_rate": 7.904729030031067e-06, "loss": 0.9183, "step": 2074 }, { "epoch": 1.9328984156570364, "loss_cot": 0.45907899737358093, "loss_nocot": 0.26443517208099365, "step": 2074 }, { "epoch": 1.9338303821062441, "grad_norm": 0.6651605401249097, "learning_rate": 7.897825336555058e-06, "loss": 0.9037, "step": 2075 }, { "epoch": 1.9338303821062441, "loss_cot": 0.524346113204956, "loss_nocot": 0.4412095248699188, "step": 2075 }, { "epoch": 1.9347623485554521, "grad_norm": 0.6037198220421414, "learning_rate": 7.890921643079048e-06, "loss": 0.8356, "step": 2076 }, { "epoch": 1.9347623485554521, "loss_cot": 0.5358054637908936, "loss_nocot": 0.4219455122947693, "step": 2076 }, { "epoch": 1.93569431500466, "grad_norm": 0.6111092211716215, "learning_rate": 7.884017949603038e-06, "loss": 0.8427, "step": 2077 }, { "epoch": 1.93569431500466, "loss_cot": 0.551874577999115, "loss_nocot": 0.2605327367782593, "step": 2077 }, { "epoch": 1.9366262814538677, "grad_norm": 0.6425996085441774, "learning_rate": 7.877114256127028e-06, "loss": 0.8712, "step": 2078 }, { "epoch": 1.9366262814538677, "loss_cot": 0.5098764896392822, "loss_nocot": 0.330480694770813, "step": 2078 }, { "epoch": 1.9375582479030755, "grad_norm": 0.6832959700121429, "learning_rate": 7.870210562651019e-06, "loss": 0.8441, "step": 2079 }, { "epoch": 1.9375582479030755, "loss_cot": 0.5073165893554688, "loss_nocot": 0.2720791697502136, "step": 2079 }, { "epoch": 1.9384902143522833, "grad_norm": 0.6264033317107516, "learning_rate": 7.86330686917501e-06, "loss": 0.8465, "step": 2080 }, { "epoch": 1.9384902143522833, "loss_cot": 0.5183631181716919, "loss_nocot": 0.26715004444122314, "step": 2080 }, { "epoch": 1.939422180801491, "grad_norm": 0.5944316148251896, "learning_rate": 7.856403175699e-06, "loss": 0.7766, "step": 2081 }, { "epoch": 1.939422180801491, "loss_cot": 0.46646010875701904, "loss_nocot": 0.3584482967853546, "step": 2081 }, { "epoch": 1.9403541472506989, "grad_norm": 0.6774126678289968, "learning_rate": 7.84949948222299e-06, "loss": 0.8988, "step": 2082 }, { "epoch": 1.9403541472506989, "loss_cot": 0.5502140522003174, "loss_nocot": 0.381773442029953, "step": 2082 }, { "epoch": 1.9412861136999067, "grad_norm": 0.6682388804320368, "learning_rate": 7.84259578874698e-06, "loss": 0.9278, "step": 2083 }, { "epoch": 1.9412861136999067, "loss_cot": 0.49260008335113525, "loss_nocot": 0.2619968056678772, "step": 2083 }, { "epoch": 1.9422180801491147, "grad_norm": 0.5682873284797717, "learning_rate": 7.835692095270971e-06, "loss": 0.7877, "step": 2084 }, { "epoch": 1.9422180801491147, "loss_cot": 0.5906864404678345, "loss_nocot": 0.276957631111145, "step": 2084 }, { "epoch": 1.9431500465983225, "grad_norm": 0.6040334716985036, "learning_rate": 7.828788401794962e-06, "loss": 0.873, "step": 2085 }, { "epoch": 1.9431500465983225, "loss_cot": 0.48823776841163635, "loss_nocot": 0.3343670964241028, "step": 2085 }, { "epoch": 1.9440820130475303, "grad_norm": 0.6639150608255424, "learning_rate": 7.82188470831895e-06, "loss": 0.9085, "step": 2086 }, { "epoch": 1.9440820130475303, "loss_cot": 0.4733473062515259, "loss_nocot": 0.34287574887275696, "step": 2086 }, { "epoch": 1.9450139794967383, "grad_norm": 0.6027815477710133, "learning_rate": 7.814981014842941e-06, "loss": 0.7992, "step": 2087 }, { "epoch": 1.9450139794967383, "loss_cot": 0.46842533349990845, "loss_nocot": 0.3180403709411621, "step": 2087 }, { "epoch": 1.945945945945946, "grad_norm": 0.624240798464021, "learning_rate": 7.808077321366932e-06, "loss": 0.8551, "step": 2088 }, { "epoch": 1.945945945945946, "loss_cot": 0.5187634229660034, "loss_nocot": 0.3697713315486908, "step": 2088 }, { "epoch": 1.9468779123951538, "grad_norm": 0.6075348442592355, "learning_rate": 7.801173627890923e-06, "loss": 0.8379, "step": 2089 }, { "epoch": 1.9468779123951538, "loss_cot": 0.5802284479141235, "loss_nocot": 0.31447362899780273, "step": 2089 }, { "epoch": 1.9478098788443616, "grad_norm": 0.6114338673279528, "learning_rate": 7.794269934414914e-06, "loss": 0.8304, "step": 2090 }, { "epoch": 1.9478098788443616, "loss_cot": 0.45342588424682617, "loss_nocot": 0.4158898591995239, "step": 2090 }, { "epoch": 1.9487418452935694, "grad_norm": 0.630085317581013, "learning_rate": 7.787366240938903e-06, "loss": 0.819, "step": 2091 }, { "epoch": 1.9487418452935694, "loss_cot": 0.4887777268886566, "loss_nocot": 0.4390994906425476, "step": 2091 }, { "epoch": 1.9496738117427772, "grad_norm": 0.6645486925856438, "learning_rate": 7.780462547462893e-06, "loss": 0.8675, "step": 2092 }, { "epoch": 1.9496738117427772, "loss_cot": 0.5004564523696899, "loss_nocot": 0.273185670375824, "step": 2092 }, { "epoch": 1.950605778191985, "grad_norm": 0.650555897650412, "learning_rate": 7.773558853986884e-06, "loss": 0.8589, "step": 2093 }, { "epoch": 1.950605778191985, "loss_cot": 0.4625943899154663, "loss_nocot": 0.2794012427330017, "step": 2093 }, { "epoch": 1.9515377446411928, "grad_norm": 0.6029949570978144, "learning_rate": 7.766655160510875e-06, "loss": 0.779, "step": 2094 }, { "epoch": 1.9515377446411928, "loss_cot": 0.46993309259414673, "loss_nocot": 0.41047167778015137, "step": 2094 }, { "epoch": 1.9524697110904008, "grad_norm": 0.6570986973304517, "learning_rate": 7.759751467034864e-06, "loss": 0.8848, "step": 2095 }, { "epoch": 1.9524697110904008, "loss_cot": 0.4986523687839508, "loss_nocot": 0.3059651255607605, "step": 2095 }, { "epoch": 1.9534016775396086, "grad_norm": 0.6875402751371107, "learning_rate": 7.752847773558855e-06, "loss": 0.8233, "step": 2096 }, { "epoch": 1.9534016775396086, "loss_cot": 0.503125011920929, "loss_nocot": 0.3089625835418701, "step": 2096 }, { "epoch": 1.9543336439888164, "grad_norm": 0.6230716267765638, "learning_rate": 7.745944080082844e-06, "loss": 0.9312, "step": 2097 }, { "epoch": 1.9543336439888164, "loss_cot": 0.5134497880935669, "loss_nocot": 0.31666022539138794, "step": 2097 }, { "epoch": 1.9552656104380244, "grad_norm": 0.645567598219066, "learning_rate": 7.739040386606836e-06, "loss": 0.8758, "step": 2098 }, { "epoch": 1.9552656104380244, "loss_cot": 0.4926230311393738, "loss_nocot": 0.36895298957824707, "step": 2098 }, { "epoch": 1.9561975768872322, "grad_norm": 0.6429218450017756, "learning_rate": 7.732136693130827e-06, "loss": 0.8472, "step": 2099 }, { "epoch": 1.9561975768872322, "loss_cot": 0.47575515508651733, "loss_nocot": 0.3608907461166382, "step": 2099 }, { "epoch": 1.95712954333644, "grad_norm": 0.6501141905298892, "learning_rate": 7.725232999654816e-06, "loss": 0.8677, "step": 2100 }, { "epoch": 1.95712954333644, "loss_cot": 0.4810792803764343, "loss_nocot": 0.38730525970458984, "step": 2100 }, { "epoch": 1.9580615097856477, "grad_norm": 0.6864604635420031, "learning_rate": 7.718329306178807e-06, "loss": 0.9286, "step": 2101 }, { "epoch": 1.9580615097856477, "loss_cot": 0.5172949433326721, "loss_nocot": 0.35220152139663696, "step": 2101 }, { "epoch": 1.9589934762348555, "grad_norm": 0.6293936162804518, "learning_rate": 7.711425612702796e-06, "loss": 0.8382, "step": 2102 }, { "epoch": 1.9589934762348555, "loss_cot": 0.46226829290390015, "loss_nocot": 0.2854282259941101, "step": 2102 }, { "epoch": 1.9599254426840633, "grad_norm": 0.5997929666661809, "learning_rate": 7.704521919226788e-06, "loss": 0.8091, "step": 2103 }, { "epoch": 1.9599254426840633, "loss_cot": 0.4888775050640106, "loss_nocot": 0.35441744327545166, "step": 2103 }, { "epoch": 1.9608574091332711, "grad_norm": 0.6143451059102351, "learning_rate": 7.697618225750777e-06, "loss": 0.8706, "step": 2104 }, { "epoch": 1.9608574091332711, "loss_cot": 0.5135310292243958, "loss_nocot": 0.2828158140182495, "step": 2104 }, { "epoch": 1.961789375582479, "grad_norm": 0.6111782982225037, "learning_rate": 7.690714532274768e-06, "loss": 0.835, "step": 2105 }, { "epoch": 1.961789375582479, "loss_cot": 0.47320252656936646, "loss_nocot": 0.38744407892227173, "step": 2105 }, { "epoch": 1.962721342031687, "grad_norm": 0.648965487455705, "learning_rate": 7.683810838798757e-06, "loss": 0.8612, "step": 2106 }, { "epoch": 1.962721342031687, "loss_cot": 0.5094584822654724, "loss_nocot": 0.3118249177932739, "step": 2106 }, { "epoch": 1.9636533084808947, "grad_norm": 0.6267347268909685, "learning_rate": 7.676907145322748e-06, "loss": 0.7991, "step": 2107 }, { "epoch": 1.9636533084808947, "loss_cot": 0.5405951738357544, "loss_nocot": 0.37783825397491455, "step": 2107 }, { "epoch": 1.9645852749301025, "grad_norm": 0.6721757248607692, "learning_rate": 7.670003451846738e-06, "loss": 0.9624, "step": 2108 }, { "epoch": 1.9645852749301025, "loss_cot": 0.48748505115509033, "loss_nocot": 0.32607007026672363, "step": 2108 }, { "epoch": 1.9655172413793105, "grad_norm": 0.6718150887921241, "learning_rate": 7.663099758370729e-06, "loss": 0.8483, "step": 2109 }, { "epoch": 1.9655172413793105, "loss_cot": 0.5488321781158447, "loss_nocot": 0.3403766453266144, "step": 2109 }, { "epoch": 1.9664492078285183, "grad_norm": 0.6428320961772727, "learning_rate": 7.65619606489472e-06, "loss": 0.8768, "step": 2110 }, { "epoch": 1.9664492078285183, "loss_cot": 0.5042811632156372, "loss_nocot": 0.38541263341903687, "step": 2110 }, { "epoch": 1.967381174277726, "grad_norm": 0.6919702914324773, "learning_rate": 7.649292371418709e-06, "loss": 0.9726, "step": 2111 }, { "epoch": 1.967381174277726, "loss_cot": 0.5174698233604431, "loss_nocot": 0.32095447182655334, "step": 2111 }, { "epoch": 1.9683131407269339, "grad_norm": 0.6141173799170063, "learning_rate": 7.6423886779427e-06, "loss": 0.8331, "step": 2112 }, { "epoch": 1.9683131407269339, "loss_cot": 0.47961148619651794, "loss_nocot": 0.40214288234710693, "step": 2112 }, { "epoch": 1.9692451071761417, "grad_norm": 0.6017895036806644, "learning_rate": 7.63548498446669e-06, "loss": 0.8342, "step": 2113 }, { "epoch": 1.9692451071761417, "loss_cot": 0.4834802746772766, "loss_nocot": 0.37852799892425537, "step": 2113 }, { "epoch": 1.9701770736253494, "grad_norm": 0.6733703666713139, "learning_rate": 7.628581290990681e-06, "loss": 0.9112, "step": 2114 }, { "epoch": 1.9701770736253494, "loss_cot": 0.4743978977203369, "loss_nocot": 0.4165835976600647, "step": 2114 }, { "epoch": 1.9711090400745572, "grad_norm": 0.6165298484639357, "learning_rate": 7.621677597514671e-06, "loss": 0.829, "step": 2115 }, { "epoch": 1.9711090400745572, "loss_cot": 0.49101752042770386, "loss_nocot": 0.5211883187294006, "step": 2115 }, { "epoch": 1.972041006523765, "grad_norm": 0.6232016076967712, "learning_rate": 7.614773904038662e-06, "loss": 0.882, "step": 2116 }, { "epoch": 1.972041006523765, "loss_cot": 0.4819696843624115, "loss_nocot": 0.2767386734485626, "step": 2116 }, { "epoch": 1.972972972972973, "grad_norm": 0.6219385706256344, "learning_rate": 7.6078702105626516e-06, "loss": 0.8293, "step": 2117 }, { "epoch": 1.972972972972973, "loss_cot": 0.5562058091163635, "loss_nocot": 0.4384424090385437, "step": 2117 }, { "epoch": 1.9739049394221808, "grad_norm": 0.6828171647591592, "learning_rate": 7.600966517086642e-06, "loss": 0.9891, "step": 2118 }, { "epoch": 1.9739049394221808, "loss_cot": 0.40799713134765625, "loss_nocot": 0.3956957757472992, "step": 2118 }, { "epoch": 1.9748369058713886, "grad_norm": 0.6123638127533574, "learning_rate": 7.594062823610633e-06, "loss": 0.8375, "step": 2119 }, { "epoch": 1.9748369058713886, "loss_cot": 0.48035576939582825, "loss_nocot": 0.39328041672706604, "step": 2119 }, { "epoch": 1.9757688723205966, "grad_norm": 0.6005606750026762, "learning_rate": 7.587159130134623e-06, "loss": 0.7813, "step": 2120 }, { "epoch": 1.9757688723205966, "loss_cot": 0.5549098253250122, "loss_nocot": 0.4235258102416992, "step": 2120 }, { "epoch": 1.9767008387698044, "grad_norm": 0.6391343402828, "learning_rate": 7.580255436658614e-06, "loss": 0.8818, "step": 2121 }, { "epoch": 1.9767008387698044, "loss_cot": 0.461577832698822, "loss_nocot": 0.3032688498497009, "step": 2121 }, { "epoch": 1.9776328052190122, "grad_norm": 0.6804894706835627, "learning_rate": 7.5733517431826035e-06, "loss": 0.9312, "step": 2122 }, { "epoch": 1.9776328052190122, "loss_cot": 0.46213090419769287, "loss_nocot": 0.3220868706703186, "step": 2122 }, { "epoch": 1.97856477166822, "grad_norm": 0.6282282209189618, "learning_rate": 7.566448049706594e-06, "loss": 0.8633, "step": 2123 }, { "epoch": 1.97856477166822, "loss_cot": 0.513740599155426, "loss_nocot": 0.36585935950279236, "step": 2123 }, { "epoch": 1.9794967381174278, "grad_norm": 0.6124137905980696, "learning_rate": 7.559544356230583e-06, "loss": 0.8326, "step": 2124 }, { "epoch": 1.9794967381174278, "loss_cot": 0.4813849925994873, "loss_nocot": 0.30577293038368225, "step": 2124 }, { "epoch": 1.9804287045666356, "grad_norm": 0.5971200444099566, "learning_rate": 7.552640662754575e-06, "loss": 0.7964, "step": 2125 }, { "epoch": 1.9804287045666356, "loss_cot": 0.5033297538757324, "loss_nocot": 0.3845515549182892, "step": 2125 }, { "epoch": 1.9813606710158433, "grad_norm": 0.6126880561610375, "learning_rate": 7.545736969278564e-06, "loss": 0.8059, "step": 2126 }, { "epoch": 1.9813606710158433, "loss_cot": 0.4450299143791199, "loss_nocot": 0.3656204342842102, "step": 2126 }, { "epoch": 1.9822926374650511, "grad_norm": 0.6187991891138322, "learning_rate": 7.5388332758025555e-06, "loss": 0.848, "step": 2127 }, { "epoch": 1.9822926374650511, "loss_cot": 0.594595193862915, "loss_nocot": 0.350493848323822, "step": 2127 }, { "epoch": 1.983224603914259, "grad_norm": 0.5928467288158791, "learning_rate": 7.5319295823265445e-06, "loss": 0.8603, "step": 2128 }, { "epoch": 1.983224603914259, "loss_cot": 0.4605376124382019, "loss_nocot": 0.29569974541664124, "step": 2128 }, { "epoch": 1.984156570363467, "grad_norm": 0.6194975553713015, "learning_rate": 7.525025888850535e-06, "loss": 0.7975, "step": 2129 }, { "epoch": 1.984156570363467, "loss_cot": 0.5363701581954956, "loss_nocot": 0.3244205117225647, "step": 2129 }, { "epoch": 1.9850885368126747, "grad_norm": 0.6175975237953917, "learning_rate": 7.518122195374527e-06, "loss": 0.835, "step": 2130 }, { "epoch": 1.9850885368126747, "loss_cot": 0.47237783670425415, "loss_nocot": 0.30357152223587036, "step": 2130 }, { "epoch": 1.9860205032618827, "grad_norm": 0.6170692780840095, "learning_rate": 7.511218501898516e-06, "loss": 0.8438, "step": 2131 }, { "epoch": 1.9860205032618827, "loss_cot": 0.47873127460479736, "loss_nocot": 0.4070214331150055, "step": 2131 }, { "epoch": 1.9869524697110905, "grad_norm": 0.6030854479085582, "learning_rate": 7.504314808422507e-06, "loss": 0.8046, "step": 2132 }, { "epoch": 1.9869524697110905, "loss_cot": 0.41281288862228394, "loss_nocot": 0.3223102390766144, "step": 2132 }, { "epoch": 1.9878844361602983, "grad_norm": 0.7329165985541699, "learning_rate": 7.4974111149464965e-06, "loss": 0.8534, "step": 2133 }, { "epoch": 1.9878844361602983, "loss_cot": 0.5443917512893677, "loss_nocot": 0.2866746783256531, "step": 2133 }, { "epoch": 1.988816402609506, "grad_norm": 0.5703757927607608, "learning_rate": 7.490507421470487e-06, "loss": 0.7964, "step": 2134 }, { "epoch": 1.988816402609506, "loss_cot": 0.5216517448425293, "loss_nocot": 0.3659076392650604, "step": 2134 }, { "epoch": 1.9897483690587139, "grad_norm": 0.5656805094121408, "learning_rate": 7.483603727994477e-06, "loss": 0.8002, "step": 2135 }, { "epoch": 1.9897483690587139, "loss_cot": 0.40765297412872314, "loss_nocot": 0.37350723147392273, "step": 2135 }, { "epoch": 1.9906803355079217, "grad_norm": 0.6303934877968514, "learning_rate": 7.476700034518468e-06, "loss": 0.8649, "step": 2136 }, { "epoch": 1.9906803355079217, "loss_cot": 0.5415270328521729, "loss_nocot": 0.26002174615859985, "step": 2136 }, { "epoch": 1.9916123019571295, "grad_norm": 0.6123796772721348, "learning_rate": 7.469796341042458e-06, "loss": 0.8552, "step": 2137 }, { "epoch": 1.9916123019571295, "loss_cot": 0.4531547427177429, "loss_nocot": 0.25001654028892517, "step": 2137 }, { "epoch": 1.9925442684063372, "grad_norm": 0.6147894163905666, "learning_rate": 7.4628926475664485e-06, "loss": 0.8158, "step": 2138 }, { "epoch": 1.9925442684063372, "loss_cot": 0.42909157276153564, "loss_nocot": 0.39625757932662964, "step": 2138 }, { "epoch": 1.993476234855545, "grad_norm": 0.6430475201059337, "learning_rate": 7.455988954090439e-06, "loss": 0.8635, "step": 2139 }, { "epoch": 1.993476234855545, "loss_cot": 0.5371889472007751, "loss_nocot": 0.41674888134002686, "step": 2139 }, { "epoch": 1.994408201304753, "grad_norm": 0.5935151273546159, "learning_rate": 7.449085260614429e-06, "loss": 0.8309, "step": 2140 }, { "epoch": 1.994408201304753, "loss_cot": 0.4388512372970581, "loss_nocot": 0.3180384635925293, "step": 2140 }, { "epoch": 1.9953401677539608, "grad_norm": 0.6680795280419762, "learning_rate": 7.44218156713842e-06, "loss": 0.8641, "step": 2141 }, { "epoch": 1.9953401677539608, "loss_cot": 0.49563607573509216, "loss_nocot": 0.41267961263656616, "step": 2141 }, { "epoch": 1.9962721342031688, "grad_norm": 0.6171445430754136, "learning_rate": 7.43527787366241e-06, "loss": 0.8359, "step": 2142 }, { "epoch": 1.9962721342031688, "loss_cot": 0.45424607396125793, "loss_nocot": 0.352103590965271, "step": 2142 }, { "epoch": 1.9972041006523766, "grad_norm": 0.6425082719939932, "learning_rate": 7.4283741801864004e-06, "loss": 0.8217, "step": 2143 }, { "epoch": 1.9972041006523766, "loss_cot": 0.45075249671936035, "loss_nocot": 0.3164307773113251, "step": 2143 }, { "epoch": 1.9981360671015844, "grad_norm": 0.6297784160652672, "learning_rate": 7.42147048671039e-06, "loss": 0.8689, "step": 2144 }, { "epoch": 1.9981360671015844, "loss_cot": 0.5645795464515686, "loss_nocot": 0.350711464881897, "step": 2144 }, { "epoch": 1.9990680335507922, "grad_norm": 0.6447587572014488, "learning_rate": 7.414566793234381e-06, "loss": 0.8621, "step": 2145 }, { "epoch": 1.9990680335507922, "loss_cot": 0.42749956250190735, "loss_nocot": 0.3510480523109436, "step": 2145 }, { "epoch": 2.0, "grad_norm": 0.5918184066143014, "learning_rate": 7.407663099758371e-06, "loss": 0.7807, "step": 2146 }, { "epoch": 2.0, "loss_cot": 0.5063148736953735, "loss_nocot": 0.2751339077949524, "step": 2146 }, { "epoch": 2.000931966449208, "grad_norm": 0.5790909320963993, "learning_rate": 7.400759406282362e-06, "loss": 0.7404, "step": 2147 }, { "epoch": 2.000931966449208, "loss_cot": 0.5110547542572021, "loss_nocot": 0.2078242301940918, "step": 2147 }, { "epoch": 2.0018639328984156, "grad_norm": 0.5264536443294799, "learning_rate": 7.3938557128063516e-06, "loss": 0.7061, "step": 2148 }, { "epoch": 2.0018639328984156, "loss_cot": 0.452187716960907, "loss_nocot": 0.23146727681159973, "step": 2148 }, { "epoch": 2.0027958993476234, "grad_norm": 0.584752625419171, "learning_rate": 7.386952019330342e-06, "loss": 0.7723, "step": 2149 }, { "epoch": 2.0027958993476234, "loss_cot": 0.4596843123435974, "loss_nocot": 0.2723137140274048, "step": 2149 }, { "epoch": 2.003727865796831, "grad_norm": 0.6415698622327001, "learning_rate": 7.380048325854333e-06, "loss": 0.7694, "step": 2150 }, { "epoch": 2.003727865796831, "loss_cot": 0.5049436092376709, "loss_nocot": 0.2930569052696228, "step": 2150 }, { "epoch": 2.004659832246039, "grad_norm": 0.6263361527001483, "learning_rate": 7.373144632378323e-06, "loss": 0.8159, "step": 2151 }, { "epoch": 2.004659832246039, "loss_cot": 0.48899778723716736, "loss_nocot": 0.31296616792678833, "step": 2151 }, { "epoch": 2.005591798695247, "grad_norm": 0.5633251583160828, "learning_rate": 7.366240938902314e-06, "loss": 0.7441, "step": 2152 }, { "epoch": 2.005591798695247, "loss_cot": 0.4852796196937561, "loss_nocot": 0.2786470055580139, "step": 2152 }, { "epoch": 2.006523765144455, "grad_norm": 0.6043828433913858, "learning_rate": 7.3593372454263035e-06, "loss": 0.8191, "step": 2153 }, { "epoch": 2.006523765144455, "loss_cot": 0.5163220763206482, "loss_nocot": 0.27185380458831787, "step": 2153 }, { "epoch": 2.0074557315936628, "grad_norm": 0.6070035708909612, "learning_rate": 7.352433551950294e-06, "loss": 0.7915, "step": 2154 }, { "epoch": 2.0074557315936628, "loss_cot": 0.4697286784648895, "loss_nocot": 0.2872334122657776, "step": 2154 }, { "epoch": 2.0083876980428705, "grad_norm": 0.5786813115573813, "learning_rate": 7.345529858474284e-06, "loss": 0.752, "step": 2155 }, { "epoch": 2.0083876980428705, "loss_cot": 0.48874133825302124, "loss_nocot": 0.2993541359901428, "step": 2155 }, { "epoch": 2.0093196644920783, "grad_norm": 0.5311294518987498, "learning_rate": 7.338626164998275e-06, "loss": 0.7418, "step": 2156 }, { "epoch": 2.0093196644920783, "loss_cot": 0.47618162631988525, "loss_nocot": 0.2543139159679413, "step": 2156 }, { "epoch": 2.010251630941286, "grad_norm": 0.5873630519779417, "learning_rate": 7.331722471522265e-06, "loss": 0.7678, "step": 2157 }, { "epoch": 2.010251630941286, "loss_cot": 0.432364821434021, "loss_nocot": 0.29808056354522705, "step": 2157 }, { "epoch": 2.011183597390494, "grad_norm": 0.5878891385301585, "learning_rate": 7.3248187780462555e-06, "loss": 0.7821, "step": 2158 }, { "epoch": 2.011183597390494, "loss_cot": 0.4917373061180115, "loss_nocot": 0.3034052550792694, "step": 2158 }, { "epoch": 2.0121155638397017, "grad_norm": 0.6148340346469544, "learning_rate": 7.317915084570245e-06, "loss": 0.7599, "step": 2159 }, { "epoch": 2.0121155638397017, "loss_cot": 0.5279329419136047, "loss_nocot": 0.21165044605731964, "step": 2159 }, { "epoch": 2.0130475302889095, "grad_norm": 0.5991497964399276, "learning_rate": 7.311011391094236e-06, "loss": 0.7454, "step": 2160 }, { "epoch": 2.0130475302889095, "loss_cot": 0.46555715799331665, "loss_nocot": 0.2142878621816635, "step": 2160 }, { "epoch": 2.0139794967381173, "grad_norm": 0.6355258731590413, "learning_rate": 7.304107697618227e-06, "loss": 0.7933, "step": 2161 }, { "epoch": 2.0139794967381173, "loss_cot": 0.43254354596138, "loss_nocot": 0.26779764890670776, "step": 2161 }, { "epoch": 2.014911463187325, "grad_norm": 0.630596088770694, "learning_rate": 7.297204004142217e-06, "loss": 0.7145, "step": 2162 }, { "epoch": 2.014911463187325, "loss_cot": 0.5679255723953247, "loss_nocot": 0.2305373251438141, "step": 2162 }, { "epoch": 2.0158434296365333, "grad_norm": 0.6510135091340724, "learning_rate": 7.2903003106662075e-06, "loss": 0.7387, "step": 2163 }, { "epoch": 2.0158434296365333, "loss_cot": 0.5337595343589783, "loss_nocot": 0.2748110294342041, "step": 2163 }, { "epoch": 2.016775396085741, "grad_norm": 0.7421445062773725, "learning_rate": 7.283396617190197e-06, "loss": 0.7482, "step": 2164 }, { "epoch": 2.016775396085741, "loss_cot": 0.5018220543861389, "loss_nocot": 0.3264148235321045, "step": 2164 }, { "epoch": 2.017707362534949, "grad_norm": 0.6308350511649395, "learning_rate": 7.276492923714188e-06, "loss": 0.781, "step": 2165 }, { "epoch": 2.017707362534949, "loss_cot": 0.573140025138855, "loss_nocot": 0.2842129170894623, "step": 2165 }, { "epoch": 2.0186393289841567, "grad_norm": 0.6209893518214143, "learning_rate": 7.269589230238178e-06, "loss": 0.7193, "step": 2166 }, { "epoch": 2.0186393289841567, "loss_cot": 0.5931062698364258, "loss_nocot": 0.29955387115478516, "step": 2166 }, { "epoch": 2.0195712954333644, "grad_norm": 0.7082032795732107, "learning_rate": 7.262685536762169e-06, "loss": 0.7912, "step": 2167 }, { "epoch": 2.0195712954333644, "loss_cot": 0.5147140622138977, "loss_nocot": 0.3929263949394226, "step": 2167 }, { "epoch": 2.0205032618825722, "grad_norm": 0.6750612014560983, "learning_rate": 7.255781843286159e-06, "loss": 0.8117, "step": 2168 }, { "epoch": 2.0205032618825722, "loss_cot": 0.482356458902359, "loss_nocot": 0.2151077687740326, "step": 2168 }, { "epoch": 2.02143522833178, "grad_norm": 0.5912445540628638, "learning_rate": 7.248878149810149e-06, "loss": 0.7111, "step": 2169 }, { "epoch": 2.02143522833178, "loss_cot": 0.4460352063179016, "loss_nocot": 0.17494064569473267, "step": 2169 }, { "epoch": 2.022367194780988, "grad_norm": 0.595897221006365, "learning_rate": 7.24197445633414e-06, "loss": 0.7311, "step": 2170 }, { "epoch": 2.022367194780988, "loss_cot": 0.4790748953819275, "loss_nocot": 0.28638386726379395, "step": 2170 }, { "epoch": 2.0232991612301956, "grad_norm": 0.6030710057383647, "learning_rate": 7.23507076285813e-06, "loss": 0.7363, "step": 2171 }, { "epoch": 2.0232991612301956, "loss_cot": 0.4874011278152466, "loss_nocot": 0.282709002494812, "step": 2171 }, { "epoch": 2.0242311276794034, "grad_norm": 0.6063034727646092, "learning_rate": 7.228167069382121e-06, "loss": 0.7485, "step": 2172 }, { "epoch": 2.0242311276794034, "loss_cot": 0.5375598669052124, "loss_nocot": 0.3317708373069763, "step": 2172 }, { "epoch": 2.025163094128611, "grad_norm": 0.6289118355505523, "learning_rate": 7.2212633759061106e-06, "loss": 0.7723, "step": 2173 }, { "epoch": 2.025163094128611, "loss_cot": 0.530107319355011, "loss_nocot": 0.2892037034034729, "step": 2173 }, { "epoch": 2.0260950605778194, "grad_norm": 0.6582003475484535, "learning_rate": 7.214359682430101e-06, "loss": 0.7925, "step": 2174 }, { "epoch": 2.0260950605778194, "loss_cot": 0.45623302459716797, "loss_nocot": 0.23744599521160126, "step": 2174 }, { "epoch": 2.027027027027027, "grad_norm": 0.6001047407632953, "learning_rate": 7.20745598895409e-06, "loss": 0.7232, "step": 2175 }, { "epoch": 2.027027027027027, "loss_cot": 0.5441352128982544, "loss_nocot": 0.2198764532804489, "step": 2175 }, { "epoch": 2.027958993476235, "grad_norm": 0.5893372404833392, "learning_rate": 7.200552295478082e-06, "loss": 0.7355, "step": 2176 }, { "epoch": 2.027958993476235, "loss_cot": 0.5127980709075928, "loss_nocot": 0.21139481663703918, "step": 2176 }, { "epoch": 2.0288909599254428, "grad_norm": 0.6688837834370563, "learning_rate": 7.193648602002071e-06, "loss": 0.8308, "step": 2177 }, { "epoch": 2.0288909599254428, "loss_cot": 0.4956958293914795, "loss_nocot": 0.22419990599155426, "step": 2177 }, { "epoch": 2.0298229263746506, "grad_norm": 0.622898690017902, "learning_rate": 7.1867449085260625e-06, "loss": 0.7642, "step": 2178 }, { "epoch": 2.0298229263746506, "loss_cot": 0.5384262800216675, "loss_nocot": 0.22005528211593628, "step": 2178 }, { "epoch": 2.0307548928238583, "grad_norm": 0.5397418661708725, "learning_rate": 7.1798412150500516e-06, "loss": 0.7211, "step": 2179 }, { "epoch": 2.0307548928238583, "loss_cot": 0.5396438241004944, "loss_nocot": 0.2929450273513794, "step": 2179 }, { "epoch": 2.031686859273066, "grad_norm": 0.6488632040652199, "learning_rate": 7.172937521574042e-06, "loss": 0.7825, "step": 2180 }, { "epoch": 2.031686859273066, "loss_cot": 0.5015982389450073, "loss_nocot": 0.1949855387210846, "step": 2180 }, { "epoch": 2.032618825722274, "grad_norm": 0.5894047046376147, "learning_rate": 7.166033828098034e-06, "loss": 0.7826, "step": 2181 }, { "epoch": 2.032618825722274, "loss_cot": 0.5173017978668213, "loss_nocot": 0.2446620613336563, "step": 2181 }, { "epoch": 2.0335507921714817, "grad_norm": 0.6119621551611515, "learning_rate": 7.159130134622023e-06, "loss": 0.743, "step": 2182 }, { "epoch": 2.0335507921714817, "loss_cot": 0.4905954599380493, "loss_nocot": 0.2569734454154968, "step": 2182 }, { "epoch": 2.0344827586206895, "grad_norm": 0.5880626665584004, "learning_rate": 7.152226441146014e-06, "loss": 0.7346, "step": 2183 }, { "epoch": 2.0344827586206895, "loss_cot": 0.5078799724578857, "loss_nocot": 0.22537727653980255, "step": 2183 }, { "epoch": 2.0354147250698973, "grad_norm": 0.5859031121582188, "learning_rate": 7.1453227476700035e-06, "loss": 0.7184, "step": 2184 }, { "epoch": 2.0354147250698973, "loss_cot": 0.4106627106666565, "loss_nocot": 0.1785258650779724, "step": 2184 }, { "epoch": 2.0363466915191055, "grad_norm": 0.5891991501556488, "learning_rate": 7.138419054193994e-06, "loss": 0.6992, "step": 2185 }, { "epoch": 2.0363466915191055, "loss_cot": 0.48343586921691895, "loss_nocot": 0.22087283432483673, "step": 2185 }, { "epoch": 2.0372786579683133, "grad_norm": 0.6447825098649616, "learning_rate": 7.131515360717984e-06, "loss": 0.7427, "step": 2186 }, { "epoch": 2.0372786579683133, "loss_cot": 0.5177657604217529, "loss_nocot": 0.2715245485305786, "step": 2186 }, { "epoch": 2.038210624417521, "grad_norm": 0.6029699183099396, "learning_rate": 7.124611667241975e-06, "loss": 0.7676, "step": 2187 }, { "epoch": 2.038210624417521, "loss_cot": 0.5096319913864136, "loss_nocot": 0.2992444336414337, "step": 2187 }, { "epoch": 2.039142590866729, "grad_norm": 0.6187349183373163, "learning_rate": 7.117707973765965e-06, "loss": 0.7536, "step": 2188 }, { "epoch": 2.039142590866729, "loss_cot": 0.41814279556274414, "loss_nocot": 0.26651981472969055, "step": 2188 }, { "epoch": 2.0400745573159367, "grad_norm": 0.6029007285814638, "learning_rate": 7.1108042802899555e-06, "loss": 0.733, "step": 2189 }, { "epoch": 2.0400745573159367, "loss_cot": 0.5120385885238647, "loss_nocot": 0.24420449137687683, "step": 2189 }, { "epoch": 2.0410065237651445, "grad_norm": 0.6241244244211278, "learning_rate": 7.103900586813946e-06, "loss": 0.7627, "step": 2190 }, { "epoch": 2.0410065237651445, "loss_cot": 0.5696752071380615, "loss_nocot": 0.5148236751556396, "step": 2190 }, { "epoch": 2.0419384902143523, "grad_norm": 0.7076066359668791, "learning_rate": 7.096996893337936e-06, "loss": 0.8667, "step": 2191 }, { "epoch": 2.0419384902143523, "loss_cot": 0.5032553672790527, "loss_nocot": 0.3112058639526367, "step": 2191 }, { "epoch": 2.04287045666356, "grad_norm": 0.6798278184734448, "learning_rate": 7.090093199861927e-06, "loss": 0.8045, "step": 2192 }, { "epoch": 2.04287045666356, "loss_cot": 0.5012984871864319, "loss_nocot": 0.31903785467147827, "step": 2192 }, { "epoch": 2.043802423112768, "grad_norm": 0.6446292101926334, "learning_rate": 7.083189506385917e-06, "loss": 0.7263, "step": 2193 }, { "epoch": 2.043802423112768, "loss_cot": 0.49153614044189453, "loss_nocot": 0.25665968656539917, "step": 2193 }, { "epoch": 2.0447343895619756, "grad_norm": 0.6506978787993796, "learning_rate": 7.0762858129099075e-06, "loss": 0.7521, "step": 2194 }, { "epoch": 2.0447343895619756, "loss_cot": 0.5657792687416077, "loss_nocot": 0.26205137372016907, "step": 2194 }, { "epoch": 2.0456663560111834, "grad_norm": 0.623134746040012, "learning_rate": 7.069382119433897e-06, "loss": 0.7975, "step": 2195 }, { "epoch": 2.0456663560111834, "loss_cot": 0.5386648178100586, "loss_nocot": 0.3111107349395752, "step": 2195 }, { "epoch": 2.0465983224603916, "grad_norm": 0.63878380810594, "learning_rate": 7.062478425957888e-06, "loss": 0.7785, "step": 2196 }, { "epoch": 2.0465983224603916, "loss_cot": 0.4935891628265381, "loss_nocot": 0.2572527527809143, "step": 2196 }, { "epoch": 2.0475302889095994, "grad_norm": 0.633231195522786, "learning_rate": 7.055574732481878e-06, "loss": 0.7472, "step": 2197 }, { "epoch": 2.0475302889095994, "loss_cot": 0.5955255627632141, "loss_nocot": 0.26621121168136597, "step": 2197 }, { "epoch": 2.048462255358807, "grad_norm": 0.6410432700632066, "learning_rate": 7.048671039005869e-06, "loss": 0.7593, "step": 2198 }, { "epoch": 2.048462255358807, "loss_cot": 0.5673276782035828, "loss_nocot": 0.3002014756202698, "step": 2198 }, { "epoch": 2.049394221808015, "grad_norm": 0.6418306995309475, "learning_rate": 7.041767345529859e-06, "loss": 0.8187, "step": 2199 }, { "epoch": 2.049394221808015, "loss_cot": 0.4524160325527191, "loss_nocot": 0.24763603508472443, "step": 2199 }, { "epoch": 2.050326188257223, "grad_norm": 0.6277331953001679, "learning_rate": 7.034863652053849e-06, "loss": 0.767, "step": 2200 }, { "epoch": 2.050326188257223, "loss_cot": 0.5207799673080444, "loss_nocot": 0.21395103633403778, "step": 2200 }, { "epoch": 2.0512581547064306, "grad_norm": 0.5789861482799192, "learning_rate": 7.02795995857784e-06, "loss": 0.7052, "step": 2201 }, { "epoch": 2.0512581547064306, "loss_cot": 0.49954313039779663, "loss_nocot": 0.25714612007141113, "step": 2201 }, { "epoch": 2.0521901211556384, "grad_norm": 0.6581168907493025, "learning_rate": 7.02105626510183e-06, "loss": 0.7872, "step": 2202 }, { "epoch": 2.0521901211556384, "loss_cot": 0.49816688895225525, "loss_nocot": 0.2649959623813629, "step": 2202 }, { "epoch": 2.053122087604846, "grad_norm": 0.6079308891766381, "learning_rate": 7.014152571625821e-06, "loss": 0.7326, "step": 2203 }, { "epoch": 2.053122087604846, "loss_cot": 0.42540299892425537, "loss_nocot": 0.22582118213176727, "step": 2203 }, { "epoch": 2.054054054054054, "grad_norm": 0.6268617279209523, "learning_rate": 7.0072488781498106e-06, "loss": 0.7161, "step": 2204 }, { "epoch": 2.054054054054054, "loss_cot": 0.5090879201889038, "loss_nocot": 0.19328981637954712, "step": 2204 }, { "epoch": 2.0549860205032617, "grad_norm": 0.6593879877092145, "learning_rate": 7.000345184673801e-06, "loss": 0.7436, "step": 2205 }, { "epoch": 2.0549860205032617, "loss_cot": 0.4871932864189148, "loss_nocot": 0.27313587069511414, "step": 2205 }, { "epoch": 2.0559179869524695, "grad_norm": 0.6662260907905665, "learning_rate": 6.993441491197791e-06, "loss": 0.8076, "step": 2206 }, { "epoch": 2.0559179869524695, "loss_cot": 0.4697513282299042, "loss_nocot": 0.2578495442867279, "step": 2206 }, { "epoch": 2.0568499534016778, "grad_norm": 0.643085591610667, "learning_rate": 6.986537797721782e-06, "loss": 0.7446, "step": 2207 }, { "epoch": 2.0568499534016778, "loss_cot": 0.458071231842041, "loss_nocot": 0.2514258027076721, "step": 2207 }, { "epoch": 2.0577819198508855, "grad_norm": 0.5818073297239312, "learning_rate": 6.979634104245772e-06, "loss": 0.728, "step": 2208 }, { "epoch": 2.0577819198508855, "loss_cot": 0.4735347032546997, "loss_nocot": 0.21867460012435913, "step": 2208 }, { "epoch": 2.0587138863000933, "grad_norm": 0.6024158719332339, "learning_rate": 6.9727304107697625e-06, "loss": 0.7278, "step": 2209 }, { "epoch": 2.0587138863000933, "loss_cot": 0.5070505738258362, "loss_nocot": 0.32515862584114075, "step": 2209 }, { "epoch": 2.059645852749301, "grad_norm": 0.6165416099050951, "learning_rate": 6.965826717293753e-06, "loss": 0.7273, "step": 2210 }, { "epoch": 2.059645852749301, "loss_cot": 0.5022174119949341, "loss_nocot": 0.20698347687721252, "step": 2210 }, { "epoch": 2.060577819198509, "grad_norm": 0.5807968174329231, "learning_rate": 6.958923023817743e-06, "loss": 0.7148, "step": 2211 }, { "epoch": 2.060577819198509, "loss_cot": 0.5343444347381592, "loss_nocot": 0.2321859747171402, "step": 2211 }, { "epoch": 2.0615097856477167, "grad_norm": 0.6216036946581176, "learning_rate": 6.952019330341734e-06, "loss": 0.7452, "step": 2212 }, { "epoch": 2.0615097856477167, "loss_cot": 0.46115759015083313, "loss_nocot": 0.2468537986278534, "step": 2212 }, { "epoch": 2.0624417520969245, "grad_norm": 0.621740725116705, "learning_rate": 6.945115636865724e-06, "loss": 0.7551, "step": 2213 }, { "epoch": 2.0624417520969245, "loss_cot": 0.500333309173584, "loss_nocot": 0.23676757514476776, "step": 2213 }, { "epoch": 2.0633737185461323, "grad_norm": 0.5825608484848054, "learning_rate": 6.9382119433897145e-06, "loss": 0.7376, "step": 2214 }, { "epoch": 2.0633737185461323, "loss_cot": 0.5183586478233337, "loss_nocot": 0.2149895280599594, "step": 2214 }, { "epoch": 2.06430568499534, "grad_norm": 0.6222844254878921, "learning_rate": 6.931308249913704e-06, "loss": 0.7727, "step": 2215 }, { "epoch": 2.06430568499534, "loss_cot": 0.4177071452140808, "loss_nocot": 0.29038605093955994, "step": 2215 }, { "epoch": 2.065237651444548, "grad_norm": 0.6241930970986124, "learning_rate": 6.924404556437695e-06, "loss": 0.7383, "step": 2216 }, { "epoch": 2.065237651444548, "loss_cot": 0.5016688108444214, "loss_nocot": 0.26403748989105225, "step": 2216 }, { "epoch": 2.0661696178937556, "grad_norm": 0.6392637615060194, "learning_rate": 6.917500862961685e-06, "loss": 0.7623, "step": 2217 }, { "epoch": 2.0661696178937556, "loss_cot": 0.4133419096469879, "loss_nocot": 0.17268739640712738, "step": 2217 }, { "epoch": 2.0671015843429634, "grad_norm": 0.5870214785340394, "learning_rate": 6.910597169485676e-06, "loss": 0.6892, "step": 2218 }, { "epoch": 2.0671015843429634, "loss_cot": 0.5292990207672119, "loss_nocot": 0.25285691022872925, "step": 2218 }, { "epoch": 2.0680335507921717, "grad_norm": 0.6336746766191643, "learning_rate": 6.903693476009666e-06, "loss": 0.7762, "step": 2219 }, { "epoch": 2.0680335507921717, "loss_cot": 0.4811863303184509, "loss_nocot": 0.3348786532878876, "step": 2219 }, { "epoch": 2.0689655172413794, "grad_norm": 0.7080943107509284, "learning_rate": 6.896789782533656e-06, "loss": 0.7792, "step": 2220 }, { "epoch": 2.0689655172413794, "loss_cot": 0.4686201214790344, "loss_nocot": 0.3023153245449066, "step": 2220 }, { "epoch": 2.0698974836905872, "grad_norm": 0.6347232226480671, "learning_rate": 6.889886089057647e-06, "loss": 0.7516, "step": 2221 }, { "epoch": 2.0698974836905872, "loss_cot": 0.4726859927177429, "loss_nocot": 0.236513152718544, "step": 2221 }, { "epoch": 2.070829450139795, "grad_norm": 0.6406706110074076, "learning_rate": 6.882982395581637e-06, "loss": 0.7634, "step": 2222 }, { "epoch": 2.070829450139795, "loss_cot": 0.47965261340141296, "loss_nocot": 0.3190292418003082, "step": 2222 }, { "epoch": 2.071761416589003, "grad_norm": 0.6728230602021635, "learning_rate": 6.876078702105628e-06, "loss": 0.761, "step": 2223 }, { "epoch": 2.071761416589003, "loss_cot": 0.5014488101005554, "loss_nocot": 0.1959477961063385, "step": 2223 }, { "epoch": 2.0726933830382106, "grad_norm": 0.6557393163450987, "learning_rate": 6.869175008629618e-06, "loss": 0.7591, "step": 2224 }, { "epoch": 2.0726933830382106, "loss_cot": 0.4308757781982422, "loss_nocot": 0.2913239002227783, "step": 2224 }, { "epoch": 2.0736253494874184, "grad_norm": 0.6594625529296905, "learning_rate": 6.862271315153608e-06, "loss": 0.7779, "step": 2225 }, { "epoch": 2.0736253494874184, "loss_cot": 0.46545684337615967, "loss_nocot": 0.19742991030216217, "step": 2225 }, { "epoch": 2.074557315936626, "grad_norm": 0.6211778526613324, "learning_rate": 6.855367621677597e-06, "loss": 0.6905, "step": 2226 }, { "epoch": 2.074557315936626, "loss_cot": 0.5694681406021118, "loss_nocot": 0.3444597125053406, "step": 2226 }, { "epoch": 2.075489282385834, "grad_norm": 0.7066995341336266, "learning_rate": 6.848463928201589e-06, "loss": 0.8021, "step": 2227 }, { "epoch": 2.075489282385834, "loss_cot": 0.4749389886856079, "loss_nocot": 0.31278514862060547, "step": 2227 }, { "epoch": 2.0764212488350418, "grad_norm": 0.6047657060123984, "learning_rate": 6.841560234725578e-06, "loss": 0.7546, "step": 2228 }, { "epoch": 2.0764212488350418, "loss_cot": 0.49892351031303406, "loss_nocot": 0.23320886492729187, "step": 2228 }, { "epoch": 2.0773532152842495, "grad_norm": 0.632664505513178, "learning_rate": 6.834656541249569e-06, "loss": 0.7292, "step": 2229 }, { "epoch": 2.0773532152842495, "loss_cot": 0.46963071823120117, "loss_nocot": 0.28722095489501953, "step": 2229 }, { "epoch": 2.0782851817334578, "grad_norm": 0.5673744054830471, "learning_rate": 6.82775284777356e-06, "loss": 0.7016, "step": 2230 }, { "epoch": 2.0782851817334578, "loss_cot": 0.5921226739883423, "loss_nocot": 0.322613000869751, "step": 2230 }, { "epoch": 2.0792171481826656, "grad_norm": 0.7168974911150064, "learning_rate": 6.820849154297549e-06, "loss": 0.8473, "step": 2231 }, { "epoch": 2.0792171481826656, "loss_cot": 0.5296406745910645, "loss_nocot": 0.2669958472251892, "step": 2231 }, { "epoch": 2.0801491146318734, "grad_norm": 0.6335376817718938, "learning_rate": 6.813945460821541e-06, "loss": 0.7185, "step": 2232 }, { "epoch": 2.0801491146318734, "loss_cot": 0.43774592876434326, "loss_nocot": 0.20426148176193237, "step": 2232 }, { "epoch": 2.081081081081081, "grad_norm": 0.643426487465445, "learning_rate": 6.80704176734553e-06, "loss": 0.7175, "step": 2233 }, { "epoch": 2.081081081081081, "loss_cot": 0.4635629653930664, "loss_nocot": 0.20574289560317993, "step": 2233 }, { "epoch": 2.082013047530289, "grad_norm": 0.5775464592480466, "learning_rate": 6.800138073869521e-06, "loss": 0.7352, "step": 2234 }, { "epoch": 2.082013047530289, "loss_cot": 0.44935664534568787, "loss_nocot": 0.3882616460323334, "step": 2234 }, { "epoch": 2.0829450139794967, "grad_norm": 0.6993856195673138, "learning_rate": 6.7932343803935106e-06, "loss": 0.7399, "step": 2235 }, { "epoch": 2.0829450139794967, "loss_cot": 0.4856802821159363, "loss_nocot": 0.2675018906593323, "step": 2235 }, { "epoch": 2.0838769804287045, "grad_norm": 0.8427882977864606, "learning_rate": 6.786330686917501e-06, "loss": 0.7697, "step": 2236 }, { "epoch": 2.0838769804287045, "loss_cot": 0.5271037220954895, "loss_nocot": 0.20695802569389343, "step": 2236 }, { "epoch": 2.0848089468779123, "grad_norm": 0.6865085727242856, "learning_rate": 6.779426993441491e-06, "loss": 0.778, "step": 2237 }, { "epoch": 2.0848089468779123, "loss_cot": 0.4996021091938019, "loss_nocot": 0.22897829115390778, "step": 2237 }, { "epoch": 2.08574091332712, "grad_norm": 0.6032421583349826, "learning_rate": 6.772523299965482e-06, "loss": 0.779, "step": 2238 }, { "epoch": 2.08574091332712, "loss_cot": 0.5318493843078613, "loss_nocot": 0.2031235694885254, "step": 2238 }, { "epoch": 2.086672879776328, "grad_norm": 0.652140667553388, "learning_rate": 6.765619606489472e-06, "loss": 0.7536, "step": 2239 }, { "epoch": 2.086672879776328, "loss_cot": 0.5003806948661804, "loss_nocot": 0.28743064403533936, "step": 2239 }, { "epoch": 2.0876048462255357, "grad_norm": 0.6427777753427029, "learning_rate": 6.7587159130134625e-06, "loss": 0.7739, "step": 2240 }, { "epoch": 2.0876048462255357, "loss_cot": 0.4936380386352539, "loss_nocot": 0.33229225873947144, "step": 2240 }, { "epoch": 2.088536812674744, "grad_norm": 0.6554371188760927, "learning_rate": 6.751812219537453e-06, "loss": 0.772, "step": 2241 }, { "epoch": 2.088536812674744, "loss_cot": 0.46683740615844727, "loss_nocot": 0.21723175048828125, "step": 2241 }, { "epoch": 2.0894687791239517, "grad_norm": 0.6200333160390039, "learning_rate": 6.744908526061443e-06, "loss": 0.7566, "step": 2242 }, { "epoch": 2.0894687791239517, "loss_cot": 0.5107567310333252, "loss_nocot": 0.2317279875278473, "step": 2242 }, { "epoch": 2.0904007455731595, "grad_norm": 0.6398829763487481, "learning_rate": 6.738004832585434e-06, "loss": 0.7033, "step": 2243 }, { "epoch": 2.0904007455731595, "loss_cot": 0.5151894688606262, "loss_nocot": 0.2889728248119354, "step": 2243 }, { "epoch": 2.0913327120223673, "grad_norm": 0.6611414186746088, "learning_rate": 6.731101139109424e-06, "loss": 0.7365, "step": 2244 }, { "epoch": 2.0913327120223673, "loss_cot": 0.5259726047515869, "loss_nocot": 0.23515017330646515, "step": 2244 }, { "epoch": 2.092264678471575, "grad_norm": 0.6275715754478558, "learning_rate": 6.7241974456334145e-06, "loss": 0.7391, "step": 2245 }, { "epoch": 2.092264678471575, "loss_cot": 0.5207613110542297, "loss_nocot": 0.23387929797172546, "step": 2245 }, { "epoch": 2.093196644920783, "grad_norm": 0.6573275527794538, "learning_rate": 6.717293752157404e-06, "loss": 0.7625, "step": 2246 }, { "epoch": 2.093196644920783, "loss_cot": 0.46900397539138794, "loss_nocot": 0.20900914072990417, "step": 2246 }, { "epoch": 2.0941286113699906, "grad_norm": 0.5711802784063581, "learning_rate": 6.710390058681395e-06, "loss": 0.7482, "step": 2247 }, { "epoch": 2.0941286113699906, "loss_cot": 0.4988064467906952, "loss_nocot": 0.20017951726913452, "step": 2247 }, { "epoch": 2.0950605778191984, "grad_norm": 0.6399025101880712, "learning_rate": 6.703486365205385e-06, "loss": 0.7406, "step": 2248 }, { "epoch": 2.0950605778191984, "loss_cot": 0.5372735261917114, "loss_nocot": 0.2589099705219269, "step": 2248 }, { "epoch": 2.095992544268406, "grad_norm": 0.7077931876046024, "learning_rate": 6.696582671729376e-06, "loss": 0.7816, "step": 2249 }, { "epoch": 2.095992544268406, "loss_cot": 0.48591485619544983, "loss_nocot": 0.3090733289718628, "step": 2249 }, { "epoch": 2.096924510717614, "grad_norm": 0.5985981764456622, "learning_rate": 6.6896789782533665e-06, "loss": 0.7303, "step": 2250 }, { "epoch": 2.096924510717614, "loss_cot": 0.5050349831581116, "loss_nocot": 0.31009578704833984, "step": 2250 }, { "epoch": 2.0978564771668218, "grad_norm": 0.6337292316307297, "learning_rate": 6.682775284777356e-06, "loss": 0.8005, "step": 2251 }, { "epoch": 2.0978564771668218, "loss_cot": 0.49697235226631165, "loss_nocot": 0.22704541683197021, "step": 2251 }, { "epoch": 2.09878844361603, "grad_norm": 0.6685707048360636, "learning_rate": 6.675871591301347e-06, "loss": 0.7705, "step": 2252 }, { "epoch": 2.09878844361603, "loss_cot": 0.5077889561653137, "loss_nocot": 0.26674553751945496, "step": 2252 }, { "epoch": 2.099720410065238, "grad_norm": 0.6659157319027508, "learning_rate": 6.668967897825337e-06, "loss": 0.772, "step": 2253 }, { "epoch": 2.099720410065238, "loss_cot": 0.4538978636264801, "loss_nocot": 0.3077273964881897, "step": 2253 }, { "epoch": 2.1006523765144456, "grad_norm": 0.7133023376334146, "learning_rate": 6.662064204349328e-06, "loss": 0.7915, "step": 2254 }, { "epoch": 2.1006523765144456, "loss_cot": 0.5200697183609009, "loss_nocot": 0.21826376020908356, "step": 2254 }, { "epoch": 2.1015843429636534, "grad_norm": 0.6244170948548199, "learning_rate": 6.655160510873318e-06, "loss": 0.7746, "step": 2255 }, { "epoch": 2.1015843429636534, "loss_cot": 0.6067367792129517, "loss_nocot": 0.3288043737411499, "step": 2255 }, { "epoch": 2.102516309412861, "grad_norm": 0.6360406069660798, "learning_rate": 6.648256817397308e-06, "loss": 0.7766, "step": 2256 }, { "epoch": 2.102516309412861, "loss_cot": 0.45739036798477173, "loss_nocot": 0.33642855286598206, "step": 2256 }, { "epoch": 2.103448275862069, "grad_norm": 0.6264835469163892, "learning_rate": 6.641353123921298e-06, "loss": 0.7336, "step": 2257 }, { "epoch": 2.103448275862069, "loss_cot": 0.4874810576438904, "loss_nocot": 0.25382277369499207, "step": 2257 }, { "epoch": 2.1043802423112767, "grad_norm": 0.6173986305882654, "learning_rate": 6.634449430445289e-06, "loss": 0.8006, "step": 2258 }, { "epoch": 2.1043802423112767, "loss_cot": 0.5067711472511292, "loss_nocot": 0.20160380005836487, "step": 2258 }, { "epoch": 2.1053122087604845, "grad_norm": 0.6246894289755309, "learning_rate": 6.627545736969279e-06, "loss": 0.774, "step": 2259 }, { "epoch": 2.1053122087604845, "loss_cot": 0.4437258839607239, "loss_nocot": 0.1568743884563446, "step": 2259 }, { "epoch": 2.1062441752096923, "grad_norm": 0.6154130990264376, "learning_rate": 6.6206420434932696e-06, "loss": 0.694, "step": 2260 }, { "epoch": 2.1062441752096923, "loss_cot": 0.5044950246810913, "loss_nocot": 0.19520758092403412, "step": 2260 }, { "epoch": 2.1071761416589, "grad_norm": 0.6525645279330827, "learning_rate": 6.61373835001726e-06, "loss": 0.7405, "step": 2261 }, { "epoch": 2.1071761416589, "loss_cot": 0.4494158625602722, "loss_nocot": 0.2829522490501404, "step": 2261 }, { "epoch": 2.108108108108108, "grad_norm": 0.6999456763419014, "learning_rate": 6.60683465654125e-06, "loss": 0.8104, "step": 2262 }, { "epoch": 2.108108108108108, "loss_cot": 0.4714573621749878, "loss_nocot": 0.3140127658843994, "step": 2262 }, { "epoch": 2.109040074557316, "grad_norm": 0.6493768273699982, "learning_rate": 6.599930963065241e-06, "loss": 0.7939, "step": 2263 }, { "epoch": 2.109040074557316, "loss_cot": 0.4770096242427826, "loss_nocot": 0.2876702547073364, "step": 2263 }, { "epoch": 2.109972041006524, "grad_norm": 0.6216943544593185, "learning_rate": 6.593027269589231e-06, "loss": 0.7219, "step": 2264 }, { "epoch": 2.109972041006524, "loss_cot": 0.5303176641464233, "loss_nocot": 0.1693129539489746, "step": 2264 }, { "epoch": 2.1109040074557317, "grad_norm": 0.6472943677669807, "learning_rate": 6.5861235761132215e-06, "loss": 0.7611, "step": 2265 }, { "epoch": 2.1109040074557317, "loss_cot": 0.43767309188842773, "loss_nocot": 0.17321865260601044, "step": 2265 }, { "epoch": 2.1118359739049395, "grad_norm": 0.6176270372555703, "learning_rate": 6.579219882637211e-06, "loss": 0.7591, "step": 2266 }, { "epoch": 2.1118359739049395, "loss_cot": 0.4749515652656555, "loss_nocot": 0.18854036927223206, "step": 2266 }, { "epoch": 2.1127679403541473, "grad_norm": 0.6637478115089942, "learning_rate": 6.572316189161202e-06, "loss": 0.7739, "step": 2267 }, { "epoch": 2.1127679403541473, "loss_cot": 0.5114880800247192, "loss_nocot": 0.24175576865673065, "step": 2267 }, { "epoch": 2.113699906803355, "grad_norm": 0.6436785761514264, "learning_rate": 6.565412495685192e-06, "loss": 0.7406, "step": 2268 }, { "epoch": 2.113699906803355, "loss_cot": 0.5046656131744385, "loss_nocot": 0.28367966413497925, "step": 2268 }, { "epoch": 2.114631873252563, "grad_norm": 0.6073890982641035, "learning_rate": 6.558508802209183e-06, "loss": 0.7275, "step": 2269 }, { "epoch": 2.114631873252563, "loss_cot": 0.5643400549888611, "loss_nocot": 0.2731871008872986, "step": 2269 }, { "epoch": 2.1155638397017706, "grad_norm": 0.7002383317168056, "learning_rate": 6.551605108733173e-06, "loss": 0.8385, "step": 2270 }, { "epoch": 2.1155638397017706, "loss_cot": 0.5760115385055542, "loss_nocot": 0.23682430386543274, "step": 2270 }, { "epoch": 2.1164958061509784, "grad_norm": 0.6219713547569001, "learning_rate": 6.544701415257163e-06, "loss": 0.7934, "step": 2271 }, { "epoch": 2.1164958061509784, "loss_cot": 0.5236760973930359, "loss_nocot": 0.2642553746700287, "step": 2271 }, { "epoch": 2.117427772600186, "grad_norm": 0.6418084885839879, "learning_rate": 6.537797721781154e-06, "loss": 0.7627, "step": 2272 }, { "epoch": 2.117427772600186, "loss_cot": 0.506365180015564, "loss_nocot": 0.21179746091365814, "step": 2272 }, { "epoch": 2.118359739049394, "grad_norm": 0.658701826049692, "learning_rate": 6.530894028305144e-06, "loss": 0.7714, "step": 2273 }, { "epoch": 2.118359739049394, "loss_cot": 0.4990561604499817, "loss_nocot": 0.340660035610199, "step": 2273 }, { "epoch": 2.1192917054986022, "grad_norm": 0.6714108270340212, "learning_rate": 6.523990334829135e-06, "loss": 0.8117, "step": 2274 }, { "epoch": 2.1192917054986022, "loss_cot": 0.42803746461868286, "loss_nocot": 0.23015667498111725, "step": 2274 }, { "epoch": 2.12022367194781, "grad_norm": 0.6310862968509698, "learning_rate": 6.517086641353124e-06, "loss": 0.7218, "step": 2275 }, { "epoch": 2.12022367194781, "loss_cot": 0.4701617360115051, "loss_nocot": 0.1804933100938797, "step": 2275 }, { "epoch": 2.121155638397018, "grad_norm": 0.6579278944809057, "learning_rate": 6.510182947877115e-06, "loss": 0.7608, "step": 2276 }, { "epoch": 2.121155638397018, "loss_cot": 0.5276651382446289, "loss_nocot": 0.28374338150024414, "step": 2276 }, { "epoch": 2.1220876048462256, "grad_norm": 0.7523165825749466, "learning_rate": 6.503279254401104e-06, "loss": 0.8215, "step": 2277 }, { "epoch": 2.1220876048462256, "loss_cot": 0.5136685371398926, "loss_nocot": 0.3587073087692261, "step": 2277 }, { "epoch": 2.1230195712954334, "grad_norm": 0.6493412157977223, "learning_rate": 6.496375560925096e-06, "loss": 0.7978, "step": 2278 }, { "epoch": 2.1230195712954334, "loss_cot": 0.48403358459472656, "loss_nocot": 0.34633204340934753, "step": 2278 }, { "epoch": 2.123951537744641, "grad_norm": 0.6537122201423147, "learning_rate": 6.489471867449085e-06, "loss": 0.7927, "step": 2279 }, { "epoch": 2.123951537744641, "loss_cot": 0.5129128694534302, "loss_nocot": 0.24771836400032043, "step": 2279 }, { "epoch": 2.124883504193849, "grad_norm": 0.6149998034811811, "learning_rate": 6.482568173973076e-06, "loss": 0.7752, "step": 2280 }, { "epoch": 2.124883504193849, "loss_cot": 0.4905134439468384, "loss_nocot": 0.34251922369003296, "step": 2280 }, { "epoch": 2.1258154706430568, "grad_norm": 0.7074446141820134, "learning_rate": 6.475664480497067e-06, "loss": 0.76, "step": 2281 }, { "epoch": 2.1258154706430568, "loss_cot": 0.5450223088264465, "loss_nocot": 0.3110519349575043, "step": 2281 }, { "epoch": 2.1267474370922645, "grad_norm": 0.6453738920387224, "learning_rate": 6.468760787021056e-06, "loss": 0.7471, "step": 2282 }, { "epoch": 2.1267474370922645, "loss_cot": 0.5204129815101624, "loss_nocot": 0.19688774645328522, "step": 2282 }, { "epoch": 2.1276794035414723, "grad_norm": 0.595032444824102, "learning_rate": 6.461857093545048e-06, "loss": 0.7171, "step": 2283 }, { "epoch": 2.1276794035414723, "loss_cot": 0.5072507858276367, "loss_nocot": 0.27814313769340515, "step": 2283 }, { "epoch": 2.12861136999068, "grad_norm": 0.6221533198026544, "learning_rate": 6.454953400069037e-06, "loss": 0.7521, "step": 2284 }, { "epoch": 2.12861136999068, "loss_cot": 0.47278058528900146, "loss_nocot": 0.19367095828056335, "step": 2284 }, { "epoch": 2.1295433364398884, "grad_norm": 0.5847743517640848, "learning_rate": 6.448049706593028e-06, "loss": 0.7078, "step": 2285 }, { "epoch": 2.1295433364398884, "loss_cot": 0.5326089859008789, "loss_nocot": 0.24348339438438416, "step": 2285 }, { "epoch": 2.130475302889096, "grad_norm": 0.6588822294159148, "learning_rate": 6.441146013117018e-06, "loss": 0.7782, "step": 2286 }, { "epoch": 2.130475302889096, "loss_cot": 0.5232976675033569, "loss_nocot": 0.20984384417533875, "step": 2286 }, { "epoch": 2.131407269338304, "grad_norm": 0.5765262745590293, "learning_rate": 6.434242319641008e-06, "loss": 0.734, "step": 2287 }, { "epoch": 2.131407269338304, "loss_cot": 0.4334307312965393, "loss_nocot": 0.2544833719730377, "step": 2287 }, { "epoch": 2.1323392357875117, "grad_norm": 0.6264754262981711, "learning_rate": 6.427338626164998e-06, "loss": 0.7335, "step": 2288 }, { "epoch": 2.1323392357875117, "loss_cot": 0.4648752510547638, "loss_nocot": 0.2605080306529999, "step": 2288 }, { "epoch": 2.1332712022367195, "grad_norm": 0.6682815536429272, "learning_rate": 6.420434932688989e-06, "loss": 0.8079, "step": 2289 }, { "epoch": 2.1332712022367195, "loss_cot": 0.46892836689949036, "loss_nocot": 0.28242576122283936, "step": 2289 }, { "epoch": 2.1342031686859273, "grad_norm": 0.625358625207261, "learning_rate": 6.413531239212979e-06, "loss": 0.7394, "step": 2290 }, { "epoch": 2.1342031686859273, "loss_cot": 0.5523853302001953, "loss_nocot": 0.2723756432533264, "step": 2290 }, { "epoch": 2.135135135135135, "grad_norm": 0.7053921514042569, "learning_rate": 6.4066275457369696e-06, "loss": 0.7442, "step": 2291 }, { "epoch": 2.135135135135135, "loss_cot": 0.6231092810630798, "loss_nocot": 0.17273765802383423, "step": 2291 }, { "epoch": 2.136067101584343, "grad_norm": 0.6342149143803186, "learning_rate": 6.39972385226096e-06, "loss": 0.8118, "step": 2292 }, { "epoch": 2.136067101584343, "loss_cot": 0.48148488998413086, "loss_nocot": 0.2834794223308563, "step": 2292 }, { "epoch": 2.1369990680335507, "grad_norm": 0.5992285945019653, "learning_rate": 6.39282015878495e-06, "loss": 0.6931, "step": 2293 }, { "epoch": 2.1369990680335507, "loss_cot": 0.5021353960037231, "loss_nocot": 0.25289973616600037, "step": 2293 }, { "epoch": 2.1379310344827585, "grad_norm": 0.5971823264507213, "learning_rate": 6.385916465308941e-06, "loss": 0.7417, "step": 2294 }, { "epoch": 2.1379310344827585, "loss_cot": 0.47442543506622314, "loss_nocot": 0.20524989068508148, "step": 2294 }, { "epoch": 2.1388630009319662, "grad_norm": 0.7158353892969302, "learning_rate": 6.379012771832931e-06, "loss": 0.7463, "step": 2295 }, { "epoch": 2.1388630009319662, "loss_cot": 0.5164635181427002, "loss_nocot": 0.20016366243362427, "step": 2295 }, { "epoch": 2.1397949673811745, "grad_norm": 0.6245388637255558, "learning_rate": 6.3721090783569215e-06, "loss": 0.7235, "step": 2296 }, { "epoch": 2.1397949673811745, "loss_cot": 0.46661847829818726, "loss_nocot": 0.39572852849960327, "step": 2296 }, { "epoch": 2.1407269338303823, "grad_norm": 0.6255794483416637, "learning_rate": 6.365205384880911e-06, "loss": 0.7878, "step": 2297 }, { "epoch": 2.1407269338303823, "loss_cot": 0.4966045022010803, "loss_nocot": 0.1882007122039795, "step": 2297 }, { "epoch": 2.14165890027959, "grad_norm": 0.58311450948438, "learning_rate": 6.358301691404902e-06, "loss": 0.7397, "step": 2298 }, { "epoch": 2.14165890027959, "loss_cot": 0.4705989956855774, "loss_nocot": 0.21925485134124756, "step": 2298 }, { "epoch": 2.142590866728798, "grad_norm": 0.6538687631069534, "learning_rate": 6.351397997928892e-06, "loss": 0.7171, "step": 2299 }, { "epoch": 2.142590866728798, "loss_cot": 0.5508192181587219, "loss_nocot": 0.32626789808273315, "step": 2299 }, { "epoch": 2.1435228331780056, "grad_norm": 0.6614254417723022, "learning_rate": 6.344494304452883e-06, "loss": 0.8014, "step": 2300 }, { "epoch": 2.1435228331780056, "loss_cot": 0.4963268041610718, "loss_nocot": 0.19979293644428253, "step": 2300 }, { "epoch": 2.1444547996272134, "grad_norm": 0.6473622962829426, "learning_rate": 6.3375906109768735e-06, "loss": 0.7405, "step": 2301 }, { "epoch": 2.1444547996272134, "loss_cot": 0.4783831536769867, "loss_nocot": 0.2093982696533203, "step": 2301 }, { "epoch": 2.145386766076421, "grad_norm": 0.6547944489855237, "learning_rate": 6.330686917500863e-06, "loss": 0.7754, "step": 2302 }, { "epoch": 2.145386766076421, "loss_cot": 0.5264371633529663, "loss_nocot": 0.2467418760061264, "step": 2302 }, { "epoch": 2.146318732525629, "grad_norm": 0.6455477778836533, "learning_rate": 6.323783224024854e-06, "loss": 0.7553, "step": 2303 }, { "epoch": 2.146318732525629, "loss_cot": 0.47605055570602417, "loss_nocot": 0.19100122153759003, "step": 2303 }, { "epoch": 2.147250698974837, "grad_norm": 0.6470899807035992, "learning_rate": 6.316879530548844e-06, "loss": 0.7455, "step": 2304 }, { "epoch": 2.147250698974837, "loss_cot": 0.49117615818977356, "loss_nocot": 0.2030566930770874, "step": 2304 }, { "epoch": 2.1481826654240446, "grad_norm": 0.6278174177723206, "learning_rate": 6.309975837072835e-06, "loss": 0.7187, "step": 2305 }, { "epoch": 2.1481826654240446, "loss_cot": 0.4800347685813904, "loss_nocot": 0.3031626343727112, "step": 2305 }, { "epoch": 2.1491146318732524, "grad_norm": 0.6438294696143967, "learning_rate": 6.303072143596825e-06, "loss": 0.7543, "step": 2306 }, { "epoch": 2.1491146318732524, "loss_cot": 0.6303797960281372, "loss_nocot": 0.29169994592666626, "step": 2306 }, { "epoch": 2.1500465983224606, "grad_norm": 0.6392429387696175, "learning_rate": 6.296168450120815e-06, "loss": 0.7985, "step": 2307 }, { "epoch": 2.1500465983224606, "loss_cot": 0.49836450815200806, "loss_nocot": 0.29054027795791626, "step": 2307 }, { "epoch": 2.1509785647716684, "grad_norm": 0.6430171063482062, "learning_rate": 6.289264756644805e-06, "loss": 0.7551, "step": 2308 }, { "epoch": 2.1509785647716684, "loss_cot": 0.5123248100280762, "loss_nocot": 0.2580368220806122, "step": 2308 }, { "epoch": 2.151910531220876, "grad_norm": 0.6113608325456419, "learning_rate": 6.282361063168796e-06, "loss": 0.7633, "step": 2309 }, { "epoch": 2.151910531220876, "loss_cot": 0.418297678232193, "loss_nocot": 0.3556128144264221, "step": 2309 }, { "epoch": 2.152842497670084, "grad_norm": 0.668348301249592, "learning_rate": 6.275457369692786e-06, "loss": 0.7429, "step": 2310 }, { "epoch": 2.152842497670084, "loss_cot": 0.5016223192214966, "loss_nocot": 0.2390640377998352, "step": 2310 }, { "epoch": 2.1537744641192917, "grad_norm": 0.6221049832041619, "learning_rate": 6.268553676216777e-06, "loss": 0.772, "step": 2311 }, { "epoch": 2.1537744641192917, "loss_cot": 0.5439712405204773, "loss_nocot": 0.23903626203536987, "step": 2311 }, { "epoch": 2.1547064305684995, "grad_norm": 0.7027967020761199, "learning_rate": 6.261649982740767e-06, "loss": 0.8205, "step": 2312 }, { "epoch": 2.1547064305684995, "loss_cot": 0.5607745051383972, "loss_nocot": 0.3003307580947876, "step": 2312 }, { "epoch": 2.1556383970177073, "grad_norm": 0.6976770783004939, "learning_rate": 6.254746289264757e-06, "loss": 0.826, "step": 2313 }, { "epoch": 2.1556383970177073, "loss_cot": 0.48126280307769775, "loss_nocot": 0.2966982126235962, "step": 2313 }, { "epoch": 2.156570363466915, "grad_norm": 0.611614533256291, "learning_rate": 6.247842595788748e-06, "loss": 0.7365, "step": 2314 }, { "epoch": 2.156570363466915, "loss_cot": 0.47997522354125977, "loss_nocot": 0.3491491675376892, "step": 2314 }, { "epoch": 2.157502329916123, "grad_norm": 0.61989198739779, "learning_rate": 6.240938902312738e-06, "loss": 0.7835, "step": 2315 }, { "epoch": 2.157502329916123, "loss_cot": 0.4669930934906006, "loss_nocot": 0.2022787630558014, "step": 2315 }, { "epoch": 2.1584342963653307, "grad_norm": 0.6084755593321247, "learning_rate": 6.2340352088367286e-06, "loss": 0.7324, "step": 2316 }, { "epoch": 2.1584342963653307, "loss_cot": 0.4473307430744171, "loss_nocot": 0.24621708691120148, "step": 2316 }, { "epoch": 2.1593662628145385, "grad_norm": 0.7050822117310898, "learning_rate": 6.2271315153607184e-06, "loss": 0.7698, "step": 2317 }, { "epoch": 2.1593662628145385, "loss_cot": 0.4786427617073059, "loss_nocot": 0.21376870572566986, "step": 2317 }, { "epoch": 2.1602982292637467, "grad_norm": 0.6282351063051266, "learning_rate": 6.220227821884709e-06, "loss": 0.7513, "step": 2318 }, { "epoch": 2.1602982292637467, "loss_cot": 0.49965155124664307, "loss_nocot": 0.19862070679664612, "step": 2318 }, { "epoch": 2.1612301957129545, "grad_norm": 0.641484185203674, "learning_rate": 6.213324128408699e-06, "loss": 0.7171, "step": 2319 }, { "epoch": 2.1612301957129545, "loss_cot": 0.48978814482688904, "loss_nocot": 0.20720107853412628, "step": 2319 }, { "epoch": 2.1621621621621623, "grad_norm": 0.6410535844448482, "learning_rate": 6.20642043493269e-06, "loss": 0.7069, "step": 2320 }, { "epoch": 2.1621621621621623, "loss_cot": 0.4672064185142517, "loss_nocot": 0.2834963798522949, "step": 2320 }, { "epoch": 2.16309412861137, "grad_norm": 0.7092924892262988, "learning_rate": 6.1995167414566805e-06, "loss": 0.8071, "step": 2321 }, { "epoch": 2.16309412861137, "loss_cot": 0.5324002504348755, "loss_nocot": 0.28549692034721375, "step": 2321 }, { "epoch": 2.164026095060578, "grad_norm": 0.660347210593027, "learning_rate": 6.19261304798067e-06, "loss": 0.8038, "step": 2322 }, { "epoch": 2.164026095060578, "loss_cot": 0.43516185879707336, "loss_nocot": 0.20131200551986694, "step": 2322 }, { "epoch": 2.1649580615097856, "grad_norm": 0.6074175061438721, "learning_rate": 6.185709354504661e-06, "loss": 0.7185, "step": 2323 }, { "epoch": 2.1649580615097856, "loss_cot": 0.537939190864563, "loss_nocot": 0.2433038353919983, "step": 2323 }, { "epoch": 2.1658900279589934, "grad_norm": 0.6213932750760819, "learning_rate": 6.178805661028651e-06, "loss": 0.7582, "step": 2324 }, { "epoch": 2.1658900279589934, "loss_cot": 0.5429742932319641, "loss_nocot": 0.2669978141784668, "step": 2324 }, { "epoch": 2.1668219944082012, "grad_norm": 0.6555306084622732, "learning_rate": 6.171901967552642e-06, "loss": 0.7868, "step": 2325 }, { "epoch": 2.1668219944082012, "loss_cot": 0.5487173795700073, "loss_nocot": 0.2799314558506012, "step": 2325 }, { "epoch": 2.167753960857409, "grad_norm": 0.6657845128956968, "learning_rate": 6.164998274076631e-06, "loss": 0.7654, "step": 2326 }, { "epoch": 2.167753960857409, "loss_cot": 0.47681087255477905, "loss_nocot": 0.18364910781383514, "step": 2326 }, { "epoch": 2.168685927306617, "grad_norm": 0.6356976312466706, "learning_rate": 6.158094580600622e-06, "loss": 0.7359, "step": 2327 }, { "epoch": 2.168685927306617, "loss_cot": 0.5322237014770508, "loss_nocot": 0.2051301896572113, "step": 2327 }, { "epoch": 2.1696178937558246, "grad_norm": 0.599790947804301, "learning_rate": 6.151190887124611e-06, "loss": 0.7358, "step": 2328 }, { "epoch": 2.1696178937558246, "loss_cot": 0.5519852042198181, "loss_nocot": 0.2321251630783081, "step": 2328 }, { "epoch": 2.170549860205033, "grad_norm": 0.6224166679917471, "learning_rate": 6.144287193648603e-06, "loss": 0.7403, "step": 2329 }, { "epoch": 2.170549860205033, "loss_cot": 0.467915415763855, "loss_nocot": 0.22972866892814636, "step": 2329 }, { "epoch": 2.1714818266542406, "grad_norm": 0.6794374900957872, "learning_rate": 6.137383500172592e-06, "loss": 0.7669, "step": 2330 }, { "epoch": 2.1714818266542406, "loss_cot": 0.521618664264679, "loss_nocot": 0.1973903328180313, "step": 2330 }, { "epoch": 2.1724137931034484, "grad_norm": 0.6178524130356082, "learning_rate": 6.130479806696583e-06, "loss": 0.7242, "step": 2331 }, { "epoch": 2.1724137931034484, "loss_cot": 0.45684826374053955, "loss_nocot": 0.22858986258506775, "step": 2331 }, { "epoch": 2.173345759552656, "grad_norm": 0.607937726967414, "learning_rate": 6.123576113220574e-06, "loss": 0.7241, "step": 2332 }, { "epoch": 2.173345759552656, "loss_cot": 0.4597760736942291, "loss_nocot": 0.1863122284412384, "step": 2332 }, { "epoch": 2.174277726001864, "grad_norm": 0.6386106487745848, "learning_rate": 6.116672419744563e-06, "loss": 0.7583, "step": 2333 }, { "epoch": 2.174277726001864, "loss_cot": 0.48697277903556824, "loss_nocot": 0.2261834591627121, "step": 2333 }, { "epoch": 2.1752096924510718, "grad_norm": 0.8865150718801363, "learning_rate": 6.109768726268555e-06, "loss": 0.7082, "step": 2334 }, { "epoch": 2.1752096924510718, "loss_cot": 0.4760884642601013, "loss_nocot": 0.22795262932777405, "step": 2334 }, { "epoch": 2.1761416589002796, "grad_norm": 0.6293905178606026, "learning_rate": 6.102865032792544e-06, "loss": 0.7322, "step": 2335 }, { "epoch": 2.1761416589002796, "loss_cot": 0.40607553720474243, "loss_nocot": 0.2179379165172577, "step": 2335 }, { "epoch": 2.1770736253494873, "grad_norm": 0.6045063098874476, "learning_rate": 6.095961339316535e-06, "loss": 0.6979, "step": 2336 }, { "epoch": 2.1770736253494873, "loss_cot": 0.5223511457443237, "loss_nocot": 0.25458014011383057, "step": 2336 }, { "epoch": 2.178005591798695, "grad_norm": 0.656108592575866, "learning_rate": 6.089057645840525e-06, "loss": 0.7596, "step": 2337 }, { "epoch": 2.178005591798695, "loss_cot": 0.47416168451309204, "loss_nocot": 0.3170369565486908, "step": 2337 }, { "epoch": 2.178937558247903, "grad_norm": 0.7127930099183228, "learning_rate": 6.082153952364515e-06, "loss": 0.7665, "step": 2338 }, { "epoch": 2.178937558247903, "loss_cot": 0.47326743602752686, "loss_nocot": 0.2949441075325012, "step": 2338 }, { "epoch": 2.1798695246971107, "grad_norm": 0.6866140749539501, "learning_rate": 6.075250258888505e-06, "loss": 0.8226, "step": 2339 }, { "epoch": 2.1798695246971107, "loss_cot": 0.44606202840805054, "loss_nocot": 0.2929256558418274, "step": 2339 }, { "epoch": 2.180801491146319, "grad_norm": 0.6037473645554867, "learning_rate": 6.068346565412496e-06, "loss": 0.7253, "step": 2340 }, { "epoch": 2.180801491146319, "loss_cot": 0.47728246450424194, "loss_nocot": 0.20703798532485962, "step": 2340 }, { "epoch": 2.1817334575955267, "grad_norm": 0.6474600625099327, "learning_rate": 6.061442871936487e-06, "loss": 0.7346, "step": 2341 }, { "epoch": 2.1817334575955267, "loss_cot": 0.5653524398803711, "loss_nocot": 0.26255300641059875, "step": 2341 }, { "epoch": 2.1826654240447345, "grad_norm": 0.656206004308042, "learning_rate": 6.054539178460477e-06, "loss": 0.7758, "step": 2342 }, { "epoch": 2.1826654240447345, "loss_cot": 0.5176970958709717, "loss_nocot": 0.2031671404838562, "step": 2342 }, { "epoch": 2.1835973904939423, "grad_norm": 0.643228897193378, "learning_rate": 6.047635484984467e-06, "loss": 0.7601, "step": 2343 }, { "epoch": 2.1835973904939423, "loss_cot": 0.5642762184143066, "loss_nocot": 0.3381923735141754, "step": 2343 }, { "epoch": 2.18452935694315, "grad_norm": 0.6601042420929161, "learning_rate": 6.040731791508457e-06, "loss": 0.7859, "step": 2344 }, { "epoch": 2.18452935694315, "loss_cot": 0.4894787073135376, "loss_nocot": 0.2346370369195938, "step": 2344 }, { "epoch": 2.185461323392358, "grad_norm": 0.665269893517957, "learning_rate": 6.033828098032448e-06, "loss": 0.7783, "step": 2345 }, { "epoch": 2.185461323392358, "loss_cot": 0.44391942024230957, "loss_nocot": 0.4967625141143799, "step": 2345 }, { "epoch": 2.1863932898415657, "grad_norm": 0.6868245090588027, "learning_rate": 6.026924404556438e-06, "loss": 0.8263, "step": 2346 }, { "epoch": 2.1863932898415657, "loss_cot": 0.44912758469581604, "loss_nocot": 0.2741363048553467, "step": 2346 }, { "epoch": 2.1873252562907735, "grad_norm": 0.688590741056265, "learning_rate": 6.0200207110804286e-06, "loss": 0.7789, "step": 2347 }, { "epoch": 2.1873252562907735, "loss_cot": 0.43365901708602905, "loss_nocot": 0.24410507082939148, "step": 2347 }, { "epoch": 2.1882572227399812, "grad_norm": 0.6502136303533056, "learning_rate": 6.0131170176044184e-06, "loss": 0.7023, "step": 2348 }, { "epoch": 2.1882572227399812, "loss_cot": 0.4649127721786499, "loss_nocot": 0.17861750721931458, "step": 2348 }, { "epoch": 2.189189189189189, "grad_norm": 0.5723441868920125, "learning_rate": 6.006213324128409e-06, "loss": 0.6734, "step": 2349 }, { "epoch": 2.189189189189189, "loss_cot": 0.508583128452301, "loss_nocot": 0.20497694611549377, "step": 2349 }, { "epoch": 2.190121155638397, "grad_norm": 0.6435350612140661, "learning_rate": 5.999309630652399e-06, "loss": 0.7393, "step": 2350 }, { "epoch": 2.190121155638397, "loss_cot": 0.48246514797210693, "loss_nocot": 0.23529234528541565, "step": 2350 }, { "epoch": 2.191053122087605, "grad_norm": 0.6585205821145395, "learning_rate": 5.99240593717639e-06, "loss": 0.7496, "step": 2351 }, { "epoch": 2.191053122087605, "loss_cot": 0.4851914048194885, "loss_nocot": 0.24569782614707947, "step": 2351 }, { "epoch": 2.191985088536813, "grad_norm": 0.603229376023161, "learning_rate": 5.9855022437003805e-06, "loss": 0.7543, "step": 2352 }, { "epoch": 2.191985088536813, "loss_cot": 0.5118460655212402, "loss_nocot": 0.2299623042345047, "step": 2352 }, { "epoch": 2.1929170549860206, "grad_norm": 0.6575946795387625, "learning_rate": 5.97859855022437e-06, "loss": 0.7834, "step": 2353 }, { "epoch": 2.1929170549860206, "loss_cot": 0.584496021270752, "loss_nocot": 0.32365068793296814, "step": 2353 }, { "epoch": 2.1938490214352284, "grad_norm": 0.6285010812397244, "learning_rate": 5.971694856748361e-06, "loss": 0.792, "step": 2354 }, { "epoch": 2.1938490214352284, "loss_cot": 0.49724191427230835, "loss_nocot": 0.38115304708480835, "step": 2354 }, { "epoch": 2.194780987884436, "grad_norm": 0.6866842024799301, "learning_rate": 5.964791163272351e-06, "loss": 0.8245, "step": 2355 }, { "epoch": 2.194780987884436, "loss_cot": 0.5125597715377808, "loss_nocot": 0.26621779799461365, "step": 2355 }, { "epoch": 2.195712954333644, "grad_norm": 0.663188643424426, "learning_rate": 5.957887469796342e-06, "loss": 0.8089, "step": 2356 }, { "epoch": 2.195712954333644, "loss_cot": 0.4844827651977539, "loss_nocot": 0.2848964333534241, "step": 2356 }, { "epoch": 2.196644920782852, "grad_norm": 0.6229450552404474, "learning_rate": 5.950983776320332e-06, "loss": 0.743, "step": 2357 }, { "epoch": 2.196644920782852, "loss_cot": 0.4404309093952179, "loss_nocot": 0.25698500871658325, "step": 2357 }, { "epoch": 2.1975768872320596, "grad_norm": 0.6595673421238346, "learning_rate": 5.944080082844322e-06, "loss": 0.7622, "step": 2358 }, { "epoch": 2.1975768872320596, "loss_cot": 0.5040642023086548, "loss_nocot": 0.28713852167129517, "step": 2358 }, { "epoch": 2.1985088536812674, "grad_norm": 0.6038618898767107, "learning_rate": 5.937176389368312e-06, "loss": 0.7532, "step": 2359 }, { "epoch": 2.1985088536812674, "loss_cot": 0.5140836238861084, "loss_nocot": 0.1989310085773468, "step": 2359 }, { "epoch": 2.199440820130475, "grad_norm": 0.6275207919533993, "learning_rate": 5.930272695892303e-06, "loss": 0.7572, "step": 2360 }, { "epoch": 2.199440820130475, "loss_cot": 0.4270375370979309, "loss_nocot": 0.25598040223121643, "step": 2360 }, { "epoch": 2.200372786579683, "grad_norm": 0.6759557203840287, "learning_rate": 5.923369002416293e-06, "loss": 0.7273, "step": 2361 }, { "epoch": 2.200372786579683, "loss_cot": 0.4378182291984558, "loss_nocot": 0.17185941338539124, "step": 2361 }, { "epoch": 2.201304753028891, "grad_norm": 0.6035996683489684, "learning_rate": 5.916465308940284e-06, "loss": 0.72, "step": 2362 }, { "epoch": 2.201304753028891, "loss_cot": 0.5373115539550781, "loss_nocot": 0.196471706032753, "step": 2362 }, { "epoch": 2.202236719478099, "grad_norm": 0.6232621458455455, "learning_rate": 5.909561615464274e-06, "loss": 0.7101, "step": 2363 }, { "epoch": 2.202236719478099, "loss_cot": 0.4669019281864166, "loss_nocot": 0.2491249144077301, "step": 2363 }, { "epoch": 2.2031686859273067, "grad_norm": 0.6829167456096028, "learning_rate": 5.902657921988264e-06, "loss": 0.7954, "step": 2364 }, { "epoch": 2.2031686859273067, "loss_cot": 0.538303017616272, "loss_nocot": 0.22424852848052979, "step": 2364 }, { "epoch": 2.2041006523765145, "grad_norm": 0.6687705793918602, "learning_rate": 5.895754228512255e-06, "loss": 0.7491, "step": 2365 }, { "epoch": 2.2041006523765145, "loss_cot": 0.4831050634384155, "loss_nocot": 0.16753259301185608, "step": 2365 }, { "epoch": 2.2050326188257223, "grad_norm": 0.6515625713590155, "learning_rate": 5.888850535036245e-06, "loss": 0.7465, "step": 2366 }, { "epoch": 2.2050326188257223, "loss_cot": 0.4783551096916199, "loss_nocot": 0.19539348781108856, "step": 2366 }, { "epoch": 2.20596458527493, "grad_norm": 0.6196696510238539, "learning_rate": 5.881946841560236e-06, "loss": 0.7244, "step": 2367 }, { "epoch": 2.20596458527493, "loss_cot": 0.5100612044334412, "loss_nocot": 0.2552680969238281, "step": 2367 }, { "epoch": 2.206896551724138, "grad_norm": 0.6241499864491165, "learning_rate": 5.8750431480842255e-06, "loss": 0.7009, "step": 2368 }, { "epoch": 2.206896551724138, "loss_cot": 0.4792134761810303, "loss_nocot": 0.293033629655838, "step": 2368 }, { "epoch": 2.2078285181733457, "grad_norm": 0.6170724593731619, "learning_rate": 5.868139454608216e-06, "loss": 0.7613, "step": 2369 }, { "epoch": 2.2078285181733457, "loss_cot": 0.5200513601303101, "loss_nocot": 0.24033240973949432, "step": 2369 }, { "epoch": 2.2087604846225535, "grad_norm": 0.6281822042082145, "learning_rate": 5.861235761132206e-06, "loss": 0.7267, "step": 2370 }, { "epoch": 2.2087604846225535, "loss_cot": 0.5313447713851929, "loss_nocot": 0.20419242978096008, "step": 2370 }, { "epoch": 2.2096924510717613, "grad_norm": 0.6433308477284058, "learning_rate": 5.854332067656197e-06, "loss": 0.7346, "step": 2371 }, { "epoch": 2.2096924510717613, "loss_cot": 0.4644842743873596, "loss_nocot": 0.18644726276397705, "step": 2371 }, { "epoch": 2.210624417520969, "grad_norm": 0.6354740457772263, "learning_rate": 5.8474283741801875e-06, "loss": 0.7425, "step": 2372 }, { "epoch": 2.210624417520969, "loss_cot": 0.45994797348976135, "loss_nocot": 0.2326311469078064, "step": 2372 }, { "epoch": 2.2115563839701773, "grad_norm": 0.6073115577749711, "learning_rate": 5.8405246807041774e-06, "loss": 0.7036, "step": 2373 }, { "epoch": 2.2115563839701773, "loss_cot": 0.4985674023628235, "loss_nocot": 0.2531474232673645, "step": 2373 }, { "epoch": 2.212488350419385, "grad_norm": 0.6510116005607948, "learning_rate": 5.833620987228168e-06, "loss": 0.7151, "step": 2374 }, { "epoch": 2.212488350419385, "loss_cot": 0.4708530008792877, "loss_nocot": 0.31155794858932495, "step": 2374 }, { "epoch": 2.213420316868593, "grad_norm": 0.6925212454694356, "learning_rate": 5.826717293752158e-06, "loss": 0.8025, "step": 2375 }, { "epoch": 2.213420316868593, "loss_cot": 0.4761505126953125, "loss_nocot": 0.2748740315437317, "step": 2375 }, { "epoch": 2.2143522833178007, "grad_norm": 0.6303622402484944, "learning_rate": 5.819813600276149e-06, "loss": 0.7671, "step": 2376 }, { "epoch": 2.2143522833178007, "loss_cot": 0.497584730386734, "loss_nocot": 0.18848755955696106, "step": 2376 }, { "epoch": 2.2152842497670084, "grad_norm": 0.5756403962621583, "learning_rate": 5.812909906800138e-06, "loss": 0.7226, "step": 2377 }, { "epoch": 2.2152842497670084, "loss_cot": 0.4513120949268341, "loss_nocot": 0.2826507091522217, "step": 2377 }, { "epoch": 2.2162162162162162, "grad_norm": 0.6753051619172028, "learning_rate": 5.806006213324129e-06, "loss": 0.758, "step": 2378 }, { "epoch": 2.2162162162162162, "loss_cot": 0.4999416470527649, "loss_nocot": 0.2907053232192993, "step": 2378 }, { "epoch": 2.217148182665424, "grad_norm": 0.6756828370271296, "learning_rate": 5.7991025198481184e-06, "loss": 0.798, "step": 2379 }, { "epoch": 2.217148182665424, "loss_cot": 0.49919357895851135, "loss_nocot": 0.2803550362586975, "step": 2379 }, { "epoch": 2.218080149114632, "grad_norm": 0.6771106255061523, "learning_rate": 5.79219882637211e-06, "loss": 0.7409, "step": 2380 }, { "epoch": 2.218080149114632, "loss_cot": 0.49926257133483887, "loss_nocot": 0.2481069415807724, "step": 2380 }, { "epoch": 2.2190121155638396, "grad_norm": 0.6853839049754183, "learning_rate": 5.785295132896099e-06, "loss": 0.8216, "step": 2381 }, { "epoch": 2.2190121155638396, "loss_cot": 0.47092103958129883, "loss_nocot": 0.30119481682777405, "step": 2381 }, { "epoch": 2.2199440820130474, "grad_norm": 0.7416075595615101, "learning_rate": 5.77839143942009e-06, "loss": 0.7534, "step": 2382 }, { "epoch": 2.2199440820130474, "loss_cot": 0.4605408310890198, "loss_nocot": 0.2724512219429016, "step": 2382 }, { "epoch": 2.220876048462255, "grad_norm": 0.6400333279263923, "learning_rate": 5.771487745944081e-06, "loss": 0.6942, "step": 2383 }, { "epoch": 2.220876048462255, "loss_cot": 0.46653395891189575, "loss_nocot": 0.27972152829170227, "step": 2383 }, { "epoch": 2.2218080149114634, "grad_norm": 0.6813304929269627, "learning_rate": 5.76458405246807e-06, "loss": 0.7818, "step": 2384 }, { "epoch": 2.2218080149114634, "loss_cot": 0.4471604824066162, "loss_nocot": 0.2650909423828125, "step": 2384 }, { "epoch": 2.222739981360671, "grad_norm": 0.5974499210917289, "learning_rate": 5.757680358992062e-06, "loss": 0.6919, "step": 2385 }, { "epoch": 2.222739981360671, "loss_cot": 0.4252878427505493, "loss_nocot": 0.24895218014717102, "step": 2385 }, { "epoch": 2.223671947809879, "grad_norm": 0.621162745936087, "learning_rate": 5.750776665516051e-06, "loss": 0.7292, "step": 2386 }, { "epoch": 2.223671947809879, "loss_cot": 0.5246870517730713, "loss_nocot": 0.3164585828781128, "step": 2386 }, { "epoch": 2.2246039142590868, "grad_norm": 0.6366656208731003, "learning_rate": 5.743872972040042e-06, "loss": 0.8013, "step": 2387 }, { "epoch": 2.2246039142590868, "loss_cot": 0.47140777111053467, "loss_nocot": 0.21098670363426208, "step": 2387 }, { "epoch": 2.2255358807082946, "grad_norm": 0.6097588773493805, "learning_rate": 5.736969278564032e-06, "loss": 0.712, "step": 2388 }, { "epoch": 2.2255358807082946, "loss_cot": 0.5278224349021912, "loss_nocot": 0.19514435529708862, "step": 2388 }, { "epoch": 2.2264678471575023, "grad_norm": 0.7190145558808524, "learning_rate": 5.730065585088022e-06, "loss": 0.7646, "step": 2389 }, { "epoch": 2.2264678471575023, "loss_cot": 0.49210914969444275, "loss_nocot": 0.21136189997196198, "step": 2389 }, { "epoch": 2.22739981360671, "grad_norm": 0.6353072039344256, "learning_rate": 5.723161891612012e-06, "loss": 0.7364, "step": 2390 }, { "epoch": 2.22739981360671, "loss_cot": 0.5019838809967041, "loss_nocot": 0.2500982880592346, "step": 2390 }, { "epoch": 2.228331780055918, "grad_norm": 0.6865848338755736, "learning_rate": 5.716258198136003e-06, "loss": 0.78, "step": 2391 }, { "epoch": 2.228331780055918, "loss_cot": 0.4964867830276489, "loss_nocot": 0.27951309084892273, "step": 2391 }, { "epoch": 2.2292637465051257, "grad_norm": 0.640837819839048, "learning_rate": 5.709354504659994e-06, "loss": 0.7694, "step": 2392 }, { "epoch": 2.2292637465051257, "loss_cot": 0.5676382184028625, "loss_nocot": 0.24048684537410736, "step": 2392 }, { "epoch": 2.2301957129543335, "grad_norm": 0.6696295764232685, "learning_rate": 5.702450811183984e-06, "loss": 0.7981, "step": 2393 }, { "epoch": 2.2301957129543335, "loss_cot": 0.4963366985321045, "loss_nocot": 0.21280637383460999, "step": 2393 }, { "epoch": 2.2311276794035413, "grad_norm": 0.681310041559733, "learning_rate": 5.695547117707974e-06, "loss": 0.7325, "step": 2394 }, { "epoch": 2.2311276794035413, "loss_cot": 0.4937550723552704, "loss_nocot": 0.18307635188102722, "step": 2394 }, { "epoch": 2.2320596458527495, "grad_norm": 0.6181779397620264, "learning_rate": 5.688643424231964e-06, "loss": 0.7065, "step": 2395 }, { "epoch": 2.2320596458527495, "loss_cot": 0.47469913959503174, "loss_nocot": 0.2893317639827728, "step": 2395 }, { "epoch": 2.2329916123019573, "grad_norm": 0.6374029411805123, "learning_rate": 5.681739730755955e-06, "loss": 0.7429, "step": 2396 }, { "epoch": 2.2329916123019573, "loss_cot": 0.4657326340675354, "loss_nocot": 0.31224483251571655, "step": 2396 }, { "epoch": 2.233923578751165, "grad_norm": 0.6695124461146527, "learning_rate": 5.674836037279945e-06, "loss": 0.7546, "step": 2397 }, { "epoch": 2.233923578751165, "loss_cot": 0.48379945755004883, "loss_nocot": 0.26794567704200745, "step": 2397 }, { "epoch": 2.234855545200373, "grad_norm": 0.6408527593753311, "learning_rate": 5.667932343803936e-06, "loss": 0.7993, "step": 2398 }, { "epoch": 2.234855545200373, "loss_cot": 0.5138959884643555, "loss_nocot": 0.25558608770370483, "step": 2398 }, { "epoch": 2.2357875116495807, "grad_norm": 0.6783638910796492, "learning_rate": 5.6610286503279255e-06, "loss": 0.7535, "step": 2399 }, { "epoch": 2.2357875116495807, "loss_cot": 0.5190343856811523, "loss_nocot": 0.19134736061096191, "step": 2399 }, { "epoch": 2.2367194780987885, "grad_norm": 0.564619434841395, "learning_rate": 5.654124956851916e-06, "loss": 0.6929, "step": 2400 }, { "epoch": 2.2367194780987885, "loss_cot": 0.5063497424125671, "loss_nocot": 0.26906058192253113, "step": 2400 }, { "epoch": 2.2376514445479962, "grad_norm": 0.6645845755452723, "learning_rate": 5.647221263375906e-06, "loss": 0.7539, "step": 2401 }, { "epoch": 2.2376514445479962, "loss_cot": 0.4309954047203064, "loss_nocot": 0.22410893440246582, "step": 2401 }, { "epoch": 2.238583410997204, "grad_norm": 0.6647155648471351, "learning_rate": 5.640317569899897e-06, "loss": 0.7452, "step": 2402 }, { "epoch": 2.238583410997204, "loss_cot": 0.43107253313064575, "loss_nocot": 0.2278495728969574, "step": 2402 }, { "epoch": 2.239515377446412, "grad_norm": 0.6601585825645695, "learning_rate": 5.6334138764238875e-06, "loss": 0.7553, "step": 2403 }, { "epoch": 2.239515377446412, "loss_cot": 0.44332343339920044, "loss_nocot": 0.21039947867393494, "step": 2403 }, { "epoch": 2.2404473438956196, "grad_norm": 0.5847242747912366, "learning_rate": 5.6265101829478774e-06, "loss": 0.6953, "step": 2404 }, { "epoch": 2.2404473438956196, "loss_cot": 0.446888267993927, "loss_nocot": 0.24632740020751953, "step": 2404 }, { "epoch": 2.2413793103448274, "grad_norm": 0.6436359450427885, "learning_rate": 5.619606489471868e-06, "loss": 0.7513, "step": 2405 }, { "epoch": 2.2413793103448274, "loss_cot": 0.5084678530693054, "loss_nocot": 0.28770893812179565, "step": 2405 }, { "epoch": 2.2423112767940356, "grad_norm": 0.652861135725292, "learning_rate": 5.612702795995858e-06, "loss": 0.7754, "step": 2406 }, { "epoch": 2.2423112767940356, "loss_cot": 0.5111614465713501, "loss_nocot": 0.34446683526039124, "step": 2406 }, { "epoch": 2.2432432432432434, "grad_norm": 0.6203395443284125, "learning_rate": 5.605799102519849e-06, "loss": 0.7502, "step": 2407 }, { "epoch": 2.2432432432432434, "loss_cot": 0.5040463209152222, "loss_nocot": 0.3161278963088989, "step": 2407 }, { "epoch": 2.244175209692451, "grad_norm": 0.6689873517708055, "learning_rate": 5.598895409043839e-06, "loss": 0.8116, "step": 2408 }, { "epoch": 2.244175209692451, "loss_cot": 0.5246340036392212, "loss_nocot": 0.23446863889694214, "step": 2408 }, { "epoch": 2.245107176141659, "grad_norm": 0.6391256814037508, "learning_rate": 5.591991715567829e-06, "loss": 0.7203, "step": 2409 }, { "epoch": 2.245107176141659, "loss_cot": 0.46185198426246643, "loss_nocot": 0.31760698556900024, "step": 2409 }, { "epoch": 2.246039142590867, "grad_norm": 0.6713588658014147, "learning_rate": 5.585088022091819e-06, "loss": 0.7694, "step": 2410 }, { "epoch": 2.246039142590867, "loss_cot": 0.5442076325416565, "loss_nocot": 0.2392864227294922, "step": 2410 }, { "epoch": 2.2469711090400746, "grad_norm": 0.6985051796377452, "learning_rate": 5.57818432861581e-06, "loss": 0.7987, "step": 2411 }, { "epoch": 2.2469711090400746, "loss_cot": 0.4430781900882721, "loss_nocot": 0.30367451906204224, "step": 2411 }, { "epoch": 2.2479030754892824, "grad_norm": 0.6617332965607134, "learning_rate": 5.571280635139801e-06, "loss": 0.7337, "step": 2412 }, { "epoch": 2.2479030754892824, "loss_cot": 0.49939030408859253, "loss_nocot": 0.25995051860809326, "step": 2412 }, { "epoch": 2.24883504193849, "grad_norm": 0.6533711729027413, "learning_rate": 5.564376941663791e-06, "loss": 0.764, "step": 2413 }, { "epoch": 2.24883504193849, "loss_cot": 0.5071934461593628, "loss_nocot": 0.20611363649368286, "step": 2413 }, { "epoch": 2.249767008387698, "grad_norm": 0.6343522804328692, "learning_rate": 5.557473248187781e-06, "loss": 0.7128, "step": 2414 }, { "epoch": 2.249767008387698, "loss_cot": 0.4928782880306244, "loss_nocot": 0.29022109508514404, "step": 2414 }, { "epoch": 2.2506989748369057, "grad_norm": 0.6536082078266175, "learning_rate": 5.550569554711771e-06, "loss": 0.7881, "step": 2415 }, { "epoch": 2.2506989748369057, "loss_cot": 0.4882975220680237, "loss_nocot": 0.22684046626091003, "step": 2415 }, { "epoch": 2.2516309412861135, "grad_norm": 0.6266541977355365, "learning_rate": 5.543665861235762e-06, "loss": 0.7299, "step": 2416 }, { "epoch": 2.2516309412861135, "loss_cot": 0.5259919762611389, "loss_nocot": 0.182715505361557, "step": 2416 }, { "epoch": 2.2525629077353218, "grad_norm": 0.64947346160091, "learning_rate": 5.536762167759752e-06, "loss": 0.7282, "step": 2417 }, { "epoch": 2.2525629077353218, "loss_cot": 0.5206425786018372, "loss_nocot": 0.23540523648262024, "step": 2417 }, { "epoch": 2.2534948741845295, "grad_norm": 0.7307864242532244, "learning_rate": 5.529858474283743e-06, "loss": 0.8054, "step": 2418 }, { "epoch": 2.2534948741845295, "loss_cot": 0.4222991466522217, "loss_nocot": 0.2728704810142517, "step": 2418 }, { "epoch": 2.2544268406337373, "grad_norm": 0.6388675327976312, "learning_rate": 5.5229547808077325e-06, "loss": 0.739, "step": 2419 }, { "epoch": 2.2544268406337373, "loss_cot": 0.4518812298774719, "loss_nocot": 0.2762024998664856, "step": 2419 }, { "epoch": 2.255358807082945, "grad_norm": 0.627113857709304, "learning_rate": 5.516051087331723e-06, "loss": 0.7479, "step": 2420 }, { "epoch": 2.255358807082945, "loss_cot": 0.5619041919708252, "loss_nocot": 0.3437194526195526, "step": 2420 }, { "epoch": 2.256290773532153, "grad_norm": 0.6882533042009946, "learning_rate": 5.509147393855713e-06, "loss": 0.8143, "step": 2421 }, { "epoch": 2.256290773532153, "loss_cot": 0.5001453161239624, "loss_nocot": 0.22138738632202148, "step": 2421 }, { "epoch": 2.2572227399813607, "grad_norm": 0.603887342218978, "learning_rate": 5.502243700379704e-06, "loss": 0.716, "step": 2422 }, { "epoch": 2.2572227399813607, "loss_cot": 0.5042319297790527, "loss_nocot": 0.21563994884490967, "step": 2422 }, { "epoch": 2.2581547064305685, "grad_norm": 0.684003516078753, "learning_rate": 5.4953400069036946e-06, "loss": 0.7908, "step": 2423 }, { "epoch": 2.2581547064305685, "loss_cot": 0.515128493309021, "loss_nocot": 0.2209438681602478, "step": 2423 }, { "epoch": 2.2590866728797763, "grad_norm": 0.6419990228603333, "learning_rate": 5.4884363134276845e-06, "loss": 0.7265, "step": 2424 }, { "epoch": 2.2590866728797763, "loss_cot": 0.4926997423171997, "loss_nocot": 0.28803831338882446, "step": 2424 }, { "epoch": 2.260018639328984, "grad_norm": 0.6342406803580113, "learning_rate": 5.481532619951675e-06, "loss": 0.7391, "step": 2425 }, { "epoch": 2.260018639328984, "loss_cot": 0.4645640552043915, "loss_nocot": 0.25157415866851807, "step": 2425 }, { "epoch": 2.260950605778192, "grad_norm": 0.5923629336739867, "learning_rate": 5.474628926475665e-06, "loss": 0.7392, "step": 2426 }, { "epoch": 2.260950605778192, "loss_cot": 0.4433892071247101, "loss_nocot": 0.3453095555305481, "step": 2426 }, { "epoch": 2.2618825722273996, "grad_norm": 0.6475719992026434, "learning_rate": 5.467725232999656e-06, "loss": 0.7324, "step": 2427 }, { "epoch": 2.2618825722273996, "loss_cot": 0.5048353672027588, "loss_nocot": 0.20702287554740906, "step": 2427 }, { "epoch": 2.262814538676608, "grad_norm": 0.6630953404204655, "learning_rate": 5.460821539523645e-06, "loss": 0.7502, "step": 2428 }, { "epoch": 2.262814538676608, "loss_cot": 0.47045013308525085, "loss_nocot": 0.4246445596218109, "step": 2428 }, { "epoch": 2.2637465051258157, "grad_norm": 0.645764758577892, "learning_rate": 5.4539178460476364e-06, "loss": 0.7448, "step": 2429 }, { "epoch": 2.2637465051258157, "loss_cot": 0.49319642782211304, "loss_nocot": 0.280031681060791, "step": 2429 }, { "epoch": 2.2646784715750234, "grad_norm": 0.7001270606549591, "learning_rate": 5.4470141525716255e-06, "loss": 0.7973, "step": 2430 }, { "epoch": 2.2646784715750234, "loss_cot": 0.4287793040275574, "loss_nocot": 0.26976174116134644, "step": 2430 }, { "epoch": 2.2656104380242312, "grad_norm": 0.6201669678767705, "learning_rate": 5.440110459095617e-06, "loss": 0.6941, "step": 2431 }, { "epoch": 2.2656104380242312, "loss_cot": 0.538937509059906, "loss_nocot": 0.24822959303855896, "step": 2431 }, { "epoch": 2.266542404473439, "grad_norm": 0.7106687618000972, "learning_rate": 5.433206765619608e-06, "loss": 0.7582, "step": 2432 }, { "epoch": 2.266542404473439, "loss_cot": 0.5369849801063538, "loss_nocot": 0.23095597326755524, "step": 2432 }, { "epoch": 2.267474370922647, "grad_norm": 0.648021556866287, "learning_rate": 5.426303072143597e-06, "loss": 0.759, "step": 2433 }, { "epoch": 2.267474370922647, "loss_cot": 0.516549825668335, "loss_nocot": 0.22005656361579895, "step": 2433 }, { "epoch": 2.2684063373718546, "grad_norm": 0.6560764031555282, "learning_rate": 5.419399378667588e-06, "loss": 0.7723, "step": 2434 }, { "epoch": 2.2684063373718546, "loss_cot": 0.5123977661132812, "loss_nocot": 0.2521495223045349, "step": 2434 }, { "epoch": 2.2693383038210624, "grad_norm": 0.6332030395689041, "learning_rate": 5.4124956851915774e-06, "loss": 0.7665, "step": 2435 }, { "epoch": 2.2693383038210624, "loss_cot": 0.45206689834594727, "loss_nocot": 0.19743067026138306, "step": 2435 }, { "epoch": 2.27027027027027, "grad_norm": 0.6220175360178501, "learning_rate": 5.405591991715568e-06, "loss": 0.7094, "step": 2436 }, { "epoch": 2.27027027027027, "loss_cot": 0.503628134727478, "loss_nocot": 0.19824859499931335, "step": 2436 }, { "epoch": 2.271202236719478, "grad_norm": 0.6188243553057756, "learning_rate": 5.398688298239558e-06, "loss": 0.7367, "step": 2437 }, { "epoch": 2.271202236719478, "loss_cot": 0.5065075159072876, "loss_nocot": 0.30750226974487305, "step": 2437 }, { "epoch": 2.2721342031686858, "grad_norm": 0.6285104480638173, "learning_rate": 5.391784604763549e-06, "loss": 0.7854, "step": 2438 }, { "epoch": 2.2721342031686858, "loss_cot": 0.4851208031177521, "loss_nocot": 0.2054424285888672, "step": 2438 }, { "epoch": 2.273066169617894, "grad_norm": 0.6517477022098079, "learning_rate": 5.384880911287539e-06, "loss": 0.6938, "step": 2439 }, { "epoch": 2.273066169617894, "loss_cot": 0.5039159059524536, "loss_nocot": 0.2582761347293854, "step": 2439 }, { "epoch": 2.2739981360671018, "grad_norm": 0.6273422025961229, "learning_rate": 5.377977217811529e-06, "loss": 0.7826, "step": 2440 }, { "epoch": 2.2739981360671018, "loss_cot": 0.47685930132865906, "loss_nocot": 0.24950671195983887, "step": 2440 }, { "epoch": 2.2749301025163096, "grad_norm": 0.6696205588506042, "learning_rate": 5.371073524335519e-06, "loss": 0.7628, "step": 2441 }, { "epoch": 2.2749301025163096, "loss_cot": 0.5251412391662598, "loss_nocot": 0.2774173319339752, "step": 2441 }, { "epoch": 2.2758620689655173, "grad_norm": 0.6094388768647001, "learning_rate": 5.36416983085951e-06, "loss": 0.7527, "step": 2442 }, { "epoch": 2.2758620689655173, "loss_cot": 0.5088222026824951, "loss_nocot": 0.19260793924331665, "step": 2442 }, { "epoch": 2.276794035414725, "grad_norm": 0.683387221301151, "learning_rate": 5.357266137383501e-06, "loss": 0.7825, "step": 2443 }, { "epoch": 2.276794035414725, "loss_cot": 0.5410382151603699, "loss_nocot": 0.22543367743492126, "step": 2443 }, { "epoch": 2.277726001863933, "grad_norm": 0.6380619697399796, "learning_rate": 5.350362443907491e-06, "loss": 0.7579, "step": 2444 }, { "epoch": 2.277726001863933, "loss_cot": 0.5031864643096924, "loss_nocot": 0.21422693133354187, "step": 2444 }, { "epoch": 2.2786579683131407, "grad_norm": 0.6886900493336242, "learning_rate": 5.343458750431481e-06, "loss": 0.7839, "step": 2445 }, { "epoch": 2.2786579683131407, "loss_cot": 0.4753825068473816, "loss_nocot": 0.23365771770477295, "step": 2445 }, { "epoch": 2.2795899347623485, "grad_norm": 0.6076306895585882, "learning_rate": 5.336555056955471e-06, "loss": 0.7246, "step": 2446 }, { "epoch": 2.2795899347623485, "loss_cot": 0.5331457257270813, "loss_nocot": 0.24383388459682465, "step": 2446 }, { "epoch": 2.2805219012115563, "grad_norm": 0.6024690444177359, "learning_rate": 5.329651363479462e-06, "loss": 0.7225, "step": 2447 }, { "epoch": 2.2805219012115563, "loss_cot": 0.45284032821655273, "loss_nocot": 0.2791684865951538, "step": 2447 }, { "epoch": 2.281453867660764, "grad_norm": 0.7021685573095845, "learning_rate": 5.322747670003452e-06, "loss": 0.7797, "step": 2448 }, { "epoch": 2.281453867660764, "loss_cot": 0.4766346216201782, "loss_nocot": 0.1986914575099945, "step": 2448 }, { "epoch": 2.282385834109972, "grad_norm": 0.590123780057772, "learning_rate": 5.315843976527443e-06, "loss": 0.7074, "step": 2449 }, { "epoch": 2.282385834109972, "loss_cot": 0.5643565654754639, "loss_nocot": 0.3421393632888794, "step": 2449 }, { "epoch": 2.28331780055918, "grad_norm": 0.639851101447047, "learning_rate": 5.3089402830514325e-06, "loss": 0.7708, "step": 2450 }, { "epoch": 2.28331780055918, "loss_cot": 0.538801908493042, "loss_nocot": 0.40190088748931885, "step": 2450 }, { "epoch": 2.284249767008388, "grad_norm": 0.6784828766225874, "learning_rate": 5.302036589575423e-06, "loss": 0.7921, "step": 2451 }, { "epoch": 2.284249767008388, "loss_cot": 0.5329070687294006, "loss_nocot": 0.28658950328826904, "step": 2451 }, { "epoch": 2.2851817334575957, "grad_norm": 0.6324887500203608, "learning_rate": 5.295132896099414e-06, "loss": 0.7595, "step": 2452 }, { "epoch": 2.2851817334575957, "loss_cot": 0.5151075124740601, "loss_nocot": 0.17785006761550903, "step": 2452 }, { "epoch": 2.2861136999068035, "grad_norm": 0.6949518530992529, "learning_rate": 5.288229202623404e-06, "loss": 0.7287, "step": 2453 }, { "epoch": 2.2861136999068035, "loss_cot": 0.5584545135498047, "loss_nocot": 0.21576693654060364, "step": 2453 }, { "epoch": 2.2870456663560113, "grad_norm": 0.6178224866853308, "learning_rate": 5.281325509147395e-06, "loss": 0.7215, "step": 2454 }, { "epoch": 2.2870456663560113, "loss_cot": 0.5160008072853088, "loss_nocot": 0.20052865147590637, "step": 2454 }, { "epoch": 2.287977632805219, "grad_norm": 0.6428872584726036, "learning_rate": 5.2744218156713845e-06, "loss": 0.7297, "step": 2455 }, { "epoch": 2.287977632805219, "loss_cot": 0.47601041197776794, "loss_nocot": 0.42495667934417725, "step": 2455 }, { "epoch": 2.288909599254427, "grad_norm": 0.6766058821548149, "learning_rate": 5.267518122195375e-06, "loss": 0.8034, "step": 2456 }, { "epoch": 2.288909599254427, "loss_cot": 0.5040698647499084, "loss_nocot": 0.24941304326057434, "step": 2456 }, { "epoch": 2.2898415657036346, "grad_norm": 0.6305033380043056, "learning_rate": 5.260614428719365e-06, "loss": 0.7259, "step": 2457 }, { "epoch": 2.2898415657036346, "loss_cot": 0.4867478013038635, "loss_nocot": 0.20958104729652405, "step": 2457 }, { "epoch": 2.2907735321528424, "grad_norm": 0.6287924607729957, "learning_rate": 5.253710735243356e-06, "loss": 0.7501, "step": 2458 }, { "epoch": 2.2907735321528424, "loss_cot": 0.4713435769081116, "loss_nocot": 0.29031217098236084, "step": 2458 }, { "epoch": 2.29170549860205, "grad_norm": 0.6127374243777198, "learning_rate": 5.246807041767346e-06, "loss": 0.7228, "step": 2459 }, { "epoch": 2.29170549860205, "loss_cot": 0.5352305173873901, "loss_nocot": 0.2660703957080841, "step": 2459 }, { "epoch": 2.292637465051258, "grad_norm": 0.6362704914333368, "learning_rate": 5.2399033482913364e-06, "loss": 0.7442, "step": 2460 }, { "epoch": 2.292637465051258, "loss_cot": 0.5193825960159302, "loss_nocot": 0.20866817235946655, "step": 2460 }, { "epoch": 2.293569431500466, "grad_norm": 0.6097773270707771, "learning_rate": 5.232999654815326e-06, "loss": 0.7335, "step": 2461 }, { "epoch": 2.293569431500466, "loss_cot": 0.47236520051956177, "loss_nocot": 0.2192668467760086, "step": 2461 }, { "epoch": 2.294501397949674, "grad_norm": 0.6308768094232038, "learning_rate": 5.226095961339317e-06, "loss": 0.7124, "step": 2462 }, { "epoch": 2.294501397949674, "loss_cot": 0.5091468095779419, "loss_nocot": 0.27957579493522644, "step": 2462 }, { "epoch": 2.295433364398882, "grad_norm": 0.686528533531319, "learning_rate": 5.219192267863308e-06, "loss": 0.7312, "step": 2463 }, { "epoch": 2.295433364398882, "loss_cot": 0.4733237326145172, "loss_nocot": 0.25219887495040894, "step": 2463 }, { "epoch": 2.2963653308480896, "grad_norm": 0.6869463967375067, "learning_rate": 5.212288574387298e-06, "loss": 0.7318, "step": 2464 }, { "epoch": 2.2963653308480896, "loss_cot": 0.464030921459198, "loss_nocot": 0.21003177762031555, "step": 2464 }, { "epoch": 2.2972972972972974, "grad_norm": 0.6394687449376149, "learning_rate": 5.205384880911288e-06, "loss": 0.7416, "step": 2465 }, { "epoch": 2.2972972972972974, "loss_cot": 0.4974824786186218, "loss_nocot": 0.1922207474708557, "step": 2465 }, { "epoch": 2.298229263746505, "grad_norm": 0.6722006052388544, "learning_rate": 5.198481187435278e-06, "loss": 0.7766, "step": 2466 }, { "epoch": 2.298229263746505, "loss_cot": 0.45381349325180054, "loss_nocot": 0.23885446786880493, "step": 2466 }, { "epoch": 2.299161230195713, "grad_norm": 0.6409786032035096, "learning_rate": 5.191577493959269e-06, "loss": 0.7278, "step": 2467 }, { "epoch": 2.299161230195713, "loss_cot": 0.47672411799430847, "loss_nocot": 0.2499573677778244, "step": 2467 }, { "epoch": 2.3000931966449207, "grad_norm": 0.6149836367801501, "learning_rate": 5.184673800483259e-06, "loss": 0.7225, "step": 2468 }, { "epoch": 2.3000931966449207, "loss_cot": 0.4720638394355774, "loss_nocot": 0.3588077127933502, "step": 2468 }, { "epoch": 2.3010251630941285, "grad_norm": 0.6525929020688518, "learning_rate": 5.17777010700725e-06, "loss": 0.728, "step": 2469 }, { "epoch": 2.3010251630941285, "loss_cot": 0.5573985576629639, "loss_nocot": 0.251727819442749, "step": 2469 }, { "epoch": 2.3019571295433363, "grad_norm": 0.6398175943057214, "learning_rate": 5.1708664135312395e-06, "loss": 0.777, "step": 2470 }, { "epoch": 2.3019571295433363, "loss_cot": 0.48716554045677185, "loss_nocot": 0.26834502816200256, "step": 2470 }, { "epoch": 2.302889095992544, "grad_norm": 7.829263979188059, "learning_rate": 5.16396272005523e-06, "loss": 0.7727, "step": 2471 }, { "epoch": 2.302889095992544, "loss_cot": 0.5062693357467651, "loss_nocot": 0.2815250754356384, "step": 2471 }, { "epoch": 2.3038210624417523, "grad_norm": 0.6827037101553476, "learning_rate": 5.15705902657922e-06, "loss": 0.7963, "step": 2472 }, { "epoch": 2.3038210624417523, "loss_cot": 0.5082489252090454, "loss_nocot": 0.2572861313819885, "step": 2472 }, { "epoch": 2.3047530288909597, "grad_norm": 0.6060860785751804, "learning_rate": 5.150155333103211e-06, "loss": 0.7659, "step": 2473 }, { "epoch": 2.3047530288909597, "loss_cot": 0.48914381861686707, "loss_nocot": 0.2478557527065277, "step": 2473 }, { "epoch": 2.305684995340168, "grad_norm": 0.6595566536747398, "learning_rate": 5.143251639627202e-06, "loss": 0.7119, "step": 2474 }, { "epoch": 2.305684995340168, "loss_cot": 0.46977555751800537, "loss_nocot": 0.2908723056316376, "step": 2474 }, { "epoch": 2.3066169617893757, "grad_norm": 0.6769741006613031, "learning_rate": 5.1363479461511915e-06, "loss": 0.7979, "step": 2475 }, { "epoch": 2.3066169617893757, "loss_cot": 0.44684773683547974, "loss_nocot": 0.25684720277786255, "step": 2475 }, { "epoch": 2.3075489282385835, "grad_norm": 0.6541006463928354, "learning_rate": 5.129444252675182e-06, "loss": 0.7364, "step": 2476 }, { "epoch": 2.3075489282385835, "loss_cot": 0.4709641933441162, "loss_nocot": 0.22664085030555725, "step": 2476 }, { "epoch": 2.3084808946877913, "grad_norm": 0.640450912006436, "learning_rate": 5.122540559199172e-06, "loss": 0.7532, "step": 2477 }, { "epoch": 2.3084808946877913, "loss_cot": 0.5204899311065674, "loss_nocot": 0.2725703716278076, "step": 2477 }, { "epoch": 2.309412861136999, "grad_norm": 0.749480301278966, "learning_rate": 5.115636865723163e-06, "loss": 0.7911, "step": 2478 }, { "epoch": 2.309412861136999, "loss_cot": 0.5041366815567017, "loss_nocot": 0.2650865614414215, "step": 2478 }, { "epoch": 2.310344827586207, "grad_norm": 0.6163507752524041, "learning_rate": 5.108733172247152e-06, "loss": 0.6992, "step": 2479 }, { "epoch": 2.310344827586207, "loss_cot": 0.5738336443901062, "loss_nocot": 0.33725064992904663, "step": 2479 }, { "epoch": 2.3112767940354146, "grad_norm": 0.6486101809432383, "learning_rate": 5.1018294787711435e-06, "loss": 0.767, "step": 2480 }, { "epoch": 2.3112767940354146, "loss_cot": 0.5238748788833618, "loss_nocot": 0.26931944489479065, "step": 2480 }, { "epoch": 2.3122087604846224, "grad_norm": 0.6881383314658817, "learning_rate": 5.0949257852951325e-06, "loss": 0.768, "step": 2481 }, { "epoch": 2.3122087604846224, "loss_cot": 0.505557656288147, "loss_nocot": 0.2274152934551239, "step": 2481 }, { "epoch": 2.31314072693383, "grad_norm": 0.679012875000789, "learning_rate": 5.088022091819124e-06, "loss": 0.8324, "step": 2482 }, { "epoch": 2.31314072693383, "loss_cot": 0.5116449594497681, "loss_nocot": 0.2798166871070862, "step": 2482 }, { "epoch": 2.3140726933830384, "grad_norm": 0.6727948847729109, "learning_rate": 5.081118398343115e-06, "loss": 0.7491, "step": 2483 }, { "epoch": 2.3140726933830384, "loss_cot": 0.46464210748672485, "loss_nocot": 0.35687071084976196, "step": 2483 }, { "epoch": 2.315004659832246, "grad_norm": 0.6643786431003655, "learning_rate": 5.074214704867104e-06, "loss": 0.7508, "step": 2484 }, { "epoch": 2.315004659832246, "loss_cot": 0.4512384235858917, "loss_nocot": 0.302531898021698, "step": 2484 }, { "epoch": 2.315936626281454, "grad_norm": 0.6692936553989506, "learning_rate": 5.0673110113910954e-06, "loss": 0.735, "step": 2485 }, { "epoch": 2.315936626281454, "loss_cot": 0.46601492166519165, "loss_nocot": 0.30389589071273804, "step": 2485 }, { "epoch": 2.316868592730662, "grad_norm": 0.6746723854300793, "learning_rate": 5.0604073179150845e-06, "loss": 0.7494, "step": 2486 }, { "epoch": 2.316868592730662, "loss_cot": 0.5399258136749268, "loss_nocot": 0.27903932332992554, "step": 2486 }, { "epoch": 2.3178005591798696, "grad_norm": 0.6056808854043211, "learning_rate": 5.053503624439075e-06, "loss": 0.7544, "step": 2487 }, { "epoch": 2.3178005591798696, "loss_cot": 0.426779180765152, "loss_nocot": 0.2655683755874634, "step": 2487 }, { "epoch": 2.3187325256290774, "grad_norm": 0.6819731720296249, "learning_rate": 5.046599930963065e-06, "loss": 0.7647, "step": 2488 }, { "epoch": 2.3187325256290774, "loss_cot": 0.5199618339538574, "loss_nocot": 0.25600430369377136, "step": 2488 }, { "epoch": 2.319664492078285, "grad_norm": 0.6416597884931303, "learning_rate": 5.039696237487056e-06, "loss": 0.7393, "step": 2489 }, { "epoch": 2.319664492078285, "loss_cot": 0.47104838490486145, "loss_nocot": 0.21628761291503906, "step": 2489 }, { "epoch": 2.320596458527493, "grad_norm": 0.5997612530047696, "learning_rate": 5.032792544011046e-06, "loss": 0.6992, "step": 2490 }, { "epoch": 2.320596458527493, "loss_cot": 0.5337921977043152, "loss_nocot": 0.2556861639022827, "step": 2490 }, { "epoch": 2.3215284249767008, "grad_norm": 0.6250650524270187, "learning_rate": 5.0258888505350364e-06, "loss": 0.7938, "step": 2491 }, { "epoch": 2.3215284249767008, "loss_cot": 0.5045154094696045, "loss_nocot": 0.25014829635620117, "step": 2491 }, { "epoch": 2.3224603914259085, "grad_norm": 0.686469269925527, "learning_rate": 5.018985157059026e-06, "loss": 0.786, "step": 2492 }, { "epoch": 2.3224603914259085, "loss_cot": 0.5539321899414062, "loss_nocot": 0.23464027047157288, "step": 2492 }, { "epoch": 2.3233923578751163, "grad_norm": 0.6819078095438043, "learning_rate": 5.012081463583017e-06, "loss": 0.8125, "step": 2493 }, { "epoch": 2.3233923578751163, "loss_cot": 0.4849748909473419, "loss_nocot": 0.16892805695533752, "step": 2493 }, { "epoch": 2.3243243243243246, "grad_norm": 0.6247383286087436, "learning_rate": 5.005177770107008e-06, "loss": 0.7553, "step": 2494 }, { "epoch": 2.3243243243243246, "loss_cot": 0.49996352195739746, "loss_nocot": 0.3437419533729553, "step": 2494 }, { "epoch": 2.325256290773532, "grad_norm": 0.6586017757908307, "learning_rate": 4.998274076630998e-06, "loss": 0.7858, "step": 2495 }, { "epoch": 2.325256290773532, "loss_cot": 0.4991597533226013, "loss_nocot": 0.23020146787166595, "step": 2495 }, { "epoch": 2.32618825722274, "grad_norm": 0.6443681573037445, "learning_rate": 4.991370383154988e-06, "loss": 0.7744, "step": 2496 }, { "epoch": 2.32618825722274, "loss_cot": 0.45912033319473267, "loss_nocot": 0.2801419794559479, "step": 2496 }, { "epoch": 2.327120223671948, "grad_norm": 0.6511150029239745, "learning_rate": 4.984466689678978e-06, "loss": 0.7326, "step": 2497 }, { "epoch": 2.327120223671948, "loss_cot": 0.5465015172958374, "loss_nocot": 0.28105002641677856, "step": 2497 }, { "epoch": 2.3280521901211557, "grad_norm": 0.6697666414875928, "learning_rate": 4.977562996202969e-06, "loss": 0.8234, "step": 2498 }, { "epoch": 2.3280521901211557, "loss_cot": 0.47733375430107117, "loss_nocot": 0.1522120237350464, "step": 2498 }, { "epoch": 2.3289841565703635, "grad_norm": 0.6041219677845305, "learning_rate": 4.97065930272696e-06, "loss": 0.7133, "step": 2499 }, { "epoch": 2.3289841565703635, "loss_cot": 0.4768950343132019, "loss_nocot": 0.24575668573379517, "step": 2499 }, { "epoch": 2.3299161230195713, "grad_norm": 0.6193668690272817, "learning_rate": 4.96375560925095e-06, "loss": 0.7166, "step": 2500 }, { "epoch": 2.3299161230195713, "loss_cot": 0.5676107406616211, "loss_nocot": 0.24548842012882233, "step": 2500 }, { "epoch": 2.330848089468779, "grad_norm": 0.6764959670427221, "learning_rate": 4.95685191577494e-06, "loss": 0.7577, "step": 2501 }, { "epoch": 2.330848089468779, "loss_cot": 0.4507817327976227, "loss_nocot": 0.2690788805484772, "step": 2501 }, { "epoch": 2.331780055917987, "grad_norm": 0.6112213496803096, "learning_rate": 4.94994822229893e-06, "loss": 0.7037, "step": 2502 }, { "epoch": 2.331780055917987, "loss_cot": 0.48492687940597534, "loss_nocot": 0.1946534812450409, "step": 2502 }, { "epoch": 2.3327120223671947, "grad_norm": 0.6905126585648834, "learning_rate": 4.943044528822921e-06, "loss": 0.7304, "step": 2503 }, { "epoch": 2.3327120223671947, "loss_cot": 0.4282480478286743, "loss_nocot": 0.24533189833164215, "step": 2503 }, { "epoch": 2.3336439888164024, "grad_norm": 0.6545790941002932, "learning_rate": 4.936140835346911e-06, "loss": 0.7279, "step": 2504 }, { "epoch": 2.3336439888164024, "loss_cot": 0.5309596657752991, "loss_nocot": 0.33923161029815674, "step": 2504 }, { "epoch": 2.3345759552656107, "grad_norm": 0.6550163326179692, "learning_rate": 4.929237141870902e-06, "loss": 0.8112, "step": 2505 }, { "epoch": 2.3345759552656107, "loss_cot": 0.5102007985115051, "loss_nocot": 0.2131149023771286, "step": 2505 }, { "epoch": 2.335507921714818, "grad_norm": 0.657664331146087, "learning_rate": 4.9223334483948915e-06, "loss": 0.7632, "step": 2506 }, { "epoch": 2.335507921714818, "loss_cot": 0.45271164178848267, "loss_nocot": 0.21722114086151123, "step": 2506 }, { "epoch": 2.3364398881640263, "grad_norm": 0.6163416418105415, "learning_rate": 4.915429754918881e-06, "loss": 0.7594, "step": 2507 }, { "epoch": 2.3364398881640263, "loss_cot": 0.5625373125076294, "loss_nocot": 0.2071441113948822, "step": 2507 }, { "epoch": 2.337371854613234, "grad_norm": 0.6354012853240844, "learning_rate": 4.908526061442873e-06, "loss": 0.7756, "step": 2508 }, { "epoch": 2.337371854613234, "loss_cot": 0.5054823160171509, "loss_nocot": 0.22021165490150452, "step": 2508 }, { "epoch": 2.338303821062442, "grad_norm": 0.6312537392234595, "learning_rate": 4.901622367966863e-06, "loss": 0.7791, "step": 2509 }, { "epoch": 2.338303821062442, "loss_cot": 0.525395929813385, "loss_nocot": 0.24739721417427063, "step": 2509 }, { "epoch": 2.3392357875116496, "grad_norm": 0.6951900871260512, "learning_rate": 4.894718674490853e-06, "loss": 0.8055, "step": 2510 }, { "epoch": 2.3392357875116496, "loss_cot": 0.5082524418830872, "loss_nocot": 0.5031512975692749, "step": 2510 }, { "epoch": 2.3401677539608574, "grad_norm": 0.6769510280896391, "learning_rate": 4.8878149810148435e-06, "loss": 0.8118, "step": 2511 }, { "epoch": 2.3401677539608574, "loss_cot": 0.4995702803134918, "loss_nocot": 0.28740477561950684, "step": 2511 }, { "epoch": 2.341099720410065, "grad_norm": 0.6668566222999576, "learning_rate": 4.880911287538833e-06, "loss": 0.7575, "step": 2512 }, { "epoch": 2.341099720410065, "loss_cot": 0.49833041429519653, "loss_nocot": 0.16747432947158813, "step": 2512 }, { "epoch": 2.342031686859273, "grad_norm": 0.63260558532882, "learning_rate": 4.874007594062824e-06, "loss": 0.7139, "step": 2513 }, { "epoch": 2.342031686859273, "loss_cot": 0.5120671391487122, "loss_nocot": 0.3157936930656433, "step": 2513 }, { "epoch": 2.3429636533084808, "grad_norm": 0.6662671439924813, "learning_rate": 4.867103900586814e-06, "loss": 0.7737, "step": 2514 }, { "epoch": 2.3429636533084808, "loss_cot": 0.5656626224517822, "loss_nocot": 0.20072896778583527, "step": 2514 }, { "epoch": 2.3438956197576886, "grad_norm": 0.6206520541049347, "learning_rate": 4.860200207110805e-06, "loss": 0.7692, "step": 2515 }, { "epoch": 2.3438956197576886, "loss_cot": 0.5110032558441162, "loss_nocot": 0.30236107110977173, "step": 2515 }, { "epoch": 2.344827586206897, "grad_norm": 0.6376387996927385, "learning_rate": 4.853296513634795e-06, "loss": 0.7715, "step": 2516 }, { "epoch": 2.344827586206897, "loss_cot": 0.45790934562683105, "loss_nocot": 0.2744922637939453, "step": 2516 }, { "epoch": 2.345759552656104, "grad_norm": 0.6363217893694867, "learning_rate": 4.846392820158785e-06, "loss": 0.8035, "step": 2517 }, { "epoch": 2.345759552656104, "loss_cot": 0.5180983543395996, "loss_nocot": 0.30653321743011475, "step": 2517 }, { "epoch": 2.3466915191053124, "grad_norm": 0.6553122603675057, "learning_rate": 4.839489126682776e-06, "loss": 0.7575, "step": 2518 }, { "epoch": 2.3466915191053124, "loss_cot": 0.47877833247184753, "loss_nocot": 0.22849208116531372, "step": 2518 }, { "epoch": 2.34762348555452, "grad_norm": 0.6288150640661072, "learning_rate": 4.832585433206766e-06, "loss": 0.7411, "step": 2519 }, { "epoch": 2.34762348555452, "loss_cot": 0.5435468554496765, "loss_nocot": 0.3040720820426941, "step": 2519 }, { "epoch": 2.348555452003728, "grad_norm": 0.6530027405183145, "learning_rate": 4.825681739730757e-06, "loss": 0.7591, "step": 2520 }, { "epoch": 2.348555452003728, "loss_cot": 0.43926429748535156, "loss_nocot": 0.22036519646644592, "step": 2520 }, { "epoch": 2.3494874184529357, "grad_norm": 0.6536267752392557, "learning_rate": 4.8187780462547465e-06, "loss": 0.7699, "step": 2521 }, { "epoch": 2.3494874184529357, "loss_cot": 0.4794537425041199, "loss_nocot": 0.2419794648885727, "step": 2521 }, { "epoch": 2.3504193849021435, "grad_norm": 0.6478795472525745, "learning_rate": 4.811874352778737e-06, "loss": 0.751, "step": 2522 }, { "epoch": 2.3504193849021435, "loss_cot": 0.4971347451210022, "loss_nocot": 0.2865154445171356, "step": 2522 }, { "epoch": 2.3513513513513513, "grad_norm": 0.6438172787642342, "learning_rate": 4.804970659302727e-06, "loss": 0.7491, "step": 2523 }, { "epoch": 2.3513513513513513, "loss_cot": 0.49324923753738403, "loss_nocot": 0.3025158643722534, "step": 2523 }, { "epoch": 2.352283317800559, "grad_norm": 0.6601459910016684, "learning_rate": 4.798066965826718e-06, "loss": 0.7685, "step": 2524 }, { "epoch": 2.352283317800559, "loss_cot": 0.527550220489502, "loss_nocot": 0.438152939081192, "step": 2524 }, { "epoch": 2.353215284249767, "grad_norm": 0.6883850456056747, "learning_rate": 4.791163272350708e-06, "loss": 0.8145, "step": 2525 }, { "epoch": 2.353215284249767, "loss_cot": 0.49097394943237305, "loss_nocot": 0.22801972925662994, "step": 2525 }, { "epoch": 2.3541472506989747, "grad_norm": 0.6345276757674458, "learning_rate": 4.7842595788746985e-06, "loss": 0.7639, "step": 2526 }, { "epoch": 2.3541472506989747, "loss_cot": 0.5286282300949097, "loss_nocot": 0.3995586037635803, "step": 2526 }, { "epoch": 2.355079217148183, "grad_norm": 0.670383751905294, "learning_rate": 4.777355885398688e-06, "loss": 0.7779, "step": 2527 }, { "epoch": 2.355079217148183, "loss_cot": 0.4780208468437195, "loss_nocot": 0.21769756078720093, "step": 2527 }, { "epoch": 2.3560111835973903, "grad_norm": 0.6049756170476495, "learning_rate": 4.770452191922679e-06, "loss": 0.7055, "step": 2528 }, { "epoch": 2.3560111835973903, "loss_cot": 0.4574727416038513, "loss_nocot": 0.27286410331726074, "step": 2528 }, { "epoch": 2.3569431500465985, "grad_norm": 0.669850016855681, "learning_rate": 4.76354849844667e-06, "loss": 0.7884, "step": 2529 }, { "epoch": 2.3569431500465985, "loss_cot": 0.560218334197998, "loss_nocot": 0.2630486786365509, "step": 2529 }, { "epoch": 2.3578751164958063, "grad_norm": 0.6408964736996997, "learning_rate": 4.75664480497066e-06, "loss": 0.7588, "step": 2530 }, { "epoch": 2.3578751164958063, "loss_cot": 0.555975079536438, "loss_nocot": 0.29852229356765747, "step": 2530 }, { "epoch": 2.358807082945014, "grad_norm": 0.6391712208521927, "learning_rate": 4.7497411114946505e-06, "loss": 0.7612, "step": 2531 }, { "epoch": 2.358807082945014, "loss_cot": 0.5230541229248047, "loss_nocot": 0.24404534697532654, "step": 2531 }, { "epoch": 2.359739049394222, "grad_norm": 0.6384274190518752, "learning_rate": 4.74283741801864e-06, "loss": 0.74, "step": 2532 }, { "epoch": 2.359739049394222, "loss_cot": 0.4726073145866394, "loss_nocot": 0.2891489565372467, "step": 2532 }, { "epoch": 2.3606710158434296, "grad_norm": 0.6450361903628644, "learning_rate": 4.73593372454263e-06, "loss": 0.7426, "step": 2533 }, { "epoch": 2.3606710158434296, "loss_cot": 0.5071746110916138, "loss_nocot": 0.24723833799362183, "step": 2533 }, { "epoch": 2.3616029822926374, "grad_norm": 0.5943461771675544, "learning_rate": 4.729030031066621e-06, "loss": 0.7296, "step": 2534 }, { "epoch": 2.3616029822926374, "loss_cot": 0.4983029067516327, "loss_nocot": 0.23133927583694458, "step": 2534 }, { "epoch": 2.362534948741845, "grad_norm": 0.7304521561639498, "learning_rate": 4.722126337590611e-06, "loss": 0.7865, "step": 2535 }, { "epoch": 2.362534948741845, "loss_cot": 0.4822935461997986, "loss_nocot": 0.39034727215766907, "step": 2535 }, { "epoch": 2.363466915191053, "grad_norm": 0.99535357831053, "learning_rate": 4.715222644114602e-06, "loss": 0.7811, "step": 2536 }, { "epoch": 2.363466915191053, "loss_cot": 0.5094420313835144, "loss_nocot": 0.28354817628860474, "step": 2536 }, { "epoch": 2.364398881640261, "grad_norm": 0.6459247538937155, "learning_rate": 4.7083189506385915e-06, "loss": 0.7802, "step": 2537 }, { "epoch": 2.364398881640261, "loss_cot": 0.5215068459510803, "loss_nocot": 0.2230319380760193, "step": 2537 }, { "epoch": 2.3653308480894686, "grad_norm": 0.5785032287062533, "learning_rate": 4.701415257162582e-06, "loss": 0.7199, "step": 2538 }, { "epoch": 2.3653308480894686, "loss_cot": 0.37909016013145447, "loss_nocot": 0.23194804787635803, "step": 2538 }, { "epoch": 2.3662628145386764, "grad_norm": 0.6355505373984679, "learning_rate": 4.694511563686573e-06, "loss": 0.7297, "step": 2539 }, { "epoch": 2.3662628145386764, "loss_cot": 0.4986344575881958, "loss_nocot": 0.2816922068595886, "step": 2539 }, { "epoch": 2.3671947809878846, "grad_norm": 0.6490799827007804, "learning_rate": 4.687607870210563e-06, "loss": 0.6859, "step": 2540 }, { "epoch": 2.3671947809878846, "loss_cot": 0.5045379400253296, "loss_nocot": 0.18978643417358398, "step": 2540 }, { "epoch": 2.3681267474370924, "grad_norm": 0.6570066711535698, "learning_rate": 4.6807041767345536e-06, "loss": 0.7221, "step": 2541 }, { "epoch": 2.3681267474370924, "loss_cot": 0.5601776838302612, "loss_nocot": 0.2647358775138855, "step": 2541 }, { "epoch": 2.3690587138863, "grad_norm": 0.5988164088899409, "learning_rate": 4.6738004832585435e-06, "loss": 0.7403, "step": 2542 }, { "epoch": 2.3690587138863, "loss_cot": 0.5178830623626709, "loss_nocot": 0.3248737156391144, "step": 2542 }, { "epoch": 2.369990680335508, "grad_norm": 0.6644162048963523, "learning_rate": 4.666896789782534e-06, "loss": 0.8372, "step": 2543 }, { "epoch": 2.369990680335508, "loss_cot": 0.560415506362915, "loss_nocot": 0.1875857710838318, "step": 2543 }, { "epoch": 2.3709226467847158, "grad_norm": 0.6471045327484731, "learning_rate": 4.659993096306524e-06, "loss": 0.7575, "step": 2544 }, { "epoch": 2.3709226467847158, "loss_cot": 0.5188833475112915, "loss_nocot": 0.30646878480911255, "step": 2544 }, { "epoch": 2.3718546132339235, "grad_norm": 0.7597818979391422, "learning_rate": 4.653089402830515e-06, "loss": 0.8528, "step": 2545 }, { "epoch": 2.3718546132339235, "loss_cot": 0.4320230484008789, "loss_nocot": 0.30560070276260376, "step": 2545 }, { "epoch": 2.3727865796831313, "grad_norm": 0.6636434772571306, "learning_rate": 4.646185709354505e-06, "loss": 0.7706, "step": 2546 }, { "epoch": 2.3727865796831313, "loss_cot": 0.5481405258178711, "loss_nocot": 0.2096085548400879, "step": 2546 }, { "epoch": 2.373718546132339, "grad_norm": 0.6063758269423686, "learning_rate": 4.6392820158784954e-06, "loss": 0.7127, "step": 2547 }, { "epoch": 2.373718546132339, "loss_cot": 0.46495872735977173, "loss_nocot": 0.23168815672397614, "step": 2547 }, { "epoch": 2.374650512581547, "grad_norm": 0.671648919867664, "learning_rate": 4.632378322402486e-06, "loss": 0.739, "step": 2548 }, { "epoch": 2.374650512581547, "loss_cot": 0.48551270365715027, "loss_nocot": 0.22475551068782806, "step": 2548 }, { "epoch": 2.3755824790307547, "grad_norm": 0.6121303492010118, "learning_rate": 4.625474628926476e-06, "loss": 0.7098, "step": 2549 }, { "epoch": 2.3755824790307547, "loss_cot": 0.4628944993019104, "loss_nocot": 0.23824073374271393, "step": 2549 }, { "epoch": 2.3765144454799625, "grad_norm": 0.7013346153513992, "learning_rate": 4.618570935450467e-06, "loss": 0.7981, "step": 2550 }, { "epoch": 2.3765144454799625, "loss_cot": 0.46872478723526, "loss_nocot": 0.25731271505355835, "step": 2550 }, { "epoch": 2.3774464119291707, "grad_norm": 0.6080890815987596, "learning_rate": 4.611667241974457e-06, "loss": 0.719, "step": 2551 }, { "epoch": 2.3774464119291707, "loss_cot": 0.4604557454586029, "loss_nocot": 0.2330472469329834, "step": 2551 }, { "epoch": 2.3783783783783785, "grad_norm": 0.6370251810170245, "learning_rate": 4.604763548498447e-06, "loss": 0.7013, "step": 2552 }, { "epoch": 2.3783783783783785, "loss_cot": 0.50594562292099, "loss_nocot": 0.21111592650413513, "step": 2552 }, { "epoch": 2.3793103448275863, "grad_norm": 0.6394951193862957, "learning_rate": 4.597859855022437e-06, "loss": 0.7504, "step": 2553 }, { "epoch": 2.3793103448275863, "loss_cot": 0.4674612283706665, "loss_nocot": 0.24713006615638733, "step": 2553 }, { "epoch": 2.380242311276794, "grad_norm": 0.6630274830847277, "learning_rate": 4.590956161546428e-06, "loss": 0.744, "step": 2554 }, { "epoch": 2.380242311276794, "loss_cot": 0.51680588722229, "loss_nocot": 0.23985964059829712, "step": 2554 }, { "epoch": 2.381174277726002, "grad_norm": 0.6419560286711885, "learning_rate": 4.584052468070418e-06, "loss": 0.7342, "step": 2555 }, { "epoch": 2.381174277726002, "loss_cot": 0.517759382724762, "loss_nocot": 0.19625264406204224, "step": 2555 }, { "epoch": 2.3821062441752097, "grad_norm": 0.7398685008977974, "learning_rate": 4.577148774594408e-06, "loss": 0.7515, "step": 2556 }, { "epoch": 2.3821062441752097, "loss_cot": 0.55439293384552, "loss_nocot": 0.23463302850723267, "step": 2556 }, { "epoch": 2.3830382106244175, "grad_norm": 0.6598561730413212, "learning_rate": 4.5702450811183985e-06, "loss": 0.749, "step": 2557 }, { "epoch": 2.3830382106244175, "loss_cot": 0.500311017036438, "loss_nocot": 0.3042014241218567, "step": 2557 }, { "epoch": 2.3839701770736252, "grad_norm": 0.6967842316077617, "learning_rate": 4.563341387642389e-06, "loss": 0.7778, "step": 2558 }, { "epoch": 2.3839701770736252, "loss_cot": 0.5628005266189575, "loss_nocot": 0.2588346004486084, "step": 2558 }, { "epoch": 2.384902143522833, "grad_norm": 0.6207282600202867, "learning_rate": 4.55643769416638e-06, "loss": 0.7714, "step": 2559 }, { "epoch": 2.384902143522833, "loss_cot": 0.544895350933075, "loss_nocot": 0.19103914499282837, "step": 2559 }, { "epoch": 2.385834109972041, "grad_norm": 0.6258774196031852, "learning_rate": 4.54953400069037e-06, "loss": 0.729, "step": 2560 }, { "epoch": 2.385834109972041, "loss_cot": 0.5831416249275208, "loss_nocot": 0.35542556643486023, "step": 2560 }, { "epoch": 2.3867660764212486, "grad_norm": 0.6797312896672275, "learning_rate": 4.54263030721436e-06, "loss": 0.8081, "step": 2561 }, { "epoch": 2.3867660764212486, "loss_cot": 0.4738195836544037, "loss_nocot": 0.22133047878742218, "step": 2561 }, { "epoch": 2.387698042870457, "grad_norm": 0.6349918436320331, "learning_rate": 4.5357266137383505e-06, "loss": 0.7401, "step": 2562 }, { "epoch": 2.387698042870457, "loss_cot": 0.5266886353492737, "loss_nocot": 0.2633765637874603, "step": 2562 }, { "epoch": 2.3886300093196646, "grad_norm": 0.690522789652119, "learning_rate": 4.52882292026234e-06, "loss": 0.8024, "step": 2563 }, { "epoch": 2.3886300093196646, "loss_cot": 0.5085854530334473, "loss_nocot": 0.2999962568283081, "step": 2563 }, { "epoch": 2.3895619757688724, "grad_norm": 0.7165763769129309, "learning_rate": 4.521919226786331e-06, "loss": 0.8245, "step": 2564 }, { "epoch": 2.3895619757688724, "loss_cot": 0.4986441731452942, "loss_nocot": 0.2425258606672287, "step": 2564 }, { "epoch": 2.39049394221808, "grad_norm": 0.6737478536229695, "learning_rate": 4.515015533310321e-06, "loss": 0.7833, "step": 2565 }, { "epoch": 2.39049394221808, "loss_cot": 0.4810918867588043, "loss_nocot": 0.1874018907546997, "step": 2565 }, { "epoch": 2.391425908667288, "grad_norm": 0.7190451095023348, "learning_rate": 4.508111839834312e-06, "loss": 0.7123, "step": 2566 }, { "epoch": 2.391425908667288, "loss_cot": 0.5220165252685547, "loss_nocot": 0.2621905207633972, "step": 2566 }, { "epoch": 2.392357875116496, "grad_norm": 0.6847167113555779, "learning_rate": 4.501208146358302e-06, "loss": 0.7618, "step": 2567 }, { "epoch": 2.392357875116496, "loss_cot": 0.5012134909629822, "loss_nocot": 0.2581242322921753, "step": 2567 }, { "epoch": 2.3932898415657036, "grad_norm": 0.6843466485898798, "learning_rate": 4.494304452882292e-06, "loss": 0.7648, "step": 2568 }, { "epoch": 2.3932898415657036, "loss_cot": 0.5644490718841553, "loss_nocot": 0.14844003319740295, "step": 2568 }, { "epoch": 2.3942218080149114, "grad_norm": 0.6524898048171297, "learning_rate": 4.487400759406283e-06, "loss": 0.7659, "step": 2569 }, { "epoch": 2.3942218080149114, "loss_cot": 0.503600001335144, "loss_nocot": 0.2213878631591797, "step": 2569 }, { "epoch": 2.395153774464119, "grad_norm": 0.6106152474807955, "learning_rate": 4.480497065930273e-06, "loss": 0.7483, "step": 2570 }, { "epoch": 2.395153774464119, "loss_cot": 0.4625568091869354, "loss_nocot": 0.26818525791168213, "step": 2570 }, { "epoch": 2.396085740913327, "grad_norm": 0.620985062091514, "learning_rate": 4.473593372454264e-06, "loss": 0.7208, "step": 2571 }, { "epoch": 2.396085740913327, "loss_cot": 0.47376391291618347, "loss_nocot": 0.3217836022377014, "step": 2571 }, { "epoch": 2.3970177073625347, "grad_norm": 0.676488987773477, "learning_rate": 4.466689678978254e-06, "loss": 0.8073, "step": 2572 }, { "epoch": 2.3970177073625347, "loss_cot": 0.5327552556991577, "loss_nocot": 0.24415045976638794, "step": 2572 }, { "epoch": 2.397949673811743, "grad_norm": 0.6482471194805791, "learning_rate": 4.459785985502244e-06, "loss": 0.7686, "step": 2573 }, { "epoch": 2.397949673811743, "loss_cot": 0.45582252740859985, "loss_nocot": 0.20917774736881256, "step": 2573 }, { "epoch": 2.3988816402609507, "grad_norm": 0.6906487491593246, "learning_rate": 4.452882292026234e-06, "loss": 0.7935, "step": 2574 }, { "epoch": 2.3988816402609507, "loss_cot": 0.49675634503364563, "loss_nocot": 0.3409545421600342, "step": 2574 }, { "epoch": 2.3998136067101585, "grad_norm": 0.6341559581904557, "learning_rate": 4.445978598550225e-06, "loss": 0.7214, "step": 2575 }, { "epoch": 2.3998136067101585, "loss_cot": 0.5761955976486206, "loss_nocot": 0.26413264870643616, "step": 2575 }, { "epoch": 2.4007455731593663, "grad_norm": 0.6775541317356246, "learning_rate": 4.439074905074215e-06, "loss": 0.787, "step": 2576 }, { "epoch": 2.4007455731593663, "loss_cot": 0.49775242805480957, "loss_nocot": 0.31061309576034546, "step": 2576 }, { "epoch": 2.401677539608574, "grad_norm": 0.6291697071478085, "learning_rate": 4.4321712115982055e-06, "loss": 0.7571, "step": 2577 }, { "epoch": 2.401677539608574, "loss_cot": 0.4997842311859131, "loss_nocot": 0.28178781270980835, "step": 2577 }, { "epoch": 2.402609506057782, "grad_norm": 0.6423698744133306, "learning_rate": 4.4252675181221954e-06, "loss": 0.7624, "step": 2578 }, { "epoch": 2.402609506057782, "loss_cot": 0.5006161332130432, "loss_nocot": 0.1921703815460205, "step": 2578 }, { "epoch": 2.4035414725069897, "grad_norm": 0.6381887693226449, "learning_rate": 4.418363824646186e-06, "loss": 0.7528, "step": 2579 }, { "epoch": 2.4035414725069897, "loss_cot": 0.4675927758216858, "loss_nocot": 0.22390805184841156, "step": 2579 }, { "epoch": 2.4044734389561975, "grad_norm": 0.7163546317649989, "learning_rate": 4.411460131170177e-06, "loss": 0.7129, "step": 2580 }, { "epoch": 2.4044734389561975, "loss_cot": 0.5587093830108643, "loss_nocot": 0.2798836827278137, "step": 2580 }, { "epoch": 2.4054054054054053, "grad_norm": 0.6526327765319608, "learning_rate": 4.404556437694167e-06, "loss": 0.7653, "step": 2581 }, { "epoch": 2.4054054054054053, "loss_cot": 0.46154528856277466, "loss_nocot": 0.38103699684143066, "step": 2581 }, { "epoch": 2.406337371854613, "grad_norm": 0.7375406550475415, "learning_rate": 4.3976527442181575e-06, "loss": 0.8118, "step": 2582 }, { "epoch": 2.406337371854613, "loss_cot": 0.5272138714790344, "loss_nocot": 0.3309156894683838, "step": 2582 }, { "epoch": 2.407269338303821, "grad_norm": 0.6586140383947547, "learning_rate": 4.390749050742147e-06, "loss": 0.7995, "step": 2583 }, { "epoch": 2.407269338303821, "loss_cot": 0.505328357219696, "loss_nocot": 0.551256537437439, "step": 2583 }, { "epoch": 2.408201304753029, "grad_norm": 0.7281715483578656, "learning_rate": 4.383845357266137e-06, "loss": 0.9277, "step": 2584 }, { "epoch": 2.408201304753029, "loss_cot": 0.5272700190544128, "loss_nocot": 0.28408825397491455, "step": 2584 }, { "epoch": 2.409133271202237, "grad_norm": 0.6700289763393453, "learning_rate": 4.376941663790128e-06, "loss": 0.7715, "step": 2585 }, { "epoch": 2.409133271202237, "loss_cot": 0.5242589712142944, "loss_nocot": 0.3638646602630615, "step": 2585 }, { "epoch": 2.4100652376514446, "grad_norm": 0.6768969218795867, "learning_rate": 4.370037970314118e-06, "loss": 0.7716, "step": 2586 }, { "epoch": 2.4100652376514446, "loss_cot": 0.4261000454425812, "loss_nocot": 0.3547039031982422, "step": 2586 }, { "epoch": 2.4109972041006524, "grad_norm": 0.6912543538449328, "learning_rate": 4.363134276838109e-06, "loss": 0.8235, "step": 2587 }, { "epoch": 2.4109972041006524, "loss_cot": 0.5018534660339355, "loss_nocot": 0.2697276473045349, "step": 2587 }, { "epoch": 2.4119291705498602, "grad_norm": 0.6543542020828502, "learning_rate": 4.3562305833620985e-06, "loss": 0.7287, "step": 2588 }, { "epoch": 2.4119291705498602, "loss_cot": 0.5008049011230469, "loss_nocot": 0.25688642263412476, "step": 2588 }, { "epoch": 2.412861136999068, "grad_norm": 0.6687394275319086, "learning_rate": 4.349326889886089e-06, "loss": 0.7537, "step": 2589 }, { "epoch": 2.412861136999068, "loss_cot": 0.49741238355636597, "loss_nocot": 0.23263394832611084, "step": 2589 }, { "epoch": 2.413793103448276, "grad_norm": 0.6943006347041688, "learning_rate": 4.34242319641008e-06, "loss": 0.7296, "step": 2590 }, { "epoch": 2.413793103448276, "loss_cot": 0.44246426224708557, "loss_nocot": 0.2559131979942322, "step": 2590 }, { "epoch": 2.4147250698974836, "grad_norm": 0.5932140630483144, "learning_rate": 4.33551950293407e-06, "loss": 0.6772, "step": 2591 }, { "epoch": 2.4147250698974836, "loss_cot": 0.43398088216781616, "loss_nocot": 0.195600688457489, "step": 2591 }, { "epoch": 2.4156570363466914, "grad_norm": 0.6816813133318466, "learning_rate": 4.328615809458061e-06, "loss": 0.7274, "step": 2592 }, { "epoch": 2.4156570363466914, "loss_cot": 0.5377163887023926, "loss_nocot": 0.25763529539108276, "step": 2592 }, { "epoch": 2.416589002795899, "grad_norm": 0.6561247846519151, "learning_rate": 4.3217121159820505e-06, "loss": 0.7826, "step": 2593 }, { "epoch": 2.416589002795899, "loss_cot": 0.5223321914672852, "loss_nocot": 0.2483445107936859, "step": 2593 }, { "epoch": 2.417520969245107, "grad_norm": 0.6630867320450318, "learning_rate": 4.314808422506041e-06, "loss": 0.7942, "step": 2594 }, { "epoch": 2.417520969245107, "loss_cot": 0.4469813108444214, "loss_nocot": 0.3743695914745331, "step": 2594 }, { "epoch": 2.418452935694315, "grad_norm": 0.6512091605365121, "learning_rate": 4.307904729030031e-06, "loss": 0.7866, "step": 2595 }, { "epoch": 2.418452935694315, "loss_cot": 0.542412519454956, "loss_nocot": 0.2027091085910797, "step": 2595 }, { "epoch": 2.419384902143523, "grad_norm": 0.5916914605749775, "learning_rate": 4.301001035554022e-06, "loss": 0.7626, "step": 2596 }, { "epoch": 2.419384902143523, "loss_cot": 0.5723832845687866, "loss_nocot": 0.28781503438949585, "step": 2596 }, { "epoch": 2.4203168685927308, "grad_norm": 0.6882340676573012, "learning_rate": 4.294097342078012e-06, "loss": 0.8257, "step": 2597 }, { "epoch": 2.4203168685927308, "loss_cot": 0.5147745609283447, "loss_nocot": 0.2625125050544739, "step": 2597 }, { "epoch": 2.4212488350419386, "grad_norm": 0.6691141644500704, "learning_rate": 4.2871936486020025e-06, "loss": 0.778, "step": 2598 }, { "epoch": 2.4212488350419386, "loss_cot": 0.4419387876987457, "loss_nocot": 0.2299765944480896, "step": 2598 }, { "epoch": 2.4221808014911463, "grad_norm": 0.7534277104092312, "learning_rate": 4.280289955125993e-06, "loss": 0.7716, "step": 2599 }, { "epoch": 2.4221808014911463, "loss_cot": 0.4700906574726105, "loss_nocot": 0.2237319052219391, "step": 2599 }, { "epoch": 2.423112767940354, "grad_norm": 0.658022640931991, "learning_rate": 4.273386261649983e-06, "loss": 0.7421, "step": 2600 }, { "epoch": 2.423112767940354, "loss_cot": 0.49817872047424316, "loss_nocot": 0.31656941771507263, "step": 2600 }, { "epoch": 2.424044734389562, "grad_norm": 0.628069514471158, "learning_rate": 4.266482568173974e-06, "loss": 0.7809, "step": 2601 }, { "epoch": 2.424044734389562, "loss_cot": 0.49142152070999146, "loss_nocot": 0.2092803418636322, "step": 2601 }, { "epoch": 2.4249767008387697, "grad_norm": 0.6670739718784544, "learning_rate": 4.259578874697964e-06, "loss": 0.7627, "step": 2602 }, { "epoch": 2.4249767008387697, "loss_cot": 0.5128223299980164, "loss_nocot": 0.3417554199695587, "step": 2602 }, { "epoch": 2.4259086672879775, "grad_norm": 6.157209395555805, "learning_rate": 4.2526751812219544e-06, "loss": 0.8275, "step": 2603 }, { "epoch": 2.4259086672879775, "loss_cot": 0.5108035802841187, "loss_nocot": 0.334908664226532, "step": 2603 }, { "epoch": 2.4268406337371853, "grad_norm": 0.7375346565477455, "learning_rate": 4.245771487745944e-06, "loss": 0.7604, "step": 2604 }, { "epoch": 2.4268406337371853, "loss_cot": 0.5080376863479614, "loss_nocot": 0.17791587114334106, "step": 2604 }, { "epoch": 2.427772600186393, "grad_norm": 0.7454713962684766, "learning_rate": 4.238867794269935e-06, "loss": 0.754, "step": 2605 }, { "epoch": 2.427772600186393, "loss_cot": 0.550358772277832, "loss_nocot": 0.2519378662109375, "step": 2605 }, { "epoch": 2.4287045666356013, "grad_norm": 0.6466696592536111, "learning_rate": 4.231964100793925e-06, "loss": 0.7665, "step": 2606 }, { "epoch": 2.4287045666356013, "loss_cot": 0.47464174032211304, "loss_nocot": 0.28427356481552124, "step": 2606 }, { "epoch": 2.429636533084809, "grad_norm": 0.6084938253211908, "learning_rate": 4.225060407317915e-06, "loss": 0.7157, "step": 2607 }, { "epoch": 2.429636533084809, "loss_cot": 0.5078034400939941, "loss_nocot": 0.27464911341667175, "step": 2607 }, { "epoch": 2.430568499534017, "grad_norm": 0.6607242285012388, "learning_rate": 4.2181567138419055e-06, "loss": 0.7459, "step": 2608 }, { "epoch": 2.430568499534017, "loss_cot": 0.45050472021102905, "loss_nocot": 0.20218321681022644, "step": 2608 }, { "epoch": 2.4315004659832247, "grad_norm": 0.6172077575726034, "learning_rate": 4.211253020365896e-06, "loss": 0.7272, "step": 2609 }, { "epoch": 2.4315004659832247, "loss_cot": 0.48077231645584106, "loss_nocot": 0.2783570885658264, "step": 2609 }, { "epoch": 2.4324324324324325, "grad_norm": 0.6783097662727295, "learning_rate": 4.204349326889887e-06, "loss": 0.7698, "step": 2610 }, { "epoch": 2.4324324324324325, "loss_cot": 0.4838443696498871, "loss_nocot": 0.28450146317481995, "step": 2610 }, { "epoch": 2.4333643988816402, "grad_norm": 0.6654580188720681, "learning_rate": 4.197445633413877e-06, "loss": 0.7764, "step": 2611 }, { "epoch": 2.4333643988816402, "loss_cot": 0.5194739103317261, "loss_nocot": 0.29294660687446594, "step": 2611 }, { "epoch": 2.434296365330848, "grad_norm": 0.6185797631461762, "learning_rate": 4.190541939937867e-06, "loss": 0.7453, "step": 2612 }, { "epoch": 2.434296365330848, "loss_cot": 0.4291706681251526, "loss_nocot": 0.1943855732679367, "step": 2612 }, { "epoch": 2.435228331780056, "grad_norm": 0.6236689857806775, "learning_rate": 4.1836382464618575e-06, "loss": 0.6866, "step": 2613 }, { "epoch": 2.435228331780056, "loss_cot": 0.5058360695838928, "loss_nocot": 0.27632367610931396, "step": 2613 }, { "epoch": 2.4361602982292636, "grad_norm": 0.6868183797762808, "learning_rate": 4.176734552985847e-06, "loss": 0.748, "step": 2614 }, { "epoch": 2.4361602982292636, "loss_cot": 0.5301545858383179, "loss_nocot": 0.28046149015426636, "step": 2614 }, { "epoch": 2.4370922646784714, "grad_norm": 0.6514827999299536, "learning_rate": 4.169830859509838e-06, "loss": 0.7296, "step": 2615 }, { "epoch": 2.4370922646784714, "loss_cot": 0.5097047090530396, "loss_nocot": 0.2900773882865906, "step": 2615 }, { "epoch": 2.438024231127679, "grad_norm": 0.6923175771292583, "learning_rate": 4.162927166033828e-06, "loss": 0.7399, "step": 2616 }, { "epoch": 2.438024231127679, "loss_cot": 0.43552935123443604, "loss_nocot": 0.23033197224140167, "step": 2616 }, { "epoch": 2.4389561975768874, "grad_norm": 0.6261545715687639, "learning_rate": 4.156023472557819e-06, "loss": 0.7406, "step": 2617 }, { "epoch": 2.4389561975768874, "loss_cot": 0.4832262396812439, "loss_nocot": 0.24999456107616425, "step": 2617 }, { "epoch": 2.439888164026095, "grad_norm": 0.6367495669692442, "learning_rate": 4.149119779081809e-06, "loss": 0.7404, "step": 2618 }, { "epoch": 2.439888164026095, "loss_cot": 0.5043724775314331, "loss_nocot": 0.3478015065193176, "step": 2618 }, { "epoch": 2.440820130475303, "grad_norm": 0.6806086161888181, "learning_rate": 4.142216085605799e-06, "loss": 0.7657, "step": 2619 }, { "epoch": 2.440820130475303, "loss_cot": 0.5099269151687622, "loss_nocot": 0.22105112671852112, "step": 2619 }, { "epoch": 2.441752096924511, "grad_norm": 0.6127959594705615, "learning_rate": 4.13531239212979e-06, "loss": 0.7321, "step": 2620 }, { "epoch": 2.441752096924511, "loss_cot": 0.5138081312179565, "loss_nocot": 0.24632126092910767, "step": 2620 }, { "epoch": 2.4426840633737186, "grad_norm": 0.6110701191272087, "learning_rate": 4.12840869865378e-06, "loss": 0.7355, "step": 2621 }, { "epoch": 2.4426840633737186, "loss_cot": 0.47112584114074707, "loss_nocot": 0.27906864881515503, "step": 2621 }, { "epoch": 2.4436160298229264, "grad_norm": 0.6840485339651814, "learning_rate": 4.121505005177771e-06, "loss": 0.7673, "step": 2622 }, { "epoch": 2.4436160298229264, "loss_cot": 0.45939210057258606, "loss_nocot": 0.274067759513855, "step": 2622 }, { "epoch": 2.444547996272134, "grad_norm": 0.6236844948015753, "learning_rate": 4.114601311701761e-06, "loss": 0.7229, "step": 2623 }, { "epoch": 2.444547996272134, "loss_cot": 0.5255759358406067, "loss_nocot": 0.32057347893714905, "step": 2623 }, { "epoch": 2.445479962721342, "grad_norm": 0.6152393191133916, "learning_rate": 4.107697618225751e-06, "loss": 0.7238, "step": 2624 }, { "epoch": 2.445479962721342, "loss_cot": 0.47468215227127075, "loss_nocot": 0.27504563331604004, "step": 2624 }, { "epoch": 2.4464119291705497, "grad_norm": 0.6873632253138392, "learning_rate": 4.100793924749741e-06, "loss": 0.7768, "step": 2625 }, { "epoch": 2.4464119291705497, "loss_cot": 0.4645252227783203, "loss_nocot": 0.20365062355995178, "step": 2625 }, { "epoch": 2.4473438956197575, "grad_norm": 0.5847309132501726, "learning_rate": 4.093890231273732e-06, "loss": 0.6966, "step": 2626 }, { "epoch": 2.4473438956197575, "loss_cot": 0.49679386615753174, "loss_nocot": 0.24220684170722961, "step": 2626 }, { "epoch": 2.4482758620689653, "grad_norm": 0.6645427682311372, "learning_rate": 4.086986537797722e-06, "loss": 0.7694, "step": 2627 }, { "epoch": 2.4482758620689653, "loss_cot": 0.5368307828903198, "loss_nocot": 0.21301400661468506, "step": 2627 }, { "epoch": 2.4492078285181735, "grad_norm": 0.624696366043227, "learning_rate": 4.0800828443217126e-06, "loss": 0.7336, "step": 2628 }, { "epoch": 2.4492078285181735, "loss_cot": 0.4392428696155548, "loss_nocot": 0.20452672243118286, "step": 2628 }, { "epoch": 2.4501397949673813, "grad_norm": 0.5865261705304335, "learning_rate": 4.073179150845703e-06, "loss": 0.728, "step": 2629 }, { "epoch": 2.4501397949673813, "loss_cot": 0.4927329123020172, "loss_nocot": 0.2391982227563858, "step": 2629 }, { "epoch": 2.451071761416589, "grad_norm": 0.6215646648066837, "learning_rate": 4.066275457369693e-06, "loss": 0.6984, "step": 2630 }, { "epoch": 2.451071761416589, "loss_cot": 0.5338799357414246, "loss_nocot": 0.26464080810546875, "step": 2630 }, { "epoch": 2.452003727865797, "grad_norm": 0.6818473870218026, "learning_rate": 4.059371763893684e-06, "loss": 0.7663, "step": 2631 }, { "epoch": 2.452003727865797, "loss_cot": 0.460641473531723, "loss_nocot": 0.2525627315044403, "step": 2631 }, { "epoch": 2.4529356943150047, "grad_norm": 0.6650881265084653, "learning_rate": 4.052468070417674e-06, "loss": 0.7605, "step": 2632 }, { "epoch": 2.4529356943150047, "loss_cot": 0.5313829183578491, "loss_nocot": 0.25374457240104675, "step": 2632 }, { "epoch": 2.4538676607642125, "grad_norm": 0.6335304474488851, "learning_rate": 4.0455643769416645e-06, "loss": 0.7537, "step": 2633 }, { "epoch": 2.4538676607642125, "loss_cot": 0.5243933200836182, "loss_nocot": 0.20091909170150757, "step": 2633 }, { "epoch": 2.4547996272134203, "grad_norm": 0.6096193696489735, "learning_rate": 4.0386606834656544e-06, "loss": 0.6775, "step": 2634 }, { "epoch": 2.4547996272134203, "loss_cot": 0.5125077962875366, "loss_nocot": 0.26589763164520264, "step": 2634 }, { "epoch": 2.455731593662628, "grad_norm": 0.6486604764112807, "learning_rate": 4.031756989989644e-06, "loss": 0.7059, "step": 2635 }, { "epoch": 2.455731593662628, "loss_cot": 0.42811188101768494, "loss_nocot": 0.26861923933029175, "step": 2635 }, { "epoch": 2.456663560111836, "grad_norm": 0.6171547202201936, "learning_rate": 4.024853296513635e-06, "loss": 0.692, "step": 2636 }, { "epoch": 2.456663560111836, "loss_cot": 0.4805944263935089, "loss_nocot": 0.2634851932525635, "step": 2636 }, { "epoch": 2.4575955265610436, "grad_norm": 0.6313476645956656, "learning_rate": 4.017949603037625e-06, "loss": 0.7646, "step": 2637 }, { "epoch": 2.4575955265610436, "loss_cot": 0.5607490539550781, "loss_nocot": 0.30373600125312805, "step": 2637 }, { "epoch": 2.4585274930102514, "grad_norm": 0.6260364281829285, "learning_rate": 4.011045909561616e-06, "loss": 0.7432, "step": 2638 }, { "epoch": 2.4585274930102514, "loss_cot": 0.5274739265441895, "loss_nocot": 0.2440289855003357, "step": 2638 }, { "epoch": 2.4594594594594597, "grad_norm": 0.6096367640181859, "learning_rate": 4.004142216085606e-06, "loss": 0.7334, "step": 2639 }, { "epoch": 2.4594594594594597, "loss_cot": 0.42874735593795776, "loss_nocot": 0.31978529691696167, "step": 2639 }, { "epoch": 2.4603914259086674, "grad_norm": 0.6632449222812298, "learning_rate": 3.997238522609596e-06, "loss": 0.7395, "step": 2640 }, { "epoch": 2.4603914259086674, "loss_cot": 0.48537689447402954, "loss_nocot": 0.26538175344467163, "step": 2640 }, { "epoch": 2.4613233923578752, "grad_norm": 0.6191271882694054, "learning_rate": 3.990334829133587e-06, "loss": 0.7606, "step": 2641 }, { "epoch": 2.4613233923578752, "loss_cot": 0.4800781011581421, "loss_nocot": 0.2616208493709564, "step": 2641 }, { "epoch": 2.462255358807083, "grad_norm": 0.6189142401922418, "learning_rate": 3.983431135657577e-06, "loss": 0.7309, "step": 2642 }, { "epoch": 2.462255358807083, "loss_cot": 0.4587590992450714, "loss_nocot": 0.21531689167022705, "step": 2642 }, { "epoch": 2.463187325256291, "grad_norm": 0.6630045079865058, "learning_rate": 3.976527442181568e-06, "loss": 0.7317, "step": 2643 }, { "epoch": 2.463187325256291, "loss_cot": 0.5733495354652405, "loss_nocot": 0.24020281434059143, "step": 2643 }, { "epoch": 2.4641192917054986, "grad_norm": 0.6309805538984279, "learning_rate": 3.9696237487055575e-06, "loss": 0.7326, "step": 2644 }, { "epoch": 2.4641192917054986, "loss_cot": 0.407260000705719, "loss_nocot": 0.2906055450439453, "step": 2644 }, { "epoch": 2.4650512581547064, "grad_norm": 0.6294974987894534, "learning_rate": 3.962720055229548e-06, "loss": 0.7095, "step": 2645 }, { "epoch": 2.4650512581547064, "loss_cot": 0.5067558288574219, "loss_nocot": 0.3044518828392029, "step": 2645 }, { "epoch": 2.465983224603914, "grad_norm": 0.7501473374928646, "learning_rate": 3.955816361753538e-06, "loss": 0.8108, "step": 2646 }, { "epoch": 2.465983224603914, "loss_cot": 0.5021412968635559, "loss_nocot": 0.2745615243911743, "step": 2646 }, { "epoch": 2.466915191053122, "grad_norm": 0.7004152991208532, "learning_rate": 3.948912668277529e-06, "loss": 0.7845, "step": 2647 }, { "epoch": 2.466915191053122, "loss_cot": 0.5282354354858398, "loss_nocot": 0.24521072208881378, "step": 2647 }, { "epoch": 2.4678471575023297, "grad_norm": 0.6747182726142938, "learning_rate": 3.942008974801519e-06, "loss": 0.7479, "step": 2648 }, { "epoch": 2.4678471575023297, "loss_cot": 0.4831695854663849, "loss_nocot": 0.297707200050354, "step": 2648 }, { "epoch": 2.4687791239515375, "grad_norm": 0.7035649001855384, "learning_rate": 3.9351052813255095e-06, "loss": 0.7339, "step": 2649 }, { "epoch": 2.4687791239515375, "loss_cot": 0.5503997802734375, "loss_nocot": 0.26537176966667175, "step": 2649 }, { "epoch": 2.4697110904007458, "grad_norm": 0.6742749992640931, "learning_rate": 3.9282015878495e-06, "loss": 0.7551, "step": 2650 }, { "epoch": 2.4697110904007458, "loss_cot": 0.45644664764404297, "loss_nocot": 0.2422647625207901, "step": 2650 }, { "epoch": 2.4706430568499536, "grad_norm": 0.6655105489670188, "learning_rate": 3.92129789437349e-06, "loss": 0.7242, "step": 2651 }, { "epoch": 2.4706430568499536, "loss_cot": 0.5249446630477905, "loss_nocot": 0.16874082386493683, "step": 2651 }, { "epoch": 2.4715750232991613, "grad_norm": 0.6128785755729291, "learning_rate": 3.914394200897481e-06, "loss": 0.7243, "step": 2652 }, { "epoch": 2.4715750232991613, "loss_cot": 0.5120946168899536, "loss_nocot": 0.22810843586921692, "step": 2652 }, { "epoch": 2.472506989748369, "grad_norm": 0.6868219222611568, "learning_rate": 3.907490507421471e-06, "loss": 0.7296, "step": 2653 }, { "epoch": 2.472506989748369, "loss_cot": 0.5047143697738647, "loss_nocot": 0.2520924210548401, "step": 2653 }, { "epoch": 2.473438956197577, "grad_norm": 0.6843811578210528, "learning_rate": 3.9005868139454615e-06, "loss": 0.7671, "step": 2654 }, { "epoch": 2.473438956197577, "loss_cot": 0.46083515882492065, "loss_nocot": 0.2180033028125763, "step": 2654 }, { "epoch": 2.4743709226467847, "grad_norm": 0.6417950388701178, "learning_rate": 3.893683120469451e-06, "loss": 0.7502, "step": 2655 }, { "epoch": 2.4743709226467847, "loss_cot": 0.4982066750526428, "loss_nocot": 0.4238491654396057, "step": 2655 }, { "epoch": 2.4753028890959925, "grad_norm": 0.707268638028352, "learning_rate": 3.886779426993442e-06, "loss": 0.8459, "step": 2656 }, { "epoch": 2.4753028890959925, "loss_cot": 0.44600892066955566, "loss_nocot": 0.3156433403491974, "step": 2656 }, { "epoch": 2.4762348555452003, "grad_norm": 0.6762279113253854, "learning_rate": 3.879875733517432e-06, "loss": 0.7061, "step": 2657 }, { "epoch": 2.4762348555452003, "loss_cot": 0.4719635844230652, "loss_nocot": 0.3047654926776886, "step": 2657 }, { "epoch": 2.477166821994408, "grad_norm": 0.6385654358711255, "learning_rate": 3.872972040041422e-06, "loss": 0.7277, "step": 2658 }, { "epoch": 2.477166821994408, "loss_cot": 0.4858390986919403, "loss_nocot": 0.22073836624622345, "step": 2658 }, { "epoch": 2.478098788443616, "grad_norm": 0.649720501311499, "learning_rate": 3.866068346565413e-06, "loss": 0.7566, "step": 2659 }, { "epoch": 2.478098788443616, "loss_cot": 0.5162224769592285, "loss_nocot": 0.2514432668685913, "step": 2659 }, { "epoch": 2.4790307548928237, "grad_norm": 0.668176734380992, "learning_rate": 3.859164653089403e-06, "loss": 0.7522, "step": 2660 }, { "epoch": 2.4790307548928237, "loss_cot": 0.5417575836181641, "loss_nocot": 0.3976714611053467, "step": 2660 }, { "epoch": 2.479962721342032, "grad_norm": 0.6690425174439035, "learning_rate": 3.852260959613394e-06, "loss": 0.7872, "step": 2661 }, { "epoch": 2.479962721342032, "loss_cot": 0.4476328194141388, "loss_nocot": 0.23938867449760437, "step": 2661 }, { "epoch": 2.4808946877912397, "grad_norm": 0.6809099279308956, "learning_rate": 3.845357266137384e-06, "loss": 0.7885, "step": 2662 }, { "epoch": 2.4808946877912397, "loss_cot": 0.5280452370643616, "loss_nocot": 0.2259465754032135, "step": 2662 }, { "epoch": 2.4818266542404475, "grad_norm": 0.6564213766021421, "learning_rate": 3.838453572661374e-06, "loss": 0.7758, "step": 2663 }, { "epoch": 2.4818266542404475, "loss_cot": 0.46106231212615967, "loss_nocot": 0.25460195541381836, "step": 2663 }, { "epoch": 2.4827586206896552, "grad_norm": 0.7225170087101209, "learning_rate": 3.8315498791853645e-06, "loss": 0.7348, "step": 2664 }, { "epoch": 2.4827586206896552, "loss_cot": 0.4701656103134155, "loss_nocot": 0.2684711813926697, "step": 2664 }, { "epoch": 2.483690587138863, "grad_norm": 0.6527990002637706, "learning_rate": 3.8246461857093544e-06, "loss": 0.7286, "step": 2665 }, { "epoch": 2.483690587138863, "loss_cot": 0.4907909333705902, "loss_nocot": 0.269029438495636, "step": 2665 }, { "epoch": 2.484622553588071, "grad_norm": 0.7088542633864995, "learning_rate": 3.817742492233345e-06, "loss": 0.7681, "step": 2666 }, { "epoch": 2.484622553588071, "loss_cot": 0.4972419738769531, "loss_nocot": 0.26404035091400146, "step": 2666 }, { "epoch": 2.4855545200372786, "grad_norm": 0.6403781096614529, "learning_rate": 3.8108387987573355e-06, "loss": 0.7816, "step": 2667 }, { "epoch": 2.4855545200372786, "loss_cot": 0.4460512399673462, "loss_nocot": 0.22431951761245728, "step": 2667 }, { "epoch": 2.4864864864864864, "grad_norm": 0.6785086630051047, "learning_rate": 3.8039351052813258e-06, "loss": 0.7389, "step": 2668 }, { "epoch": 2.4864864864864864, "loss_cot": 0.433529794216156, "loss_nocot": 0.21646666526794434, "step": 2668 }, { "epoch": 2.487418452935694, "grad_norm": 0.727384541944539, "learning_rate": 3.7970314118053165e-06, "loss": 0.74, "step": 2669 }, { "epoch": 2.487418452935694, "loss_cot": 0.49295586347579956, "loss_nocot": 0.23869828879833221, "step": 2669 }, { "epoch": 2.488350419384902, "grad_norm": 0.6538801346617302, "learning_rate": 3.790127718329307e-06, "loss": 0.7965, "step": 2670 }, { "epoch": 2.488350419384902, "loss_cot": 0.565372109413147, "loss_nocot": 0.2651785612106323, "step": 2670 }, { "epoch": 2.4892823858341098, "grad_norm": 0.6850937661165375, "learning_rate": 3.783224024853297e-06, "loss": 0.7863, "step": 2671 }, { "epoch": 2.4892823858341098, "loss_cot": 0.5083761215209961, "loss_nocot": 0.27597618103027344, "step": 2671 }, { "epoch": 2.490214352283318, "grad_norm": 0.6128596112661012, "learning_rate": 3.7763203313772874e-06, "loss": 0.7449, "step": 2672 }, { "epoch": 2.490214352283318, "loss_cot": 0.5687344074249268, "loss_nocot": 0.31755372881889343, "step": 2672 }, { "epoch": 2.491146318732526, "grad_norm": 0.6695011239024514, "learning_rate": 3.7694166379012777e-06, "loss": 0.8542, "step": 2673 }, { "epoch": 2.491146318732526, "loss_cot": 0.43505674600601196, "loss_nocot": 0.1846851110458374, "step": 2673 }, { "epoch": 2.4920782851817336, "grad_norm": 0.6083639587241344, "learning_rate": 3.7625129444252676e-06, "loss": 0.7145, "step": 2674 }, { "epoch": 2.4920782851817336, "loss_cot": 0.527474045753479, "loss_nocot": 0.306851863861084, "step": 2674 }, { "epoch": 2.4930102516309414, "grad_norm": 0.7035337234892541, "learning_rate": 3.755609250949258e-06, "loss": 0.7631, "step": 2675 }, { "epoch": 2.4930102516309414, "loss_cot": 0.45725953578948975, "loss_nocot": 0.29695597290992737, "step": 2675 }, { "epoch": 2.493942218080149, "grad_norm": 0.6670781838237143, "learning_rate": 3.7487055574732483e-06, "loss": 0.7775, "step": 2676 }, { "epoch": 2.493942218080149, "loss_cot": 0.5442136526107788, "loss_nocot": 0.24293246865272522, "step": 2676 }, { "epoch": 2.494874184529357, "grad_norm": 0.6386458787085513, "learning_rate": 3.7418018639972386e-06, "loss": 0.7487, "step": 2677 }, { "epoch": 2.494874184529357, "loss_cot": 0.4519209861755371, "loss_nocot": 0.24043163657188416, "step": 2677 }, { "epoch": 2.4958061509785647, "grad_norm": 0.6097253372940418, "learning_rate": 3.734898170521229e-06, "loss": 0.7237, "step": 2678 }, { "epoch": 2.4958061509785647, "loss_cot": 0.4742729365825653, "loss_nocot": 0.30232059955596924, "step": 2678 }, { "epoch": 2.4967381174277725, "grad_norm": 0.6682032580945934, "learning_rate": 3.7279944770452196e-06, "loss": 0.7811, "step": 2679 }, { "epoch": 2.4967381174277725, "loss_cot": 0.5671504735946655, "loss_nocot": 0.3296876549720764, "step": 2679 }, { "epoch": 2.4976700838769803, "grad_norm": 0.7644272625367295, "learning_rate": 3.72109078356921e-06, "loss": 0.8804, "step": 2680 }, { "epoch": 2.4976700838769803, "loss_cot": 0.4863128364086151, "loss_nocot": 0.2727673649787903, "step": 2680 }, { "epoch": 2.498602050326188, "grad_norm": 0.691346265577003, "learning_rate": 3.7141870900932002e-06, "loss": 0.7946, "step": 2681 }, { "epoch": 2.498602050326188, "loss_cot": 0.48001283407211304, "loss_nocot": 0.20627740025520325, "step": 2681 }, { "epoch": 2.499534016775396, "grad_norm": 0.633912970051211, "learning_rate": 3.7072833966171905e-06, "loss": 0.7314, "step": 2682 }, { "epoch": 2.499534016775396, "loss_cot": 0.5701223611831665, "loss_nocot": 0.21648705005645752, "step": 2682 }, { "epoch": 2.500465983224604, "grad_norm": 0.6113415006056758, "learning_rate": 3.700379703141181e-06, "loss": 0.704, "step": 2683 }, { "epoch": 2.500465983224604, "loss_cot": 0.4455885589122772, "loss_nocot": 0.25484979152679443, "step": 2683 }, { "epoch": 2.501397949673812, "grad_norm": 0.6205284719096291, "learning_rate": 3.693476009665171e-06, "loss": 0.7313, "step": 2684 }, { "epoch": 2.501397949673812, "loss_cot": 0.5334730744361877, "loss_nocot": 0.22479897737503052, "step": 2684 }, { "epoch": 2.5023299161230197, "grad_norm": 0.6289812020878395, "learning_rate": 3.6865723161891615e-06, "loss": 0.7667, "step": 2685 }, { "epoch": 2.5023299161230197, "loss_cot": 0.5335875153541565, "loss_nocot": 0.29129016399383545, "step": 2685 }, { "epoch": 2.5032618825722275, "grad_norm": 0.691301047094526, "learning_rate": 3.6796686227131518e-06, "loss": 0.7882, "step": 2686 }, { "epoch": 2.5032618825722275, "loss_cot": 0.43482542037963867, "loss_nocot": 0.3322179913520813, "step": 2686 }, { "epoch": 2.5041938490214353, "grad_norm": 0.688423873965191, "learning_rate": 3.672764929237142e-06, "loss": 0.7951, "step": 2687 }, { "epoch": 2.5041938490214353, "loss_cot": 0.4830750524997711, "loss_nocot": 0.25176459550857544, "step": 2687 }, { "epoch": 2.505125815470643, "grad_norm": 0.6557914384958422, "learning_rate": 3.6658612357611324e-06, "loss": 0.7723, "step": 2688 }, { "epoch": 2.505125815470643, "loss_cot": 0.5007115602493286, "loss_nocot": 0.2704033851623535, "step": 2688 }, { "epoch": 2.506057781919851, "grad_norm": 0.6076403977368919, "learning_rate": 3.6589575422851227e-06, "loss": 0.7655, "step": 2689 }, { "epoch": 2.506057781919851, "loss_cot": 0.4212378263473511, "loss_nocot": 0.2658505439758301, "step": 2689 }, { "epoch": 2.5069897483690586, "grad_norm": 0.6411388213042288, "learning_rate": 3.6520538488091134e-06, "loss": 0.7667, "step": 2690 }, { "epoch": 2.5069897483690586, "loss_cot": 0.5002489686012268, "loss_nocot": 0.2049095630645752, "step": 2690 }, { "epoch": 2.5079217148182664, "grad_norm": 0.6085834704346028, "learning_rate": 3.6451501553331037e-06, "loss": 0.733, "step": 2691 }, { "epoch": 2.5079217148182664, "loss_cot": 0.5363807082176208, "loss_nocot": 0.2665998935699463, "step": 2691 }, { "epoch": 2.508853681267474, "grad_norm": 0.6083501425326895, "learning_rate": 3.638246461857094e-06, "loss": 0.7053, "step": 2692 }, { "epoch": 2.508853681267474, "loss_cot": 0.45269107818603516, "loss_nocot": 0.22424983978271484, "step": 2692 }, { "epoch": 2.509785647716682, "grad_norm": 0.6236901031740063, "learning_rate": 3.6313427683810844e-06, "loss": 0.7016, "step": 2693 }, { "epoch": 2.509785647716682, "loss_cot": 0.5168213844299316, "loss_nocot": 0.22500921785831451, "step": 2693 }, { "epoch": 2.5107176141658902, "grad_norm": 0.6064795102038328, "learning_rate": 3.6244390749050747e-06, "loss": 0.7246, "step": 2694 }, { "epoch": 2.5107176141658902, "loss_cot": 0.4796077609062195, "loss_nocot": 0.28140023350715637, "step": 2694 }, { "epoch": 2.511649580615098, "grad_norm": 0.6390772619480823, "learning_rate": 3.617535381429065e-06, "loss": 0.7243, "step": 2695 }, { "epoch": 2.511649580615098, "loss_cot": 0.5034486651420593, "loss_nocot": 0.2619515061378479, "step": 2695 }, { "epoch": 2.512581547064306, "grad_norm": 0.6347877071752122, "learning_rate": 3.6106316879530553e-06, "loss": 0.732, "step": 2696 }, { "epoch": 2.512581547064306, "loss_cot": 0.5055257081985474, "loss_nocot": 0.19633309543132782, "step": 2696 }, { "epoch": 2.5135135135135136, "grad_norm": 0.6977549634069509, "learning_rate": 3.603727994477045e-06, "loss": 0.7815, "step": 2697 }, { "epoch": 2.5135135135135136, "loss_cot": 0.5225188732147217, "loss_nocot": 0.2232954204082489, "step": 2697 }, { "epoch": 2.5144454799627214, "grad_norm": 0.6387626700092801, "learning_rate": 3.5968243010010355e-06, "loss": 0.7696, "step": 2698 }, { "epoch": 2.5144454799627214, "loss_cot": 0.45230191946029663, "loss_nocot": 0.2964434325695038, "step": 2698 }, { "epoch": 2.515377446411929, "grad_norm": 0.6497880103725209, "learning_rate": 3.5899206075250258e-06, "loss": 0.7288, "step": 2699 }, { "epoch": 2.515377446411929, "loss_cot": 0.5029399394989014, "loss_nocot": 0.24123409390449524, "step": 2699 }, { "epoch": 2.516309412861137, "grad_norm": 0.6583847534908683, "learning_rate": 3.583016914049017e-06, "loss": 0.7295, "step": 2700 }, { "epoch": 2.516309412861137, "loss_cot": 0.4649920165538788, "loss_nocot": 0.4020751118659973, "step": 2700 }, { "epoch": 2.5172413793103448, "grad_norm": 0.6395921985789086, "learning_rate": 3.576113220573007e-06, "loss": 0.7331, "step": 2701 }, { "epoch": 2.5172413793103448, "loss_cot": 0.5285487174987793, "loss_nocot": 0.363467276096344, "step": 2701 }, { "epoch": 2.5181733457595525, "grad_norm": 0.6695432871001503, "learning_rate": 3.569209527096997e-06, "loss": 0.7897, "step": 2702 }, { "epoch": 2.5181733457595525, "loss_cot": 0.47715452313423157, "loss_nocot": 0.22084327042102814, "step": 2702 }, { "epoch": 2.5191053122087603, "grad_norm": 0.6876959616516255, "learning_rate": 3.5623058336209874e-06, "loss": 0.7147, "step": 2703 }, { "epoch": 2.5191053122087603, "loss_cot": 0.45249196887016296, "loss_nocot": 0.17254742980003357, "step": 2703 }, { "epoch": 2.520037278657968, "grad_norm": 0.6199988789007077, "learning_rate": 3.5554021401449777e-06, "loss": 0.7071, "step": 2704 }, { "epoch": 2.520037278657968, "loss_cot": 0.5118785500526428, "loss_nocot": 0.33060675859451294, "step": 2704 }, { "epoch": 2.5209692451071763, "grad_norm": 0.7026712135225468, "learning_rate": 3.548498446668968e-06, "loss": 0.8213, "step": 2705 }, { "epoch": 2.5209692451071763, "loss_cot": 0.5461418628692627, "loss_nocot": 0.22206181287765503, "step": 2705 }, { "epoch": 2.5219012115563837, "grad_norm": 0.7061242192535517, "learning_rate": 3.5415947531929584e-06, "loss": 0.7889, "step": 2706 }, { "epoch": 2.5219012115563837, "loss_cot": 0.4501420855522156, "loss_nocot": 0.2353326678276062, "step": 2706 }, { "epoch": 2.522833178005592, "grad_norm": 0.6269185965973684, "learning_rate": 3.5346910597169487e-06, "loss": 0.7405, "step": 2707 }, { "epoch": 2.522833178005592, "loss_cot": 0.48736852407455444, "loss_nocot": 0.22988104820251465, "step": 2707 }, { "epoch": 2.5237651444547997, "grad_norm": 0.7050671543062941, "learning_rate": 3.527787366240939e-06, "loss": 0.7966, "step": 2708 }, { "epoch": 2.5237651444547997, "loss_cot": 0.4997139573097229, "loss_nocot": 0.2931217849254608, "step": 2708 }, { "epoch": 2.5246971109040075, "grad_norm": 0.6305473461461512, "learning_rate": 3.5208836727649293e-06, "loss": 0.7082, "step": 2709 }, { "epoch": 2.5246971109040075, "loss_cot": 0.47533246874809265, "loss_nocot": 0.27040210366249084, "step": 2709 }, { "epoch": 2.5256290773532153, "grad_norm": 0.6081140118068546, "learning_rate": 3.51397997928892e-06, "loss": 0.7286, "step": 2710 }, { "epoch": 2.5256290773532153, "loss_cot": 0.49996456503868103, "loss_nocot": 0.2533152103424072, "step": 2710 }, { "epoch": 2.526561043802423, "grad_norm": 0.6848035414414266, "learning_rate": 3.5070762858129103e-06, "loss": 0.8065, "step": 2711 }, { "epoch": 2.526561043802423, "loss_cot": 0.45087921619415283, "loss_nocot": 0.3040992021560669, "step": 2711 }, { "epoch": 2.527493010251631, "grad_norm": 0.6521105920024881, "learning_rate": 3.5001725923369006e-06, "loss": 0.776, "step": 2712 }, { "epoch": 2.527493010251631, "loss_cot": 0.5317888855934143, "loss_nocot": 0.23800267279148102, "step": 2712 }, { "epoch": 2.5284249767008387, "grad_norm": 0.6436474880967102, "learning_rate": 3.493268898860891e-06, "loss": 0.7471, "step": 2713 }, { "epoch": 2.5284249767008387, "loss_cot": 0.49996480345726013, "loss_nocot": 0.2917185127735138, "step": 2713 }, { "epoch": 2.5293569431500464, "grad_norm": 0.6637930052546982, "learning_rate": 3.4863652053848813e-06, "loss": 0.743, "step": 2714 }, { "epoch": 2.5293569431500464, "loss_cot": 0.5130043029785156, "loss_nocot": 0.23263320326805115, "step": 2714 }, { "epoch": 2.5302889095992542, "grad_norm": 0.6367219834081429, "learning_rate": 3.4794615119088716e-06, "loss": 0.7519, "step": 2715 }, { "epoch": 2.5302889095992542, "loss_cot": 0.4558185338973999, "loss_nocot": 0.1882505714893341, "step": 2715 }, { "epoch": 2.5312208760484625, "grad_norm": 0.690056449618467, "learning_rate": 3.472557818432862e-06, "loss": 0.8128, "step": 2716 }, { "epoch": 2.5312208760484625, "loss_cot": 0.5048257112503052, "loss_nocot": 0.2850652039051056, "step": 2716 }, { "epoch": 2.53215284249767, "grad_norm": 0.783679546910675, "learning_rate": 3.465654124956852e-06, "loss": 0.837, "step": 2717 }, { "epoch": 2.53215284249767, "loss_cot": 0.5181480050086975, "loss_nocot": 0.2735767364501953, "step": 2717 }, { "epoch": 2.533084808946878, "grad_norm": 0.697611486117543, "learning_rate": 3.4587504314808425e-06, "loss": 0.7782, "step": 2718 }, { "epoch": 2.533084808946878, "loss_cot": 0.4961860179901123, "loss_nocot": 0.2255481779575348, "step": 2718 }, { "epoch": 2.534016775396086, "grad_norm": 0.6400581856361302, "learning_rate": 3.451846738004833e-06, "loss": 0.7276, "step": 2719 }, { "epoch": 2.534016775396086, "loss_cot": 0.4570924639701843, "loss_nocot": 0.22715885937213898, "step": 2719 }, { "epoch": 2.5349487418452936, "grad_norm": 0.6280013429160779, "learning_rate": 3.4449430445288235e-06, "loss": 0.7246, "step": 2720 }, { "epoch": 2.5349487418452936, "loss_cot": 0.4440075159072876, "loss_nocot": 0.25722941756248474, "step": 2720 }, { "epoch": 2.5358807082945014, "grad_norm": 0.6297359604170543, "learning_rate": 3.438039351052814e-06, "loss": 0.7171, "step": 2721 }, { "epoch": 2.5358807082945014, "loss_cot": 0.5046340227127075, "loss_nocot": 0.18307660520076752, "step": 2721 }, { "epoch": 2.536812674743709, "grad_norm": 0.6020112206483275, "learning_rate": 3.431135657576804e-06, "loss": 0.7213, "step": 2722 }, { "epoch": 2.536812674743709, "loss_cot": 0.4500266909599304, "loss_nocot": 0.2781418263912201, "step": 2722 }, { "epoch": 2.537744641192917, "grad_norm": 0.6780830119942284, "learning_rate": 3.4242319641007945e-06, "loss": 0.7554, "step": 2723 }, { "epoch": 2.537744641192917, "loss_cot": 0.5284820795059204, "loss_nocot": 0.21763673424720764, "step": 2723 }, { "epoch": 2.5386766076421248, "grad_norm": 0.6445867977244142, "learning_rate": 3.4173282706247844e-06, "loss": 0.7246, "step": 2724 }, { "epoch": 2.5386766076421248, "loss_cot": 0.45467010140419006, "loss_nocot": 0.25653406977653503, "step": 2724 }, { "epoch": 2.5396085740913326, "grad_norm": 0.6616091788701026, "learning_rate": 3.4104245771487747e-06, "loss": 0.7462, "step": 2725 }, { "epoch": 2.5396085740913326, "loss_cot": 0.47700586915016174, "loss_nocot": 0.2247331440448761, "step": 2725 }, { "epoch": 2.5405405405405403, "grad_norm": 0.651592569889402, "learning_rate": 3.403520883672765e-06, "loss": 0.7587, "step": 2726 }, { "epoch": 2.5405405405405403, "loss_cot": 0.4714524745941162, "loss_nocot": 0.25870150327682495, "step": 2726 }, { "epoch": 2.5414725069897486, "grad_norm": 0.6961502265500591, "learning_rate": 3.3966171901967553e-06, "loss": 0.7776, "step": 2727 }, { "epoch": 2.5414725069897486, "loss_cot": 0.48249131441116333, "loss_nocot": 0.3195890784263611, "step": 2727 }, { "epoch": 2.542404473438956, "grad_norm": 0.6252384739888592, "learning_rate": 3.3897134967207456e-06, "loss": 0.7239, "step": 2728 }, { "epoch": 2.542404473438956, "loss_cot": 0.4774535894393921, "loss_nocot": 0.33626627922058105, "step": 2728 }, { "epoch": 2.543336439888164, "grad_norm": 0.6872496539682498, "learning_rate": 3.382809803244736e-06, "loss": 0.762, "step": 2729 }, { "epoch": 2.543336439888164, "loss_cot": 0.44211167097091675, "loss_nocot": 0.29838621616363525, "step": 2729 }, { "epoch": 2.544268406337372, "grad_norm": 0.6825492745053291, "learning_rate": 3.3759061097687266e-06, "loss": 0.7522, "step": 2730 }, { "epoch": 2.544268406337372, "loss_cot": 0.5297735929489136, "loss_nocot": 0.27379482984542847, "step": 2730 }, { "epoch": 2.5452003727865797, "grad_norm": 0.6769581487651339, "learning_rate": 3.369002416292717e-06, "loss": 0.7692, "step": 2731 }, { "epoch": 2.5452003727865797, "loss_cot": 0.4619593620300293, "loss_nocot": 0.26766151189804077, "step": 2731 }, { "epoch": 2.5461323392357875, "grad_norm": 0.64933144027615, "learning_rate": 3.3620987228167072e-06, "loss": 0.7344, "step": 2732 }, { "epoch": 2.5461323392357875, "loss_cot": 0.5372648239135742, "loss_nocot": 0.24899369478225708, "step": 2732 }, { "epoch": 2.5470643056849953, "grad_norm": 0.6228397406555973, "learning_rate": 3.3551950293406976e-06, "loss": 0.7316, "step": 2733 }, { "epoch": 2.5470643056849953, "loss_cot": 0.494049608707428, "loss_nocot": 0.23575131595134735, "step": 2733 }, { "epoch": 2.547996272134203, "grad_norm": 0.6436652559372685, "learning_rate": 3.348291335864688e-06, "loss": 0.7557, "step": 2734 }, { "epoch": 2.547996272134203, "loss_cot": 0.4620805084705353, "loss_nocot": 0.42252999544143677, "step": 2734 }, { "epoch": 2.548928238583411, "grad_norm": 0.7109333627210156, "learning_rate": 3.341387642388678e-06, "loss": 0.8016, "step": 2735 }, { "epoch": 2.548928238583411, "loss_cot": 0.4608345627784729, "loss_nocot": 0.2024776041507721, "step": 2735 }, { "epoch": 2.5498602050326187, "grad_norm": 0.6228325448412826, "learning_rate": 3.3344839489126685e-06, "loss": 0.6928, "step": 2736 }, { "epoch": 2.5498602050326187, "loss_cot": 0.4560946524143219, "loss_nocot": 0.28308552503585815, "step": 2736 }, { "epoch": 2.5507921714818265, "grad_norm": 0.6988927622418061, "learning_rate": 3.327580255436659e-06, "loss": 0.7547, "step": 2737 }, { "epoch": 2.5507921714818265, "loss_cot": 0.4848540723323822, "loss_nocot": 0.2051345854997635, "step": 2737 }, { "epoch": 2.5517241379310347, "grad_norm": 0.6736647658224535, "learning_rate": 3.320676561960649e-06, "loss": 0.7502, "step": 2738 }, { "epoch": 2.5517241379310347, "loss_cot": 0.546538233757019, "loss_nocot": 0.1685141921043396, "step": 2738 }, { "epoch": 2.552656104380242, "grad_norm": 0.6383343626442286, "learning_rate": 3.3137728684846394e-06, "loss": 0.7173, "step": 2739 }, { "epoch": 2.552656104380242, "loss_cot": 0.4759744107723236, "loss_nocot": 0.3387162685394287, "step": 2739 }, { "epoch": 2.5535880708294503, "grad_norm": 0.6600183703835466, "learning_rate": 3.30686917500863e-06, "loss": 0.7752, "step": 2740 }, { "epoch": 2.5535880708294503, "loss_cot": 0.5555898547172546, "loss_nocot": 0.17585982382297516, "step": 2740 }, { "epoch": 2.554520037278658, "grad_norm": 0.6011775040258863, "learning_rate": 3.2999654815326205e-06, "loss": 0.7245, "step": 2741 }, { "epoch": 2.554520037278658, "loss_cot": 0.39835304021835327, "loss_nocot": 0.33828702569007874, "step": 2741 }, { "epoch": 2.555452003727866, "grad_norm": 0.6683553849396024, "learning_rate": 3.2930617880566108e-06, "loss": 0.7321, "step": 2742 }, { "epoch": 2.555452003727866, "loss_cot": 0.5008731484413147, "loss_nocot": 0.15572696924209595, "step": 2742 }, { "epoch": 2.5563839701770736, "grad_norm": 0.6295450241263915, "learning_rate": 3.286158094580601e-06, "loss": 0.7492, "step": 2743 }, { "epoch": 2.5563839701770736, "loss_cot": 0.495670348405838, "loss_nocot": 0.26898813247680664, "step": 2743 }, { "epoch": 2.5573159366262814, "grad_norm": 0.6653775547436656, "learning_rate": 3.2792544011045914e-06, "loss": 0.764, "step": 2744 }, { "epoch": 2.5573159366262814, "loss_cot": 0.5190359354019165, "loss_nocot": 0.23227839171886444, "step": 2744 }, { "epoch": 2.558247903075489, "grad_norm": 0.6662202734582408, "learning_rate": 3.2723507076285817e-06, "loss": 0.7489, "step": 2745 }, { "epoch": 2.558247903075489, "loss_cot": 0.4213804602622986, "loss_nocot": 0.3182605803012848, "step": 2745 }, { "epoch": 2.559179869524697, "grad_norm": 0.7016229993179135, "learning_rate": 3.265447014152572e-06, "loss": 0.7491, "step": 2746 }, { "epoch": 2.559179869524697, "loss_cot": 0.4763026535511017, "loss_nocot": 0.2832094430923462, "step": 2746 }, { "epoch": 2.560111835973905, "grad_norm": 0.6068923849214611, "learning_rate": 3.258543320676562e-06, "loss": 0.7271, "step": 2747 }, { "epoch": 2.560111835973905, "loss_cot": 0.5248501300811768, "loss_nocot": 0.31219351291656494, "step": 2747 }, { "epoch": 2.5610438024231126, "grad_norm": 0.6765736491699047, "learning_rate": 3.251639627200552e-06, "loss": 0.783, "step": 2748 }, { "epoch": 2.5610438024231126, "loss_cot": 0.501715898513794, "loss_nocot": 0.1907745599746704, "step": 2748 }, { "epoch": 2.561975768872321, "grad_norm": 0.6189965247350319, "learning_rate": 3.2447359337245425e-06, "loss": 0.7245, "step": 2749 }, { "epoch": 2.561975768872321, "loss_cot": 0.4966229200363159, "loss_nocot": 0.28388410806655884, "step": 2749 }, { "epoch": 2.562907735321528, "grad_norm": 0.6678967639867567, "learning_rate": 3.2378322402485337e-06, "loss": 0.7627, "step": 2750 }, { "epoch": 2.562907735321528, "loss_cot": 0.48544639348983765, "loss_nocot": 0.24363666772842407, "step": 2750 }, { "epoch": 2.5638397017707364, "grad_norm": 0.661192269112675, "learning_rate": 3.230928546772524e-06, "loss": 0.7483, "step": 2751 }, { "epoch": 2.5638397017707364, "loss_cot": 0.43776392936706543, "loss_nocot": 0.21368907392024994, "step": 2751 }, { "epoch": 2.564771668219944, "grad_norm": 0.6584253362875203, "learning_rate": 3.224024853296514e-06, "loss": 0.7322, "step": 2752 }, { "epoch": 2.564771668219944, "loss_cot": 0.47875311970710754, "loss_nocot": 0.25301241874694824, "step": 2752 }, { "epoch": 2.565703634669152, "grad_norm": 0.6724015022356756, "learning_rate": 3.217121159820504e-06, "loss": 0.7865, "step": 2753 }, { "epoch": 2.565703634669152, "loss_cot": 0.5318774580955505, "loss_nocot": 0.30135107040405273, "step": 2753 }, { "epoch": 2.5666356011183598, "grad_norm": 0.66526126106008, "learning_rate": 3.2102174663444945e-06, "loss": 0.8194, "step": 2754 }, { "epoch": 2.5666356011183598, "loss_cot": 0.5002728700637817, "loss_nocot": 0.24011234939098358, "step": 2754 }, { "epoch": 2.5675675675675675, "grad_norm": 0.6464816929473453, "learning_rate": 3.2033137728684848e-06, "loss": 0.7297, "step": 2755 }, { "epoch": 2.5675675675675675, "loss_cot": 0.5449395775794983, "loss_nocot": 0.2326042354106903, "step": 2755 }, { "epoch": 2.5684995340167753, "grad_norm": 0.6318565813257905, "learning_rate": 3.196410079392475e-06, "loss": 0.7454, "step": 2756 }, { "epoch": 2.5684995340167753, "loss_cot": 0.5015572309494019, "loss_nocot": 0.3240147531032562, "step": 2756 }, { "epoch": 2.569431500465983, "grad_norm": 0.6882211927134877, "learning_rate": 3.1895063859164654e-06, "loss": 0.7924, "step": 2757 }, { "epoch": 2.569431500465983, "loss_cot": 0.4635450839996338, "loss_nocot": 0.39202070236206055, "step": 2757 }, { "epoch": 2.570363466915191, "grad_norm": 0.6977520556203521, "learning_rate": 3.1826026924404557e-06, "loss": 0.7845, "step": 2758 }, { "epoch": 2.570363466915191, "loss_cot": 0.4856380224227905, "loss_nocot": 0.2114868462085724, "step": 2758 }, { "epoch": 2.5712954333643987, "grad_norm": 0.6838728226851958, "learning_rate": 3.175698998964446e-06, "loss": 0.7614, "step": 2759 }, { "epoch": 2.5712954333643987, "loss_cot": 0.5035848617553711, "loss_nocot": 0.22417239844799042, "step": 2759 }, { "epoch": 2.572227399813607, "grad_norm": 0.6678748201733025, "learning_rate": 3.1687953054884367e-06, "loss": 0.7649, "step": 2760 }, { "epoch": 2.572227399813607, "loss_cot": 0.5152361989021301, "loss_nocot": 0.23290784657001495, "step": 2760 }, { "epoch": 2.5731593662628143, "grad_norm": 0.7146379396073798, "learning_rate": 3.161891612012427e-06, "loss": 0.8182, "step": 2761 }, { "epoch": 2.5731593662628143, "loss_cot": 0.5264038443565369, "loss_nocot": 0.20237997174263, "step": 2761 }, { "epoch": 2.5740913327120225, "grad_norm": 0.6576171259622261, "learning_rate": 3.1549879185364174e-06, "loss": 0.766, "step": 2762 }, { "epoch": 2.5740913327120225, "loss_cot": 0.5051852464675903, "loss_nocot": 0.20364755392074585, "step": 2762 }, { "epoch": 2.5750232991612303, "grad_norm": 0.6747841526865495, "learning_rate": 3.1480842250604077e-06, "loss": 0.8215, "step": 2763 }, { "epoch": 2.5750232991612303, "loss_cot": 0.5393571257591248, "loss_nocot": 0.22161895036697388, "step": 2763 }, { "epoch": 2.575955265610438, "grad_norm": 0.6532099472486047, "learning_rate": 3.141180531584398e-06, "loss": 0.763, "step": 2764 }, { "epoch": 2.575955265610438, "loss_cot": 0.5054702162742615, "loss_nocot": 0.26708441972732544, "step": 2764 }, { "epoch": 2.576887232059646, "grad_norm": 0.6392435038644421, "learning_rate": 3.1342768381083883e-06, "loss": 0.7319, "step": 2765 }, { "epoch": 2.576887232059646, "loss_cot": 0.5162937045097351, "loss_nocot": 0.2450101673603058, "step": 2765 }, { "epoch": 2.5778191985088537, "grad_norm": 0.6368755755401124, "learning_rate": 3.1273731446323786e-06, "loss": 0.7455, "step": 2766 }, { "epoch": 2.5778191985088537, "loss_cot": 0.45016223192214966, "loss_nocot": 0.25516510009765625, "step": 2766 }, { "epoch": 2.5787511649580614, "grad_norm": 0.6595249229013137, "learning_rate": 3.120469451156369e-06, "loss": 0.7025, "step": 2767 }, { "epoch": 2.5787511649580614, "loss_cot": 0.4657365679740906, "loss_nocot": 0.3014497458934784, "step": 2767 }, { "epoch": 2.5796831314072692, "grad_norm": 0.6526298027534865, "learning_rate": 3.1135657576803592e-06, "loss": 0.771, "step": 2768 }, { "epoch": 2.5796831314072692, "loss_cot": 0.4990929961204529, "loss_nocot": 0.3386952579021454, "step": 2768 }, { "epoch": 2.580615097856477, "grad_norm": 0.6131801784106605, "learning_rate": 3.1066620642043495e-06, "loss": 0.7713, "step": 2769 }, { "epoch": 2.580615097856477, "loss_cot": 0.4354022145271301, "loss_nocot": 0.2758575677871704, "step": 2769 }, { "epoch": 2.581547064305685, "grad_norm": 0.6725899270393904, "learning_rate": 3.0997583707283403e-06, "loss": 0.7196, "step": 2770 }, { "epoch": 2.581547064305685, "loss_cot": 0.5373119115829468, "loss_nocot": 0.3409634828567505, "step": 2770 }, { "epoch": 2.582479030754893, "grad_norm": 0.6253745724983232, "learning_rate": 3.0928546772523306e-06, "loss": 0.7435, "step": 2771 }, { "epoch": 2.582479030754893, "loss_cot": 0.4728933572769165, "loss_nocot": 0.2221112698316574, "step": 2771 }, { "epoch": 2.5834109972041004, "grad_norm": 0.620349502154676, "learning_rate": 3.085950983776321e-06, "loss": 0.6847, "step": 2772 }, { "epoch": 2.5834109972041004, "loss_cot": 0.48547524213790894, "loss_nocot": 0.2801324725151062, "step": 2772 }, { "epoch": 2.5843429636533086, "grad_norm": 0.6388540000713557, "learning_rate": 3.079047290300311e-06, "loss": 0.7341, "step": 2773 }, { "epoch": 2.5843429636533086, "loss_cot": 0.5423191785812378, "loss_nocot": 0.17574578523635864, "step": 2773 }, { "epoch": 2.5852749301025164, "grad_norm": 0.6447913824922055, "learning_rate": 3.0721435968243015e-06, "loss": 0.7211, "step": 2774 }, { "epoch": 2.5852749301025164, "loss_cot": 0.45300036668777466, "loss_nocot": 0.2521165609359741, "step": 2774 }, { "epoch": 2.586206896551724, "grad_norm": 0.7126541955732101, "learning_rate": 3.0652399033482914e-06, "loss": 0.7626, "step": 2775 }, { "epoch": 2.586206896551724, "loss_cot": 0.4505102038383484, "loss_nocot": 0.23660048842430115, "step": 2775 }, { "epoch": 2.587138863000932, "grad_norm": 0.6177388850132101, "learning_rate": 3.0583362098722817e-06, "loss": 0.7125, "step": 2776 }, { "epoch": 2.587138863000932, "loss_cot": 0.4734998941421509, "loss_nocot": 0.24285002052783966, "step": 2776 }, { "epoch": 2.5880708294501398, "grad_norm": 0.6730597399452662, "learning_rate": 3.051432516396272e-06, "loss": 0.7327, "step": 2777 }, { "epoch": 2.5880708294501398, "loss_cot": 0.4623604118824005, "loss_nocot": 0.17758935689926147, "step": 2777 }, { "epoch": 2.5890027958993476, "grad_norm": 0.6374366678035506, "learning_rate": 3.0445288229202623e-06, "loss": 0.7209, "step": 2778 }, { "epoch": 2.5890027958993476, "loss_cot": 0.5377905964851379, "loss_nocot": 0.3418956995010376, "step": 2778 }, { "epoch": 2.5899347623485554, "grad_norm": 0.6460537469051439, "learning_rate": 3.0376251294442526e-06, "loss": 0.7667, "step": 2779 }, { "epoch": 2.5899347623485554, "loss_cot": 0.5007438659667969, "loss_nocot": 0.363681823015213, "step": 2779 }, { "epoch": 2.590866728797763, "grad_norm": 0.7978696096961563, "learning_rate": 3.0307214359682433e-06, "loss": 0.8041, "step": 2780 }, { "epoch": 2.590866728797763, "loss_cot": 0.5344452857971191, "loss_nocot": 0.31119757890701294, "step": 2780 }, { "epoch": 2.591798695246971, "grad_norm": 0.6189097726676617, "learning_rate": 3.0238177424922337e-06, "loss": 0.759, "step": 2781 }, { "epoch": 2.591798695246971, "loss_cot": 0.451028972864151, "loss_nocot": 0.29514217376708984, "step": 2781 }, { "epoch": 2.592730661696179, "grad_norm": 0.6979049882352665, "learning_rate": 3.016914049016224e-06, "loss": 0.7898, "step": 2782 }, { "epoch": 2.592730661696179, "loss_cot": 0.4431474208831787, "loss_nocot": 0.2512623965740204, "step": 2782 }, { "epoch": 2.5936626281453865, "grad_norm": 0.634582832394507, "learning_rate": 3.0100103555402143e-06, "loss": 0.7583, "step": 2783 }, { "epoch": 2.5936626281453865, "loss_cot": 0.44886916875839233, "loss_nocot": 0.2365494966506958, "step": 2783 }, { "epoch": 2.5945945945945947, "grad_norm": 0.6276970531041159, "learning_rate": 3.0031066620642046e-06, "loss": 0.711, "step": 2784 }, { "epoch": 2.5945945945945947, "loss_cot": 0.46067875623703003, "loss_nocot": 0.21147458255290985, "step": 2784 }, { "epoch": 2.5955265610438025, "grad_norm": 0.6599828859312221, "learning_rate": 2.996202968588195e-06, "loss": 0.7391, "step": 2785 }, { "epoch": 2.5955265610438025, "loss_cot": 0.5626062154769897, "loss_nocot": 0.2714267373085022, "step": 2785 }, { "epoch": 2.5964585274930103, "grad_norm": 0.6996183441787586, "learning_rate": 2.989299275112185e-06, "loss": 0.868, "step": 2786 }, { "epoch": 2.5964585274930103, "loss_cot": 0.5272159576416016, "loss_nocot": 0.25301259756088257, "step": 2786 }, { "epoch": 2.597390493942218, "grad_norm": 0.6365145524692829, "learning_rate": 2.9823955816361755e-06, "loss": 0.7593, "step": 2787 }, { "epoch": 2.597390493942218, "loss_cot": 0.5293398499488831, "loss_nocot": 0.2503233551979065, "step": 2787 }, { "epoch": 2.598322460391426, "grad_norm": 0.676792332487768, "learning_rate": 2.975491888160166e-06, "loss": 0.7876, "step": 2788 }, { "epoch": 2.598322460391426, "loss_cot": 0.46319812536239624, "loss_nocot": 0.21893298625946045, "step": 2788 }, { "epoch": 2.5992544268406337, "grad_norm": 0.6285214089867768, "learning_rate": 2.968588194684156e-06, "loss": 0.7526, "step": 2789 }, { "epoch": 2.5992544268406337, "loss_cot": 0.4844975173473358, "loss_nocot": 0.25983256101608276, "step": 2789 }, { "epoch": 2.6001863932898415, "grad_norm": 0.677050399700733, "learning_rate": 2.9616845012081464e-06, "loss": 0.7535, "step": 2790 }, { "epoch": 2.6001863932898415, "loss_cot": 0.48087915778160095, "loss_nocot": 0.25142592191696167, "step": 2790 }, { "epoch": 2.6011183597390493, "grad_norm": 0.6342823641835976, "learning_rate": 2.954780807732137e-06, "loss": 0.7543, "step": 2791 }, { "epoch": 2.6011183597390493, "loss_cot": 0.52852463722229, "loss_nocot": 0.21961379051208496, "step": 2791 }, { "epoch": 2.602050326188257, "grad_norm": 0.6486128074527272, "learning_rate": 2.9478771142561275e-06, "loss": 0.7766, "step": 2792 }, { "epoch": 2.602050326188257, "loss_cot": 0.46905404329299927, "loss_nocot": 0.22932463884353638, "step": 2792 }, { "epoch": 2.6029822926374653, "grad_norm": 0.7337853183964974, "learning_rate": 2.940973420780118e-06, "loss": 0.7435, "step": 2793 }, { "epoch": 2.6029822926374653, "loss_cot": 0.4902459681034088, "loss_nocot": 0.3340981602668762, "step": 2793 }, { "epoch": 2.6039142590866726, "grad_norm": 0.6564181888721923, "learning_rate": 2.934069727304108e-06, "loss": 0.77, "step": 2794 }, { "epoch": 2.6039142590866726, "loss_cot": 0.5055633783340454, "loss_nocot": 0.22219237685203552, "step": 2794 }, { "epoch": 2.604846225535881, "grad_norm": 0.6211800553037737, "learning_rate": 2.9271660338280984e-06, "loss": 0.7377, "step": 2795 }, { "epoch": 2.604846225535881, "loss_cot": 0.47413820028305054, "loss_nocot": 0.28066402673721313, "step": 2795 }, { "epoch": 2.6057781919850886, "grad_norm": 0.6628071363360963, "learning_rate": 2.9202623403520887e-06, "loss": 0.7262, "step": 2796 }, { "epoch": 2.6057781919850886, "loss_cot": 0.5130020380020142, "loss_nocot": 0.3442630171775818, "step": 2796 }, { "epoch": 2.6067101584342964, "grad_norm": 0.6339635700014821, "learning_rate": 2.913358646876079e-06, "loss": 0.7383, "step": 2797 }, { "epoch": 2.6067101584342964, "loss_cot": 0.43739598989486694, "loss_nocot": 0.2981025278568268, "step": 2797 }, { "epoch": 2.607642124883504, "grad_norm": 0.6683598454217263, "learning_rate": 2.906454953400069e-06, "loss": 0.7401, "step": 2798 }, { "epoch": 2.607642124883504, "loss_cot": 0.5258008241653442, "loss_nocot": 0.21704953908920288, "step": 2798 }, { "epoch": 2.608574091332712, "grad_norm": 0.6842494847143393, "learning_rate": 2.8995512599240592e-06, "loss": 0.7415, "step": 2799 }, { "epoch": 2.608574091332712, "loss_cot": 0.5137715339660645, "loss_nocot": 0.24629519879817963, "step": 2799 }, { "epoch": 2.60950605778192, "grad_norm": 0.6001263747967094, "learning_rate": 2.8926475664480495e-06, "loss": 0.7605, "step": 2800 }, { "epoch": 2.60950605778192, "loss_cot": 0.47798120975494385, "loss_nocot": 0.29603201150894165, "step": 2800 }, { "epoch": 2.6104380242311276, "grad_norm": 0.6446394735648722, "learning_rate": 2.8857438729720407e-06, "loss": 0.7591, "step": 2801 }, { "epoch": 2.6104380242311276, "loss_cot": 0.5517392754554749, "loss_nocot": 0.3503457009792328, "step": 2801 }, { "epoch": 2.6113699906803354, "grad_norm": 0.642289459147373, "learning_rate": 2.878840179496031e-06, "loss": 0.7629, "step": 2802 }, { "epoch": 2.6113699906803354, "loss_cot": 0.46667397022247314, "loss_nocot": 0.2542894184589386, "step": 2802 }, { "epoch": 2.612301957129543, "grad_norm": 0.598802889045013, "learning_rate": 2.871936486020021e-06, "loss": 0.7318, "step": 2803 }, { "epoch": 2.612301957129543, "loss_cot": 0.45802196860313416, "loss_nocot": 0.17183955013751984, "step": 2803 }, { "epoch": 2.6132339235787514, "grad_norm": 0.6373788905603459, "learning_rate": 2.865032792544011e-06, "loss": 0.7284, "step": 2804 }, { "epoch": 2.6132339235787514, "loss_cot": 0.49446481466293335, "loss_nocot": 0.2437361627817154, "step": 2804 }, { "epoch": 2.6141658900279587, "grad_norm": 0.6372716217800735, "learning_rate": 2.8581290990680015e-06, "loss": 0.742, "step": 2805 }, { "epoch": 2.6141658900279587, "loss_cot": 0.4688764810562134, "loss_nocot": 0.23448458313941956, "step": 2805 }, { "epoch": 2.615097856477167, "grad_norm": 0.623918405317312, "learning_rate": 2.851225405591992e-06, "loss": 0.715, "step": 2806 }, { "epoch": 2.615097856477167, "loss_cot": 0.45545247197151184, "loss_nocot": 0.2272310107946396, "step": 2806 }, { "epoch": 2.6160298229263748, "grad_norm": 0.6123347169198716, "learning_rate": 2.844321712115982e-06, "loss": 0.7047, "step": 2807 }, { "epoch": 2.6160298229263748, "loss_cot": 0.5050809979438782, "loss_nocot": 0.2908993363380432, "step": 2807 }, { "epoch": 2.6169617893755825, "grad_norm": 0.6543228122878815, "learning_rate": 2.8374180186399724e-06, "loss": 0.7657, "step": 2808 }, { "epoch": 2.6169617893755825, "loss_cot": 0.5685659050941467, "loss_nocot": 0.2622295320034027, "step": 2808 }, { "epoch": 2.6178937558247903, "grad_norm": 0.6284508526386268, "learning_rate": 2.8305143251639627e-06, "loss": 0.7778, "step": 2809 }, { "epoch": 2.6178937558247903, "loss_cot": 0.45610883831977844, "loss_nocot": 0.2392982691526413, "step": 2809 }, { "epoch": 2.618825722273998, "grad_norm": 0.6906389301907382, "learning_rate": 2.823610631687953e-06, "loss": 0.7193, "step": 2810 }, { "epoch": 2.618825722273998, "loss_cot": 0.4735293388366699, "loss_nocot": 0.2675189971923828, "step": 2810 }, { "epoch": 2.619757688723206, "grad_norm": 0.6082775475872118, "learning_rate": 2.8167069382119438e-06, "loss": 0.733, "step": 2811 }, { "epoch": 2.619757688723206, "loss_cot": 0.5461004972457886, "loss_nocot": 0.24776680767536163, "step": 2811 }, { "epoch": 2.6206896551724137, "grad_norm": 0.6311695148591799, "learning_rate": 2.809803244735934e-06, "loss": 0.7664, "step": 2812 }, { "epoch": 2.6206896551724137, "loss_cot": 0.5174676775932312, "loss_nocot": 0.19354350864887238, "step": 2812 }, { "epoch": 2.6216216216216215, "grad_norm": 0.6481265195197924, "learning_rate": 2.8028995512599244e-06, "loss": 0.7634, "step": 2813 }, { "epoch": 2.6216216216216215, "loss_cot": 0.5320195555686951, "loss_nocot": 0.26073020696640015, "step": 2813 }, { "epoch": 2.6225535880708293, "grad_norm": 0.6491737179199282, "learning_rate": 2.7959958577839147e-06, "loss": 0.7547, "step": 2814 }, { "epoch": 2.6225535880708293, "loss_cot": 0.4899752736091614, "loss_nocot": 0.2891966998577118, "step": 2814 }, { "epoch": 2.6234855545200375, "grad_norm": 0.6368972137178112, "learning_rate": 2.789092164307905e-06, "loss": 0.7174, "step": 2815 }, { "epoch": 2.6234855545200375, "loss_cot": 0.44145074486732483, "loss_nocot": 0.22548913955688477, "step": 2815 }, { "epoch": 2.624417520969245, "grad_norm": 0.6183739242538697, "learning_rate": 2.7821884708318953e-06, "loss": 0.7466, "step": 2816 }, { "epoch": 2.624417520969245, "loss_cot": 0.5000108480453491, "loss_nocot": 0.29261258244514465, "step": 2816 }, { "epoch": 2.625349487418453, "grad_norm": 0.6812119652095977, "learning_rate": 2.7752847773558856e-06, "loss": 0.7902, "step": 2817 }, { "epoch": 2.625349487418453, "loss_cot": 0.4552030563354492, "loss_nocot": 0.1973584145307541, "step": 2817 }, { "epoch": 2.626281453867661, "grad_norm": 0.6094122625917479, "learning_rate": 2.768381083879876e-06, "loss": 0.7579, "step": 2818 }, { "epoch": 2.626281453867661, "loss_cot": 0.5323871374130249, "loss_nocot": 0.3055136799812317, "step": 2818 }, { "epoch": 2.6272134203168687, "grad_norm": 0.697023363686315, "learning_rate": 2.7614773904038662e-06, "loss": 0.7633, "step": 2819 }, { "epoch": 2.6272134203168687, "loss_cot": 0.49470290541648865, "loss_nocot": 0.19350257515907288, "step": 2819 }, { "epoch": 2.6281453867660765, "grad_norm": 0.6044184384797711, "learning_rate": 2.7545736969278566e-06, "loss": 0.7409, "step": 2820 }, { "epoch": 2.6281453867660765, "loss_cot": 0.5390397310256958, "loss_nocot": 0.24687299132347107, "step": 2820 }, { "epoch": 2.6290773532152842, "grad_norm": 0.6522425905512683, "learning_rate": 2.7476700034518473e-06, "loss": 0.7835, "step": 2821 }, { "epoch": 2.6290773532152842, "loss_cot": 0.5294114351272583, "loss_nocot": 0.3149833679199219, "step": 2821 }, { "epoch": 2.630009319664492, "grad_norm": 0.6842845623775055, "learning_rate": 2.7407663099758376e-06, "loss": 0.7954, "step": 2822 }, { "epoch": 2.630009319664492, "loss_cot": 0.4923137128353119, "loss_nocot": 0.23644688725471497, "step": 2822 }, { "epoch": 2.6309412861137, "grad_norm": 0.6760109744014186, "learning_rate": 2.733862616499828e-06, "loss": 0.76, "step": 2823 }, { "epoch": 2.6309412861137, "loss_cot": 0.4709388017654419, "loss_nocot": 0.28600457310676575, "step": 2823 }, { "epoch": 2.6318732525629076, "grad_norm": 0.671327633326254, "learning_rate": 2.7269589230238182e-06, "loss": 0.7634, "step": 2824 }, { "epoch": 2.6318732525629076, "loss_cot": 0.5022214651107788, "loss_nocot": 0.20302626490592957, "step": 2824 }, { "epoch": 2.6328052190121154, "grad_norm": 0.6509221591483375, "learning_rate": 2.7200552295478085e-06, "loss": 0.7414, "step": 2825 }, { "epoch": 2.6328052190121154, "loss_cot": 0.445507287979126, "loss_nocot": 0.1951369047164917, "step": 2825 }, { "epoch": 2.6337371854613236, "grad_norm": 0.5993020737565642, "learning_rate": 2.7131515360717984e-06, "loss": 0.7284, "step": 2826 }, { "epoch": 2.6337371854613236, "loss_cot": 0.5015464425086975, "loss_nocot": 0.2756150960922241, "step": 2826 }, { "epoch": 2.634669151910531, "grad_norm": 0.6645276255792023, "learning_rate": 2.7062478425957887e-06, "loss": 0.7718, "step": 2827 }, { "epoch": 2.634669151910531, "loss_cot": 0.5070730447769165, "loss_nocot": 0.2591869831085205, "step": 2827 }, { "epoch": 2.635601118359739, "grad_norm": 0.6312123033048341, "learning_rate": 2.699344149119779e-06, "loss": 0.7425, "step": 2828 }, { "epoch": 2.635601118359739, "loss_cot": 0.5686230063438416, "loss_nocot": 0.2057877480983734, "step": 2828 }, { "epoch": 2.636533084808947, "grad_norm": 0.6173478156957739, "learning_rate": 2.6924404556437693e-06, "loss": 0.7261, "step": 2829 }, { "epoch": 2.636533084808947, "loss_cot": 0.5301369428634644, "loss_nocot": 0.31233078241348267, "step": 2829 }, { "epoch": 2.637465051258155, "grad_norm": 0.6893837234325579, "learning_rate": 2.6855367621677596e-06, "loss": 0.7587, "step": 2830 }, { "epoch": 2.637465051258155, "loss_cot": 0.5176812410354614, "loss_nocot": 0.16931501030921936, "step": 2830 }, { "epoch": 2.6383970177073626, "grad_norm": 0.6178002814677871, "learning_rate": 2.6786330686917504e-06, "loss": 0.7398, "step": 2831 }, { "epoch": 2.6383970177073626, "loss_cot": 0.5246755480766296, "loss_nocot": 0.19316501915454865, "step": 2831 }, { "epoch": 2.6393289841565704, "grad_norm": 0.6428724890291515, "learning_rate": 2.6717293752157407e-06, "loss": 0.7011, "step": 2832 }, { "epoch": 2.6393289841565704, "loss_cot": 0.4659379720687866, "loss_nocot": 0.2901887893676758, "step": 2832 }, { "epoch": 2.640260950605778, "grad_norm": 0.6763000646735644, "learning_rate": 2.664825681739731e-06, "loss": 0.7944, "step": 2833 }, { "epoch": 2.640260950605778, "loss_cot": 0.520835280418396, "loss_nocot": 0.26866260170936584, "step": 2833 }, { "epoch": 2.641192917054986, "grad_norm": 0.6163065396244036, "learning_rate": 2.6579219882637213e-06, "loss": 0.7191, "step": 2834 }, { "epoch": 2.641192917054986, "loss_cot": 0.5552382469177246, "loss_nocot": 0.2263334095478058, "step": 2834 }, { "epoch": 2.6421248835041937, "grad_norm": 0.6554718988162646, "learning_rate": 2.6510182947877116e-06, "loss": 0.8162, "step": 2835 }, { "epoch": 2.6421248835041937, "loss_cot": 0.5105505585670471, "loss_nocot": 0.28381091356277466, "step": 2835 }, { "epoch": 2.6430568499534015, "grad_norm": 0.6281921613125449, "learning_rate": 2.644114601311702e-06, "loss": 0.724, "step": 2836 }, { "epoch": 2.6430568499534015, "loss_cot": 0.5503411293029785, "loss_nocot": 0.2742278575897217, "step": 2836 }, { "epoch": 2.6439888164026097, "grad_norm": 0.6706598242366799, "learning_rate": 2.6372109078356922e-06, "loss": 0.7645, "step": 2837 }, { "epoch": 2.6439888164026097, "loss_cot": 0.5983442664146423, "loss_nocot": 0.3236139714717865, "step": 2837 }, { "epoch": 2.644920782851817, "grad_norm": 0.646974822512742, "learning_rate": 2.6303072143596825e-06, "loss": 0.778, "step": 2838 }, { "epoch": 2.644920782851817, "loss_cot": 0.43826279044151306, "loss_nocot": 0.27225354313850403, "step": 2838 }, { "epoch": 2.6458527493010253, "grad_norm": 0.6965075691607905, "learning_rate": 2.623403520883673e-06, "loss": 0.7655, "step": 2839 }, { "epoch": 2.6458527493010253, "loss_cot": 0.4598883092403412, "loss_nocot": 0.22327271103858948, "step": 2839 }, { "epoch": 2.646784715750233, "grad_norm": 0.6842457951346163, "learning_rate": 2.616499827407663e-06, "loss": 0.702, "step": 2840 }, { "epoch": 2.646784715750233, "loss_cot": 0.4710864722728729, "loss_nocot": 0.32556748390197754, "step": 2840 }, { "epoch": 2.647716682199441, "grad_norm": 0.6421887085224524, "learning_rate": 2.609596133931654e-06, "loss": 0.71, "step": 2841 }, { "epoch": 2.647716682199441, "loss_cot": 0.5251688361167908, "loss_nocot": 0.2622615694999695, "step": 2841 }, { "epoch": 2.6486486486486487, "grad_norm": 0.6792603081287318, "learning_rate": 2.602692440455644e-06, "loss": 0.7675, "step": 2842 }, { "epoch": 2.6486486486486487, "loss_cot": 0.458952397108078, "loss_nocot": 0.3170627951622009, "step": 2842 }, { "epoch": 2.6495806150978565, "grad_norm": 0.734771121026701, "learning_rate": 2.5957887469796345e-06, "loss": 0.786, "step": 2843 }, { "epoch": 2.6495806150978565, "loss_cot": 0.4871843457221985, "loss_nocot": 0.2501126825809479, "step": 2843 }, { "epoch": 2.6505125815470643, "grad_norm": 0.63585291104426, "learning_rate": 2.588885053503625e-06, "loss": 0.7484, "step": 2844 }, { "epoch": 2.6505125815470643, "loss_cot": 0.5012259483337402, "loss_nocot": 0.2533828020095825, "step": 2844 }, { "epoch": 2.651444547996272, "grad_norm": 0.6412758167381208, "learning_rate": 2.581981360027615e-06, "loss": 0.7664, "step": 2845 }, { "epoch": 2.651444547996272, "loss_cot": 0.5141822695732117, "loss_nocot": 0.24621163308620453, "step": 2845 }, { "epoch": 2.65237651444548, "grad_norm": 0.6451708600167507, "learning_rate": 2.5750776665516054e-06, "loss": 0.7329, "step": 2846 }, { "epoch": 2.65237651444548, "loss_cot": 0.5121618509292603, "loss_nocot": 0.23499667644500732, "step": 2846 }, { "epoch": 2.6533084808946876, "grad_norm": 0.6627144399361099, "learning_rate": 2.5681739730755957e-06, "loss": 0.7956, "step": 2847 }, { "epoch": 2.6533084808946876, "loss_cot": 0.488847017288208, "loss_nocot": 0.2350815385580063, "step": 2847 }, { "epoch": 2.654240447343896, "grad_norm": 0.6289777359616185, "learning_rate": 2.561270279599586e-06, "loss": 0.7299, "step": 2848 }, { "epoch": 2.654240447343896, "loss_cot": 0.48000067472457886, "loss_nocot": 0.23812592029571533, "step": 2848 }, { "epoch": 2.655172413793103, "grad_norm": 0.668987873852843, "learning_rate": 2.554366586123576e-06, "loss": 0.7724, "step": 2849 }, { "epoch": 2.655172413793103, "loss_cot": 0.5194119215011597, "loss_nocot": 0.31052088737487793, "step": 2849 }, { "epoch": 2.6561043802423114, "grad_norm": 0.694375558719978, "learning_rate": 2.5474628926475662e-06, "loss": 0.8149, "step": 2850 }, { "epoch": 2.6561043802423114, "loss_cot": 0.49912941455841064, "loss_nocot": 0.2579001784324646, "step": 2850 }, { "epoch": 2.6570363466915192, "grad_norm": 0.6533259415042941, "learning_rate": 2.5405591991715574e-06, "loss": 0.7393, "step": 2851 }, { "epoch": 2.6570363466915192, "loss_cot": 0.4806220531463623, "loss_nocot": 0.21217778325080872, "step": 2851 }, { "epoch": 2.657968313140727, "grad_norm": 0.6229352908910987, "learning_rate": 2.5336555056955477e-06, "loss": 0.719, "step": 2852 }, { "epoch": 2.657968313140727, "loss_cot": 0.5478849411010742, "loss_nocot": 0.19217213988304138, "step": 2852 }, { "epoch": 2.658900279589935, "grad_norm": 0.7300609051668372, "learning_rate": 2.5267518122195376e-06, "loss": 0.7479, "step": 2853 }, { "epoch": 2.658900279589935, "loss_cot": 0.5338690280914307, "loss_nocot": 0.2633326053619385, "step": 2853 }, { "epoch": 2.6598322460391426, "grad_norm": 0.6440836447172429, "learning_rate": 2.519848118743528e-06, "loss": 0.7581, "step": 2854 }, { "epoch": 2.6598322460391426, "loss_cot": 0.4550742506980896, "loss_nocot": 0.288610577583313, "step": 2854 }, { "epoch": 2.6607642124883504, "grad_norm": 0.657250829820654, "learning_rate": 2.5129444252675182e-06, "loss": 0.7382, "step": 2855 }, { "epoch": 2.6607642124883504, "loss_cot": 0.5104023218154907, "loss_nocot": 0.2587828040122986, "step": 2855 }, { "epoch": 2.661696178937558, "grad_norm": 0.6204514237745111, "learning_rate": 2.5060407317915085e-06, "loss": 0.742, "step": 2856 }, { "epoch": 2.661696178937558, "loss_cot": 0.5490186214447021, "loss_nocot": 0.2990601062774658, "step": 2856 }, { "epoch": 2.662628145386766, "grad_norm": 0.663385678622522, "learning_rate": 2.499137038315499e-06, "loss": 0.7963, "step": 2857 }, { "epoch": 2.662628145386766, "loss_cot": 0.44513198733329773, "loss_nocot": 0.27280911803245544, "step": 2857 }, { "epoch": 2.6635601118359737, "grad_norm": 0.6645525644472695, "learning_rate": 2.492233344839489e-06, "loss": 0.7655, "step": 2858 }, { "epoch": 2.6635601118359737, "loss_cot": 0.47506436705589294, "loss_nocot": 0.26741212606430054, "step": 2858 }, { "epoch": 2.664492078285182, "grad_norm": 0.6593906771348591, "learning_rate": 2.48532965136348e-06, "loss": 0.7396, "step": 2859 }, { "epoch": 2.664492078285182, "loss_cot": 0.5302692651748657, "loss_nocot": 0.2310880422592163, "step": 2859 }, { "epoch": 2.6654240447343893, "grad_norm": 0.6230256156314191, "learning_rate": 2.47842595788747e-06, "loss": 0.761, "step": 2860 }, { "epoch": 2.6654240447343893, "loss_cot": 0.4939350187778473, "loss_nocot": 0.25144481658935547, "step": 2860 }, { "epoch": 2.6663560111835976, "grad_norm": 0.6038047246998479, "learning_rate": 2.4715222644114605e-06, "loss": 0.7332, "step": 2861 }, { "epoch": 2.6663560111835976, "loss_cot": 0.5407611727714539, "loss_nocot": 0.3694223165512085, "step": 2861 }, { "epoch": 2.6672879776328053, "grad_norm": 0.675270951066289, "learning_rate": 2.464618570935451e-06, "loss": 0.8291, "step": 2862 }, { "epoch": 2.6672879776328053, "loss_cot": 0.4571843147277832, "loss_nocot": 0.30294930934906006, "step": 2862 }, { "epoch": 2.668219944082013, "grad_norm": 0.6812155751344368, "learning_rate": 2.4577148774594407e-06, "loss": 0.7578, "step": 2863 }, { "epoch": 2.668219944082013, "loss_cot": 0.49942195415496826, "loss_nocot": 0.22231172025203705, "step": 2863 }, { "epoch": 2.669151910531221, "grad_norm": 0.635976748523477, "learning_rate": 2.4508111839834314e-06, "loss": 0.7072, "step": 2864 }, { "epoch": 2.669151910531221, "loss_cot": 0.5078970789909363, "loss_nocot": 0.22377340495586395, "step": 2864 }, { "epoch": 2.6700838769804287, "grad_norm": 0.6300053650746855, "learning_rate": 2.4439074905074217e-06, "loss": 0.7331, "step": 2865 }, { "epoch": 2.6700838769804287, "loss_cot": 0.4668547511100769, "loss_nocot": 0.17734000086784363, "step": 2865 }, { "epoch": 2.6710158434296365, "grad_norm": 0.6255174919068052, "learning_rate": 2.437003797031412e-06, "loss": 0.7147, "step": 2866 }, { "epoch": 2.6710158434296365, "loss_cot": 0.49511224031448364, "loss_nocot": 0.25842517614364624, "step": 2866 }, { "epoch": 2.6719478098788443, "grad_norm": 0.7101105555370747, "learning_rate": 2.4301001035554023e-06, "loss": 0.7818, "step": 2867 }, { "epoch": 2.6719478098788443, "loss_cot": 0.4782915711402893, "loss_nocot": 0.29928112030029297, "step": 2867 }, { "epoch": 2.672879776328052, "grad_norm": 0.6716652913048676, "learning_rate": 2.4231964100793927e-06, "loss": 0.7649, "step": 2868 }, { "epoch": 2.672879776328052, "loss_cot": 0.4808023273944855, "loss_nocot": 0.2216356098651886, "step": 2868 }, { "epoch": 2.67381174277726, "grad_norm": 0.6544721566298873, "learning_rate": 2.416292716603383e-06, "loss": 0.7338, "step": 2869 }, { "epoch": 2.67381174277726, "loss_cot": 0.4598936438560486, "loss_nocot": 0.24350017309188843, "step": 2869 }, { "epoch": 2.674743709226468, "grad_norm": 0.6688180225011913, "learning_rate": 2.4093890231273733e-06, "loss": 0.7412, "step": 2870 }, { "epoch": 2.674743709226468, "loss_cot": 0.5757302045822144, "loss_nocot": 0.28677281737327576, "step": 2870 }, { "epoch": 2.6756756756756754, "grad_norm": 0.6900900685419377, "learning_rate": 2.4024853296513636e-06, "loss": 0.7976, "step": 2871 }, { "epoch": 2.6756756756756754, "loss_cot": 0.48041513562202454, "loss_nocot": 0.1983412206172943, "step": 2871 }, { "epoch": 2.6766076421248837, "grad_norm": 0.624326211959655, "learning_rate": 2.395581636175354e-06, "loss": 0.7424, "step": 2872 }, { "epoch": 2.6766076421248837, "loss_cot": 0.47420886158943176, "loss_nocot": 0.21384671330451965, "step": 2872 }, { "epoch": 2.6775396085740915, "grad_norm": 0.5903634125982474, "learning_rate": 2.388677942699344e-06, "loss": 0.7083, "step": 2873 }, { "epoch": 2.6775396085740915, "loss_cot": 0.49244287610054016, "loss_nocot": 0.1828373521566391, "step": 2873 }, { "epoch": 2.6784715750232992, "grad_norm": 0.6215077957497951, "learning_rate": 2.381774249223335e-06, "loss": 0.7558, "step": 2874 }, { "epoch": 2.6784715750232992, "loss_cot": 0.5236537456512451, "loss_nocot": 0.1622547209262848, "step": 2874 }, { "epoch": 2.679403541472507, "grad_norm": 0.6474722577188287, "learning_rate": 2.3748705557473252e-06, "loss": 0.7751, "step": 2875 }, { "epoch": 2.679403541472507, "loss_cot": 0.49969059228897095, "loss_nocot": 0.21059581637382507, "step": 2875 }, { "epoch": 2.680335507921715, "grad_norm": 0.6519175088137981, "learning_rate": 2.367966862271315e-06, "loss": 0.7781, "step": 2876 }, { "epoch": 2.680335507921715, "loss_cot": 0.5254894495010376, "loss_nocot": 0.26705020666122437, "step": 2876 }, { "epoch": 2.6812674743709226, "grad_norm": 0.8352219443187596, "learning_rate": 2.3610631687953054e-06, "loss": 0.7271, "step": 2877 }, { "epoch": 2.6812674743709226, "loss_cot": 0.5179828405380249, "loss_nocot": 0.24240273237228394, "step": 2877 }, { "epoch": 2.6821994408201304, "grad_norm": 0.6362665598040962, "learning_rate": 2.3541594753192957e-06, "loss": 0.7535, "step": 2878 }, { "epoch": 2.6821994408201304, "loss_cot": 0.4726160764694214, "loss_nocot": 0.31518232822418213, "step": 2878 }, { "epoch": 2.683131407269338, "grad_norm": 0.6431870281574522, "learning_rate": 2.3472557818432865e-06, "loss": 0.7286, "step": 2879 }, { "epoch": 2.683131407269338, "loss_cot": 0.4714099168777466, "loss_nocot": 0.17551463842391968, "step": 2879 }, { "epoch": 2.684063373718546, "grad_norm": 0.6443942756507447, "learning_rate": 2.3403520883672768e-06, "loss": 0.7296, "step": 2880 }, { "epoch": 2.684063373718546, "loss_cot": 0.513245701789856, "loss_nocot": 0.3596438765525818, "step": 2880 }, { "epoch": 2.684995340167754, "grad_norm": 0.6908014427652004, "learning_rate": 2.333448394891267e-06, "loss": 0.775, "step": 2881 }, { "epoch": 2.684995340167754, "loss_cot": 0.5252711176872253, "loss_nocot": 0.21086333692073822, "step": 2881 }, { "epoch": 2.6859273066169616, "grad_norm": 0.6435666424579208, "learning_rate": 2.3265447014152574e-06, "loss": 0.7261, "step": 2882 }, { "epoch": 2.6859273066169616, "loss_cot": 0.4707205593585968, "loss_nocot": 0.2640058100223541, "step": 2882 }, { "epoch": 2.68685927306617, "grad_norm": 0.626820568855101, "learning_rate": 2.3196410079392477e-06, "loss": 0.7472, "step": 2883 }, { "epoch": 2.68685927306617, "loss_cot": 0.4977848529815674, "loss_nocot": 0.2134687304496765, "step": 2883 }, { "epoch": 2.6877912395153776, "grad_norm": 0.618076407967825, "learning_rate": 2.312737314463238e-06, "loss": 0.733, "step": 2884 }, { "epoch": 2.6877912395153776, "loss_cot": 0.5073052644729614, "loss_nocot": 0.29903000593185425, "step": 2884 }, { "epoch": 2.6887232059645854, "grad_norm": 0.6454204246678845, "learning_rate": 2.3058336209872283e-06, "loss": 0.7953, "step": 2885 }, { "epoch": 2.6887232059645854, "loss_cot": 0.4904238283634186, "loss_nocot": 0.22356534004211426, "step": 2885 }, { "epoch": 2.689655172413793, "grad_norm": 0.6719567826212631, "learning_rate": 2.2989299275112186e-06, "loss": 0.7867, "step": 2886 }, { "epoch": 2.689655172413793, "loss_cot": 0.5592176914215088, "loss_nocot": 0.30749279260635376, "step": 2886 }, { "epoch": 2.690587138863001, "grad_norm": 0.6453634942560351, "learning_rate": 2.292026234035209e-06, "loss": 0.7777, "step": 2887 }, { "epoch": 2.690587138863001, "loss_cot": 0.46952182054519653, "loss_nocot": 0.3112168610095978, "step": 2887 }, { "epoch": 2.6915191053122087, "grad_norm": 0.662560349639799, "learning_rate": 2.2851225405591993e-06, "loss": 0.7687, "step": 2888 }, { "epoch": 2.6915191053122087, "loss_cot": 0.5233153104782104, "loss_nocot": 0.21713438630104065, "step": 2888 }, { "epoch": 2.6924510717614165, "grad_norm": 0.646717777634727, "learning_rate": 2.27821884708319e-06, "loss": 0.7647, "step": 2889 }, { "epoch": 2.6924510717614165, "loss_cot": 0.49775347113609314, "loss_nocot": 0.2500652074813843, "step": 2889 }, { "epoch": 2.6933830382106243, "grad_norm": 0.6541883877983177, "learning_rate": 2.27131515360718e-06, "loss": 0.7509, "step": 2890 }, { "epoch": 2.6933830382106243, "loss_cot": 0.5430120825767517, "loss_nocot": 0.20687641203403473, "step": 2890 }, { "epoch": 2.694315004659832, "grad_norm": 0.66861676863383, "learning_rate": 2.26441146013117e-06, "loss": 0.7662, "step": 2891 }, { "epoch": 2.694315004659832, "loss_cot": 0.4750642776489258, "loss_nocot": 0.22947916388511658, "step": 2891 }, { "epoch": 2.6952469711090403, "grad_norm": 0.6600140469283681, "learning_rate": 2.2575077666551605e-06, "loss": 0.7667, "step": 2892 }, { "epoch": 2.6952469711090403, "loss_cot": 0.5062692761421204, "loss_nocot": 0.2697102725505829, "step": 2892 }, { "epoch": 2.6961789375582477, "grad_norm": 0.6363692786198156, "learning_rate": 2.250604073179151e-06, "loss": 0.7775, "step": 2893 }, { "epoch": 2.6961789375582477, "loss_cot": 0.5087729692459106, "loss_nocot": 0.20339608192443848, "step": 2893 }, { "epoch": 2.697110904007456, "grad_norm": 0.6133953823553779, "learning_rate": 2.2437003797031415e-06, "loss": 0.7391, "step": 2894 }, { "epoch": 2.697110904007456, "loss_cot": 0.4682990312576294, "loss_nocot": 0.18102037906646729, "step": 2894 }, { "epoch": 2.6980428704566637, "grad_norm": 0.6498422637131469, "learning_rate": 2.236796686227132e-06, "loss": 0.7315, "step": 2895 }, { "epoch": 2.6980428704566637, "loss_cot": 0.4627445936203003, "loss_nocot": 0.3419155776500702, "step": 2895 }, { "epoch": 2.6989748369058715, "grad_norm": 0.6649999118888148, "learning_rate": 2.229892992751122e-06, "loss": 0.7449, "step": 2896 }, { "epoch": 2.6989748369058715, "loss_cot": 0.481648325920105, "loss_nocot": 0.21773596107959747, "step": 2896 }, { "epoch": 2.6999068033550793, "grad_norm": 0.6503928769973784, "learning_rate": 2.2229892992751125e-06, "loss": 0.7328, "step": 2897 }, { "epoch": 2.6999068033550793, "loss_cot": 0.5226941704750061, "loss_nocot": 0.25113922357559204, "step": 2897 }, { "epoch": 2.700838769804287, "grad_norm": 0.6286039501896397, "learning_rate": 2.2160856057991028e-06, "loss": 0.7393, "step": 2898 }, { "epoch": 2.700838769804287, "loss_cot": 0.4889066517353058, "loss_nocot": 0.18466758728027344, "step": 2898 }, { "epoch": 2.701770736253495, "grad_norm": 0.7108384303483152, "learning_rate": 2.209181912323093e-06, "loss": 0.7865, "step": 2899 }, { "epoch": 2.701770736253495, "loss_cot": 0.5191621780395508, "loss_nocot": 0.2832063138484955, "step": 2899 }, { "epoch": 2.7027027027027026, "grad_norm": 0.6696196924759312, "learning_rate": 2.2022782188470834e-06, "loss": 0.783, "step": 2900 }, { "epoch": 2.7027027027027026, "loss_cot": 0.5084908604621887, "loss_nocot": 0.2839866876602173, "step": 2900 }, { "epoch": 2.7036346691519104, "grad_norm": 0.638940425040142, "learning_rate": 2.1953745253710737e-06, "loss": 0.7457, "step": 2901 }, { "epoch": 2.7036346691519104, "loss_cot": 0.43585216999053955, "loss_nocot": 0.22279150784015656, "step": 2901 }, { "epoch": 2.704566635601118, "grad_norm": 0.6591176270622489, "learning_rate": 2.188470831895064e-06, "loss": 0.7044, "step": 2902 }, { "epoch": 2.704566635601118, "loss_cot": 0.49915117025375366, "loss_nocot": 0.2909379005432129, "step": 2902 }, { "epoch": 2.7054986020503264, "grad_norm": 0.6576465380473241, "learning_rate": 2.1815671384190543e-06, "loss": 0.7513, "step": 2903 }, { "epoch": 2.7054986020503264, "loss_cot": 0.5346187949180603, "loss_nocot": 0.22935396432876587, "step": 2903 }, { "epoch": 2.706430568499534, "grad_norm": 0.7035432638921828, "learning_rate": 2.1746634449430446e-06, "loss": 0.7481, "step": 2904 }, { "epoch": 2.706430568499534, "loss_cot": 0.47802257537841797, "loss_nocot": 0.2028956115245819, "step": 2904 }, { "epoch": 2.707362534948742, "grad_norm": 0.6436850805175264, "learning_rate": 2.167759751467035e-06, "loss": 0.7367, "step": 2905 }, { "epoch": 2.707362534948742, "loss_cot": 0.5831903219223022, "loss_nocot": 0.23901525139808655, "step": 2905 }, { "epoch": 2.70829450139795, "grad_norm": 0.6478546441514256, "learning_rate": 2.1608560579910252e-06, "loss": 0.779, "step": 2906 }, { "epoch": 2.70829450139795, "loss_cot": 0.5141446590423584, "loss_nocot": 0.24819011986255646, "step": 2906 }, { "epoch": 2.7092264678471576, "grad_norm": 0.6526600864968808, "learning_rate": 2.1539523645150156e-06, "loss": 0.7537, "step": 2907 }, { "epoch": 2.7092264678471576, "loss_cot": 0.4647790789604187, "loss_nocot": 0.2538885772228241, "step": 2907 }, { "epoch": 2.7101584342963654, "grad_norm": 0.6533740104791846, "learning_rate": 2.147048671039006e-06, "loss": 0.7594, "step": 2908 }, { "epoch": 2.7101584342963654, "loss_cot": 0.5143550634384155, "loss_nocot": 0.32411330938339233, "step": 2908 }, { "epoch": 2.711090400745573, "grad_norm": 0.6650348933989012, "learning_rate": 2.1401449775629966e-06, "loss": 0.7378, "step": 2909 }, { "epoch": 2.711090400745573, "loss_cot": 0.5050765872001648, "loss_nocot": 0.25288406014442444, "step": 2909 }, { "epoch": 2.712022367194781, "grad_norm": 0.6844874983184213, "learning_rate": 2.133241284086987e-06, "loss": 0.8247, "step": 2910 }, { "epoch": 2.712022367194781, "loss_cot": 0.4825582504272461, "loss_nocot": 0.19958826899528503, "step": 2910 }, { "epoch": 2.7129543336439887, "grad_norm": 0.6240918872576953, "learning_rate": 2.1263375906109772e-06, "loss": 0.711, "step": 2911 }, { "epoch": 2.7129543336439887, "loss_cot": 0.44150853157043457, "loss_nocot": 0.2697165012359619, "step": 2911 }, { "epoch": 2.7138863000931965, "grad_norm": 0.672839711396376, "learning_rate": 2.1194338971349675e-06, "loss": 0.7704, "step": 2912 }, { "epoch": 2.7138863000931965, "loss_cot": 0.4978275001049042, "loss_nocot": 0.252410888671875, "step": 2912 }, { "epoch": 2.7148182665424043, "grad_norm": 0.6435551539901604, "learning_rate": 2.1125302036589574e-06, "loss": 0.792, "step": 2913 }, { "epoch": 2.7148182665424043, "loss_cot": 0.46452245116233826, "loss_nocot": 0.2698678970336914, "step": 2913 }, { "epoch": 2.7157502329916126, "grad_norm": 0.6804471105315265, "learning_rate": 2.105626510182948e-06, "loss": 0.7907, "step": 2914 }, { "epoch": 2.7157502329916126, "loss_cot": 0.48607659339904785, "loss_nocot": 0.3218913674354553, "step": 2914 }, { "epoch": 2.71668219944082, "grad_norm": 0.693685797598108, "learning_rate": 2.0987228167069384e-06, "loss": 0.755, "step": 2915 }, { "epoch": 2.71668219944082, "loss_cot": 0.49423083662986755, "loss_nocot": 0.28332096338272095, "step": 2915 }, { "epoch": 2.717614165890028, "grad_norm": 0.6722426546738992, "learning_rate": 2.0918191232309288e-06, "loss": 0.7678, "step": 2916 }, { "epoch": 2.717614165890028, "loss_cot": 0.4634557068347931, "loss_nocot": 0.2059815675020218, "step": 2916 }, { "epoch": 2.718546132339236, "grad_norm": 0.6221269201791504, "learning_rate": 2.084915429754919e-06, "loss": 0.697, "step": 2917 }, { "epoch": 2.718546132339236, "loss_cot": 0.45396238565444946, "loss_nocot": 0.3561326265335083, "step": 2917 }, { "epoch": 2.7194780987884437, "grad_norm": 0.7456718572675742, "learning_rate": 2.0780117362789094e-06, "loss": 0.8065, "step": 2918 }, { "epoch": 2.7194780987884437, "loss_cot": 0.46922144293785095, "loss_nocot": 0.21890029311180115, "step": 2918 }, { "epoch": 2.7204100652376515, "grad_norm": 0.6211233198428914, "learning_rate": 2.0711080428028997e-06, "loss": 0.7783, "step": 2919 }, { "epoch": 2.7204100652376515, "loss_cot": 0.4640340805053711, "loss_nocot": 0.2209141105413437, "step": 2919 }, { "epoch": 2.7213420316868593, "grad_norm": 0.6477998866411184, "learning_rate": 2.06420434932689e-06, "loss": 0.7464, "step": 2920 }, { "epoch": 2.7213420316868593, "loss_cot": 0.44785699248313904, "loss_nocot": 0.23992764949798584, "step": 2920 }, { "epoch": 2.722273998136067, "grad_norm": 0.7266270747559755, "learning_rate": 2.0573006558508803e-06, "loss": 0.7609, "step": 2921 }, { "epoch": 2.722273998136067, "loss_cot": 0.4527208209037781, "loss_nocot": 0.20996055006980896, "step": 2921 }, { "epoch": 2.723205964585275, "grad_norm": 0.6737706334322443, "learning_rate": 2.0503969623748706e-06, "loss": 0.7523, "step": 2922 }, { "epoch": 2.723205964585275, "loss_cot": 0.4359795153141022, "loss_nocot": 0.2285023331642151, "step": 2922 }, { "epoch": 2.7241379310344827, "grad_norm": 0.622008633961422, "learning_rate": 2.043493268898861e-06, "loss": 0.7039, "step": 2923 }, { "epoch": 2.7241379310344827, "loss_cot": 0.5038482546806335, "loss_nocot": 0.42641177773475647, "step": 2923 }, { "epoch": 2.7250698974836904, "grad_norm": 0.7301787208181124, "learning_rate": 2.0365895754228517e-06, "loss": 0.8618, "step": 2924 }, { "epoch": 2.7250698974836904, "loss_cot": 0.48952245712280273, "loss_nocot": 0.2398836612701416, "step": 2924 }, { "epoch": 2.7260018639328987, "grad_norm": 0.6519530823797812, "learning_rate": 2.029685881946842e-06, "loss": 0.7333, "step": 2925 }, { "epoch": 2.7260018639328987, "loss_cot": 0.45107436180114746, "loss_nocot": 0.27454251050949097, "step": 2925 }, { "epoch": 2.726933830382106, "grad_norm": 0.6481104494765454, "learning_rate": 2.0227821884708323e-06, "loss": 0.7554, "step": 2926 }, { "epoch": 2.726933830382106, "loss_cot": 0.5105250477790833, "loss_nocot": 0.31837451457977295, "step": 2926 }, { "epoch": 2.7278657968313142, "grad_norm": 0.6426246180500597, "learning_rate": 2.015878494994822e-06, "loss": 0.789, "step": 2927 }, { "epoch": 2.7278657968313142, "loss_cot": 0.4370567500591278, "loss_nocot": 0.2714376449584961, "step": 2927 }, { "epoch": 2.728797763280522, "grad_norm": 0.6274003309858001, "learning_rate": 2.0089748015188125e-06, "loss": 0.7012, "step": 2928 }, { "epoch": 2.728797763280522, "loss_cot": 0.4924056828022003, "loss_nocot": 0.236796036362648, "step": 2928 }, { "epoch": 2.72972972972973, "grad_norm": 0.6547061694835503, "learning_rate": 2.002071108042803e-06, "loss": 0.7509, "step": 2929 }, { "epoch": 2.72972972972973, "loss_cot": 0.46351441740989685, "loss_nocot": 0.2213505506515503, "step": 2929 }, { "epoch": 2.7306616961789376, "grad_norm": 0.6550959656873343, "learning_rate": 1.9951674145667935e-06, "loss": 0.7511, "step": 2930 }, { "epoch": 2.7306616961789376, "loss_cot": 0.44214388728141785, "loss_nocot": 0.2837522029876709, "step": 2930 }, { "epoch": 2.7315936626281454, "grad_norm": 0.6385887775215676, "learning_rate": 1.988263721090784e-06, "loss": 0.7188, "step": 2931 }, { "epoch": 2.7315936626281454, "loss_cot": 0.5410254001617432, "loss_nocot": 0.20123040676116943, "step": 2931 }, { "epoch": 2.732525629077353, "grad_norm": 0.6721918683362452, "learning_rate": 1.981360027614774e-06, "loss": 0.7599, "step": 2932 }, { "epoch": 2.732525629077353, "loss_cot": 0.49296286702156067, "loss_nocot": 0.4037154018878937, "step": 2932 }, { "epoch": 2.733457595526561, "grad_norm": 0.6823788293394275, "learning_rate": 1.9744563341387644e-06, "loss": 0.7748, "step": 2933 }, { "epoch": 2.733457595526561, "loss_cot": 0.473937451839447, "loss_nocot": 0.270061731338501, "step": 2933 }, { "epoch": 2.7343895619757688, "grad_norm": 0.6969908654895733, "learning_rate": 1.9675526406627547e-06, "loss": 0.7442, "step": 2934 }, { "epoch": 2.7343895619757688, "loss_cot": 0.46786704659461975, "loss_nocot": 0.22395378351211548, "step": 2934 }, { "epoch": 2.7353215284249766, "grad_norm": 0.6070753141446914, "learning_rate": 1.960648947186745e-06, "loss": 0.6989, "step": 2935 }, { "epoch": 2.7353215284249766, "loss_cot": 0.4945109486579895, "loss_nocot": 0.2852930724620819, "step": 2935 }, { "epoch": 2.736253494874185, "grad_norm": 0.7019001677366994, "learning_rate": 1.9537452537107354e-06, "loss": 0.7763, "step": 2936 }, { "epoch": 2.736253494874185, "loss_cot": 0.5170217752456665, "loss_nocot": 0.2617419362068176, "step": 2936 }, { "epoch": 2.737185461323392, "grad_norm": 0.6357439118459358, "learning_rate": 1.9468415602347257e-06, "loss": 0.796, "step": 2937 }, { "epoch": 2.737185461323392, "loss_cot": 0.459383487701416, "loss_nocot": 0.251958966255188, "step": 2937 }, { "epoch": 2.7381174277726004, "grad_norm": 0.618310296221273, "learning_rate": 1.939937866758716e-06, "loss": 0.7214, "step": 2938 }, { "epoch": 2.7381174277726004, "loss_cot": 0.48561322689056396, "loss_nocot": 0.23928827047348022, "step": 2938 }, { "epoch": 2.739049394221808, "grad_norm": 0.6372119071131465, "learning_rate": 1.9330341732827067e-06, "loss": 0.7293, "step": 2939 }, { "epoch": 2.739049394221808, "loss_cot": 0.4930487871170044, "loss_nocot": 0.1884090006351471, "step": 2939 }, { "epoch": 2.739981360671016, "grad_norm": 0.6204710840066129, "learning_rate": 1.926130479806697e-06, "loss": 0.7592, "step": 2940 }, { "epoch": 2.739981360671016, "loss_cot": 0.46389126777648926, "loss_nocot": 0.22062590718269348, "step": 2940 }, { "epoch": 2.7409133271202237, "grad_norm": 0.6427211842321432, "learning_rate": 1.919226786330687e-06, "loss": 0.7587, "step": 2941 }, { "epoch": 2.7409133271202237, "loss_cot": 0.525266170501709, "loss_nocot": 0.23078183829784393, "step": 2941 }, { "epoch": 2.7418452935694315, "grad_norm": 0.5887074130527887, "learning_rate": 1.9123230928546772e-06, "loss": 0.735, "step": 2942 }, { "epoch": 2.7418452935694315, "loss_cot": 0.46976011991500854, "loss_nocot": 0.22258351743221283, "step": 2942 }, { "epoch": 2.7427772600186393, "grad_norm": 0.6545313085553652, "learning_rate": 1.9054193993786677e-06, "loss": 0.7314, "step": 2943 }, { "epoch": 2.7427772600186393, "loss_cot": 0.47490987181663513, "loss_nocot": 0.24515938758850098, "step": 2943 }, { "epoch": 2.743709226467847, "grad_norm": 0.6547666470428887, "learning_rate": 1.8985157059026583e-06, "loss": 0.7685, "step": 2944 }, { "epoch": 2.743709226467847, "loss_cot": 0.4814486503601074, "loss_nocot": 0.27694055438041687, "step": 2944 }, { "epoch": 2.744641192917055, "grad_norm": 0.6449836804043472, "learning_rate": 1.8916120124266486e-06, "loss": 0.7709, "step": 2945 }, { "epoch": 2.744641192917055, "loss_cot": 0.5086702704429626, "loss_nocot": 0.23002514243125916, "step": 2945 }, { "epoch": 2.7455731593662627, "grad_norm": 0.6482834843674071, "learning_rate": 1.8847083189506389e-06, "loss": 0.7749, "step": 2946 }, { "epoch": 2.7455731593662627, "loss_cot": 0.5285326242446899, "loss_nocot": 0.26260486245155334, "step": 2946 }, { "epoch": 2.746505125815471, "grad_norm": 0.6283404265075223, "learning_rate": 1.877804625474629e-06, "loss": 0.7326, "step": 2947 }, { "epoch": 2.746505125815471, "loss_cot": 0.5211468935012817, "loss_nocot": 0.22559605538845062, "step": 2947 }, { "epoch": 2.7474370922646782, "grad_norm": 0.6304338608622937, "learning_rate": 1.8709009319986193e-06, "loss": 0.7369, "step": 2948 }, { "epoch": 2.7474370922646782, "loss_cot": 0.5115742087364197, "loss_nocot": 0.4321049153804779, "step": 2948 }, { "epoch": 2.7483690587138865, "grad_norm": 0.6802001061182642, "learning_rate": 1.8639972385226098e-06, "loss": 0.8395, "step": 2949 }, { "epoch": 2.7483690587138865, "loss_cot": 0.515802264213562, "loss_nocot": 0.2551132142543793, "step": 2949 }, { "epoch": 2.7493010251630943, "grad_norm": 0.6355177729624888, "learning_rate": 1.8570935450466001e-06, "loss": 0.758, "step": 2950 }, { "epoch": 2.7493010251630943, "loss_cot": 0.42669805884361267, "loss_nocot": 0.24423851072788239, "step": 2950 }, { "epoch": 2.750232991612302, "grad_norm": 0.658641006870161, "learning_rate": 1.8501898515705904e-06, "loss": 0.7392, "step": 2951 }, { "epoch": 2.750232991612302, "loss_cot": 0.4553489685058594, "loss_nocot": 0.24266266822814941, "step": 2951 }, { "epoch": 2.75116495806151, "grad_norm": 0.6031357419613218, "learning_rate": 1.8432861580945807e-06, "loss": 0.6888, "step": 2952 }, { "epoch": 2.75116495806151, "loss_cot": 0.54936683177948, "loss_nocot": 0.29959791898727417, "step": 2952 }, { "epoch": 2.7520969245107176, "grad_norm": 0.660749437648653, "learning_rate": 1.836382464618571e-06, "loss": 0.7753, "step": 2953 }, { "epoch": 2.7520969245107176, "loss_cot": 0.47474241256713867, "loss_nocot": 0.26795077323913574, "step": 2953 }, { "epoch": 2.7530288909599254, "grad_norm": 0.6470857282582961, "learning_rate": 1.8294787711425613e-06, "loss": 0.751, "step": 2954 }, { "epoch": 2.7530288909599254, "loss_cot": 0.45862483978271484, "loss_nocot": 0.43350428342819214, "step": 2954 }, { "epoch": 2.753960857409133, "grad_norm": 0.7588716045089772, "learning_rate": 1.8225750776665519e-06, "loss": 0.7775, "step": 2955 }, { "epoch": 2.753960857409133, "loss_cot": 0.45509007573127747, "loss_nocot": 0.30316615104675293, "step": 2955 }, { "epoch": 2.754892823858341, "grad_norm": 0.6450658797618208, "learning_rate": 1.8156713841905422e-06, "loss": 0.7589, "step": 2956 }, { "epoch": 2.754892823858341, "loss_cot": 0.47183531522750854, "loss_nocot": 0.2677963376045227, "step": 2956 }, { "epoch": 2.755824790307549, "grad_norm": 0.6735244203318912, "learning_rate": 1.8087676907145325e-06, "loss": 0.7546, "step": 2957 }, { "epoch": 2.755824790307549, "loss_cot": 0.48916095495224, "loss_nocot": 0.26224151253700256, "step": 2957 }, { "epoch": 2.756756756756757, "grad_norm": 0.6239640183939467, "learning_rate": 1.8018639972385226e-06, "loss": 0.7388, "step": 2958 }, { "epoch": 2.756756756756757, "loss_cot": 0.5104418396949768, "loss_nocot": 0.23655954003334045, "step": 2958 }, { "epoch": 2.7576887232059644, "grad_norm": 0.6846401545810084, "learning_rate": 1.7949603037625129e-06, "loss": 0.8055, "step": 2959 }, { "epoch": 2.7576887232059644, "loss_cot": 0.4646468758583069, "loss_nocot": 0.263465017080307, "step": 2959 }, { "epoch": 2.7586206896551726, "grad_norm": 0.6740564598149231, "learning_rate": 1.7880566102865034e-06, "loss": 0.7419, "step": 2960 }, { "epoch": 2.7586206896551726, "loss_cot": 0.4866594672203064, "loss_nocot": 0.19702909886837006, "step": 2960 }, { "epoch": 2.7595526561043804, "grad_norm": 0.6155956504476469, "learning_rate": 1.7811529168104937e-06, "loss": 0.7638, "step": 2961 }, { "epoch": 2.7595526561043804, "loss_cot": 0.5435211658477783, "loss_nocot": 0.34651413559913635, "step": 2961 }, { "epoch": 2.760484622553588, "grad_norm": 0.6680063094846972, "learning_rate": 1.774249223334484e-06, "loss": 0.7807, "step": 2962 }, { "epoch": 2.760484622553588, "loss_cot": 0.47326532006263733, "loss_nocot": 0.2267780750989914, "step": 2962 }, { "epoch": 2.761416589002796, "grad_norm": 0.6573202755537076, "learning_rate": 1.7673455298584743e-06, "loss": 0.775, "step": 2963 }, { "epoch": 2.761416589002796, "loss_cot": 0.4977615475654602, "loss_nocot": 0.2298295944929123, "step": 2963 }, { "epoch": 2.7623485554520038, "grad_norm": 0.5912878730061162, "learning_rate": 1.7604418363824646e-06, "loss": 0.6797, "step": 2964 }, { "epoch": 2.7623485554520038, "loss_cot": 0.5141921043395996, "loss_nocot": 0.30148762464523315, "step": 2964 }, { "epoch": 2.7632805219012115, "grad_norm": 0.6768403422368883, "learning_rate": 1.7535381429064552e-06, "loss": 0.753, "step": 2965 }, { "epoch": 2.7632805219012115, "loss_cot": 0.5423554182052612, "loss_nocot": 0.2522960901260376, "step": 2965 }, { "epoch": 2.7642124883504193, "grad_norm": 0.6399653459382855, "learning_rate": 1.7466344494304455e-06, "loss": 0.7698, "step": 2966 }, { "epoch": 2.7642124883504193, "loss_cot": 0.47814804315567017, "loss_nocot": 0.18165887892246246, "step": 2966 }, { "epoch": 2.765144454799627, "grad_norm": 0.6007161325924035, "learning_rate": 1.7397307559544358e-06, "loss": 0.7009, "step": 2967 }, { "epoch": 2.765144454799627, "loss_cot": 0.537105917930603, "loss_nocot": 0.2503146231174469, "step": 2967 }, { "epoch": 2.766076421248835, "grad_norm": 0.6454024737950325, "learning_rate": 1.732827062478426e-06, "loss": 0.778, "step": 2968 }, { "epoch": 2.766076421248835, "loss_cot": 0.4827781319618225, "loss_nocot": 0.21856465935707092, "step": 2968 }, { "epoch": 2.767008387698043, "grad_norm": 0.6277584251264359, "learning_rate": 1.7259233690024164e-06, "loss": 0.7641, "step": 2969 }, { "epoch": 2.767008387698043, "loss_cot": 0.4927179515361786, "loss_nocot": 0.1924397349357605, "step": 2969 }, { "epoch": 2.7679403541472505, "grad_norm": 0.6907925902984536, "learning_rate": 1.719019675526407e-06, "loss": 0.7787, "step": 2970 }, { "epoch": 2.7679403541472505, "loss_cot": 0.5073033571243286, "loss_nocot": 0.2363838255405426, "step": 2970 }, { "epoch": 2.7688723205964587, "grad_norm": 0.653232002348978, "learning_rate": 1.7121159820503972e-06, "loss": 0.735, "step": 2971 }, { "epoch": 2.7688723205964587, "loss_cot": 0.41692841053009033, "loss_nocot": 0.20604589581489563, "step": 2971 }, { "epoch": 2.7698042870456665, "grad_norm": 0.6757459812394013, "learning_rate": 1.7052122885743873e-06, "loss": 0.8017, "step": 2972 }, { "epoch": 2.7698042870456665, "loss_cot": 0.541267454624176, "loss_nocot": 0.21800753474235535, "step": 2972 }, { "epoch": 2.7707362534948743, "grad_norm": 0.6357708227662333, "learning_rate": 1.6983085950983776e-06, "loss": 0.7284, "step": 2973 }, { "epoch": 2.7707362534948743, "loss_cot": 0.4650079011917114, "loss_nocot": 0.20913735032081604, "step": 2973 }, { "epoch": 2.771668219944082, "grad_norm": 0.6946328680143613, "learning_rate": 1.691404901622368e-06, "loss": 0.7922, "step": 2974 }, { "epoch": 2.771668219944082, "loss_cot": 0.43283987045288086, "loss_nocot": 0.3085944950580597, "step": 2974 }, { "epoch": 2.77260018639329, "grad_norm": 0.7052387228062006, "learning_rate": 1.6845012081463585e-06, "loss": 0.7845, "step": 2975 }, { "epoch": 2.77260018639329, "loss_cot": 0.5421237945556641, "loss_nocot": 0.24752551317214966, "step": 2975 }, { "epoch": 2.7735321528424977, "grad_norm": 0.6906855715850534, "learning_rate": 1.6775975146703488e-06, "loss": 0.7393, "step": 2976 }, { "epoch": 2.7735321528424977, "loss_cot": 0.5283225774765015, "loss_nocot": 0.2679048478603363, "step": 2976 }, { "epoch": 2.7744641192917054, "grad_norm": 0.635521446490198, "learning_rate": 1.670693821194339e-06, "loss": 0.721, "step": 2977 }, { "epoch": 2.7744641192917054, "loss_cot": 0.47028711438179016, "loss_nocot": 0.31170889735221863, "step": 2977 }, { "epoch": 2.7753960857409132, "grad_norm": 0.6381374256704158, "learning_rate": 1.6637901277183294e-06, "loss": 0.738, "step": 2978 }, { "epoch": 2.7753960857409132, "loss_cot": 0.4664146602153778, "loss_nocot": 0.5083022713661194, "step": 2978 }, { "epoch": 2.776328052190121, "grad_norm": 0.7088309393053556, "learning_rate": 1.6568864342423197e-06, "loss": 0.8025, "step": 2979 }, { "epoch": 2.776328052190121, "loss_cot": 0.4831816554069519, "loss_nocot": 0.30806678533554077, "step": 2979 }, { "epoch": 2.7772600186393293, "grad_norm": 0.7083954582968277, "learning_rate": 1.6499827407663102e-06, "loss": 0.7551, "step": 2980 }, { "epoch": 2.7772600186393293, "loss_cot": 0.5181349515914917, "loss_nocot": 0.34913504123687744, "step": 2980 }, { "epoch": 2.7781919850885366, "grad_norm": 0.6897368777566898, "learning_rate": 1.6430790472903005e-06, "loss": 0.7561, "step": 2981 }, { "epoch": 2.7781919850885366, "loss_cot": 0.660175621509552, "loss_nocot": 0.20337896049022675, "step": 2981 }, { "epoch": 2.779123951537745, "grad_norm": 0.6032742639471055, "learning_rate": 1.6361753538142908e-06, "loss": 0.7649, "step": 2982 }, { "epoch": 2.779123951537745, "loss_cot": 0.46905702352523804, "loss_nocot": 0.26420214772224426, "step": 2982 }, { "epoch": 2.7800559179869526, "grad_norm": 0.689642705612544, "learning_rate": 1.629271660338281e-06, "loss": 0.7834, "step": 2983 }, { "epoch": 2.7800559179869526, "loss_cot": 0.5206334590911865, "loss_nocot": 0.2883966565132141, "step": 2983 }, { "epoch": 2.7809878844361604, "grad_norm": 0.6911479968233725, "learning_rate": 1.6223679668622713e-06, "loss": 0.8207, "step": 2984 }, { "epoch": 2.7809878844361604, "loss_cot": 0.4501945376396179, "loss_nocot": 0.28910744190216064, "step": 2984 }, { "epoch": 2.781919850885368, "grad_norm": 0.7178333642647701, "learning_rate": 1.615464273386262e-06, "loss": 0.7854, "step": 2985 }, { "epoch": 2.781919850885368, "loss_cot": 0.5324463844299316, "loss_nocot": 0.2604440152645111, "step": 2985 }, { "epoch": 2.782851817334576, "grad_norm": 0.6699592902271596, "learning_rate": 1.608560579910252e-06, "loss": 0.77, "step": 2986 }, { "epoch": 2.782851817334576, "loss_cot": 0.49733638763427734, "loss_nocot": 0.16774266958236694, "step": 2986 }, { "epoch": 2.7837837837837838, "grad_norm": 0.6365038035404927, "learning_rate": 1.6016568864342424e-06, "loss": 0.7446, "step": 2987 }, { "epoch": 2.7837837837837838, "loss_cot": 0.5207290053367615, "loss_nocot": 0.37474697828292847, "step": 2987 }, { "epoch": 2.7847157502329916, "grad_norm": 0.6738880497126515, "learning_rate": 1.5947531929582327e-06, "loss": 0.8002, "step": 2988 }, { "epoch": 2.7847157502329916, "loss_cot": 0.4376632869243622, "loss_nocot": 0.2817623019218445, "step": 2988 }, { "epoch": 2.7856477166821993, "grad_norm": 0.6709571495031262, "learning_rate": 1.587849499482223e-06, "loss": 0.7914, "step": 2989 }, { "epoch": 2.7856477166821993, "loss_cot": 0.5911984443664551, "loss_nocot": 0.2915102243423462, "step": 2989 }, { "epoch": 2.786579683131407, "grad_norm": 0.8178612184286972, "learning_rate": 1.5809458060062135e-06, "loss": 0.7908, "step": 2990 }, { "epoch": 2.786579683131407, "loss_cot": 0.45223426818847656, "loss_nocot": 0.2625669240951538, "step": 2990 }, { "epoch": 2.7875116495806154, "grad_norm": 0.6555946436467841, "learning_rate": 1.5740421125302038e-06, "loss": 0.723, "step": 2991 }, { "epoch": 2.7875116495806154, "loss_cot": 0.4453498423099518, "loss_nocot": 0.2096560299396515, "step": 2991 }, { "epoch": 2.7884436160298227, "grad_norm": 0.6859677649302205, "learning_rate": 1.5671384190541941e-06, "loss": 0.7257, "step": 2992 }, { "epoch": 2.7884436160298227, "loss_cot": 0.49533748626708984, "loss_nocot": 0.20324981212615967, "step": 2992 }, { "epoch": 2.789375582479031, "grad_norm": 0.6172268351867994, "learning_rate": 1.5602347255781845e-06, "loss": 0.7413, "step": 2993 }, { "epoch": 2.789375582479031, "loss_cot": 0.46722277998924255, "loss_nocot": 0.22247853875160217, "step": 2993 }, { "epoch": 2.7903075489282387, "grad_norm": 0.6321140721561548, "learning_rate": 1.5533310321021748e-06, "loss": 0.7608, "step": 2994 }, { "epoch": 2.7903075489282387, "loss_cot": 0.4635564088821411, "loss_nocot": 0.26689279079437256, "step": 2994 }, { "epoch": 2.7912395153774465, "grad_norm": 0.6734795788694037, "learning_rate": 1.5464273386261653e-06, "loss": 0.7752, "step": 2995 }, { "epoch": 2.7912395153774465, "loss_cot": 0.5188173055648804, "loss_nocot": 0.21736474335193634, "step": 2995 }, { "epoch": 2.7921714818266543, "grad_norm": 0.6182855526720653, "learning_rate": 1.5395236451501556e-06, "loss": 0.7431, "step": 2996 }, { "epoch": 2.7921714818266543, "loss_cot": 0.46359723806381226, "loss_nocot": 0.24321752786636353, "step": 2996 }, { "epoch": 2.793103448275862, "grad_norm": 0.6125540138888491, "learning_rate": 1.5326199516741457e-06, "loss": 0.7133, "step": 2997 }, { "epoch": 2.793103448275862, "loss_cot": 0.4844985902309418, "loss_nocot": 0.20965875685214996, "step": 2997 }, { "epoch": 2.79403541472507, "grad_norm": 0.5970907876371818, "learning_rate": 1.525716258198136e-06, "loss": 0.7217, "step": 2998 }, { "epoch": 2.79403541472507, "loss_cot": 0.5001505613327026, "loss_nocot": 0.25695833563804626, "step": 2998 }, { "epoch": 2.7949673811742777, "grad_norm": 0.668318460394604, "learning_rate": 1.5188125647221263e-06, "loss": 0.756, "step": 2999 }, { "epoch": 2.7949673811742777, "loss_cot": 0.45363283157348633, "loss_nocot": 0.21518078446388245, "step": 2999 }, { "epoch": 2.7958993476234855, "grad_norm": 0.6412308317950234, "learning_rate": 1.5119088712461168e-06, "loss": 0.7089, "step": 3000 }, { "epoch": 2.7958993476234855, "loss_cot": 0.6343899965286255, "loss_nocot": 0.4525456130504608, "step": 3000 }, { "epoch": 2.7968313140726933, "grad_norm": 0.6738029870705502, "learning_rate": 1.5050051777701071e-06, "loss": 0.7869, "step": 3001 }, { "epoch": 2.7968313140726933, "loss_cot": 0.5729362964630127, "loss_nocot": 0.27026641368865967, "step": 3001 }, { "epoch": 2.7977632805219015, "grad_norm": 0.6956990630050965, "learning_rate": 1.4981014842940974e-06, "loss": 0.7766, "step": 3002 }, { "epoch": 2.7977632805219015, "loss_cot": 0.5144612789154053, "loss_nocot": 0.21943509578704834, "step": 3002 }, { "epoch": 2.798695246971109, "grad_norm": 0.5920585948727067, "learning_rate": 1.4911977908180878e-06, "loss": 0.6786, "step": 3003 }, { "epoch": 2.798695246971109, "loss_cot": 0.48698699474334717, "loss_nocot": 0.16655460000038147, "step": 3003 }, { "epoch": 2.799627213420317, "grad_norm": 0.6508610348496519, "learning_rate": 1.484294097342078e-06, "loss": 0.7666, "step": 3004 }, { "epoch": 2.799627213420317, "loss_cot": 0.5167057514190674, "loss_nocot": 0.23497048020362854, "step": 3004 }, { "epoch": 2.800559179869525, "grad_norm": 0.5987610475040899, "learning_rate": 1.4773904038660686e-06, "loss": 0.7434, "step": 3005 }, { "epoch": 2.800559179869525, "loss_cot": 0.5275509357452393, "loss_nocot": 0.2221052050590515, "step": 3005 }, { "epoch": 2.8014911463187326, "grad_norm": 0.639523696709783, "learning_rate": 1.470486710390059e-06, "loss": 0.7897, "step": 3006 }, { "epoch": 2.8014911463187326, "loss_cot": 0.5580320954322815, "loss_nocot": 0.2464390993118286, "step": 3006 }, { "epoch": 2.8024231127679404, "grad_norm": 0.6495021938851581, "learning_rate": 1.4635830169140492e-06, "loss": 0.7881, "step": 3007 }, { "epoch": 2.8024231127679404, "loss_cot": 0.4755408763885498, "loss_nocot": 0.19449546933174133, "step": 3007 }, { "epoch": 2.803355079217148, "grad_norm": 0.6339969649588019, "learning_rate": 1.4566793234380395e-06, "loss": 0.7386, "step": 3008 }, { "epoch": 2.803355079217148, "loss_cot": 0.45797842741012573, "loss_nocot": 0.23743285238742828, "step": 3008 }, { "epoch": 2.804287045666356, "grad_norm": 0.6137524952072848, "learning_rate": 1.4497756299620296e-06, "loss": 0.6876, "step": 3009 }, { "epoch": 2.804287045666356, "loss_cot": 0.46704205870628357, "loss_nocot": 0.2793141007423401, "step": 3009 }, { "epoch": 2.805219012115564, "grad_norm": 0.6492523472791758, "learning_rate": 1.4428719364860203e-06, "loss": 0.7595, "step": 3010 }, { "epoch": 2.805219012115564, "loss_cot": 0.4901541769504547, "loss_nocot": 0.26558586955070496, "step": 3010 }, { "epoch": 2.8061509785647716, "grad_norm": 0.7145665182446924, "learning_rate": 1.4359682430100104e-06, "loss": 0.7645, "step": 3011 }, { "epoch": 2.8061509785647716, "loss_cot": 0.45066022872924805, "loss_nocot": 0.25313302874565125, "step": 3011 }, { "epoch": 2.8070829450139794, "grad_norm": 0.6496879649927917, "learning_rate": 1.4290645495340007e-06, "loss": 0.7483, "step": 3012 }, { "epoch": 2.8070829450139794, "loss_cot": 0.4914502501487732, "loss_nocot": 0.217585951089859, "step": 3012 }, { "epoch": 2.8080149114631876, "grad_norm": 0.653611185490453, "learning_rate": 1.422160856057991e-06, "loss": 0.7619, "step": 3013 }, { "epoch": 2.8080149114631876, "loss_cot": 0.48312294483184814, "loss_nocot": 0.2500483989715576, "step": 3013 }, { "epoch": 2.808946877912395, "grad_norm": 0.6482216769197016, "learning_rate": 1.4152571625819814e-06, "loss": 0.7858, "step": 3014 }, { "epoch": 2.808946877912395, "loss_cot": 0.4661865234375, "loss_nocot": 0.2149500846862793, "step": 3014 }, { "epoch": 2.809878844361603, "grad_norm": 0.6016235372443851, "learning_rate": 1.4083534691059719e-06, "loss": 0.7145, "step": 3015 }, { "epoch": 2.809878844361603, "loss_cot": 0.49411487579345703, "loss_nocot": 0.3060298264026642, "step": 3015 }, { "epoch": 2.810810810810811, "grad_norm": 0.7010408609652817, "learning_rate": 1.4014497756299622e-06, "loss": 0.7949, "step": 3016 }, { "epoch": 2.810810810810811, "loss_cot": 0.475696861743927, "loss_nocot": 0.20252200961112976, "step": 3016 }, { "epoch": 2.8117427772600188, "grad_norm": 0.6238587285520684, "learning_rate": 1.3945460821539525e-06, "loss": 0.6927, "step": 3017 }, { "epoch": 2.8117427772600188, "loss_cot": 0.47082945704460144, "loss_nocot": 0.31241846084594727, "step": 3017 }, { "epoch": 2.8126747437092265, "grad_norm": 0.7053334660068196, "learning_rate": 1.3876423886779428e-06, "loss": 0.8265, "step": 3018 }, { "epoch": 2.8126747437092265, "loss_cot": 0.46643829345703125, "loss_nocot": 0.17433597147464752, "step": 3018 }, { "epoch": 2.8136067101584343, "grad_norm": 0.6236780690951823, "learning_rate": 1.3807386952019331e-06, "loss": 0.7278, "step": 3019 }, { "epoch": 2.8136067101584343, "loss_cot": 0.4998742938041687, "loss_nocot": 0.21198876202106476, "step": 3019 }, { "epoch": 2.814538676607642, "grad_norm": 0.6342400107341892, "learning_rate": 1.3738350017259236e-06, "loss": 0.7168, "step": 3020 }, { "epoch": 2.814538676607642, "loss_cot": 0.4793511629104614, "loss_nocot": 0.2438870370388031, "step": 3020 }, { "epoch": 2.81547064305685, "grad_norm": 0.642876564199816, "learning_rate": 1.366931308249914e-06, "loss": 0.7742, "step": 3021 }, { "epoch": 2.81547064305685, "loss_cot": 0.48794594407081604, "loss_nocot": 0.30248722434043884, "step": 3021 }, { "epoch": 2.8164026095060577, "grad_norm": 0.6473450576082387, "learning_rate": 1.3600276147739043e-06, "loss": 0.7863, "step": 3022 }, { "epoch": 2.8164026095060577, "loss_cot": 0.5346725583076477, "loss_nocot": 0.2209559977054596, "step": 3022 }, { "epoch": 2.8173345759552655, "grad_norm": 0.6202900258743466, "learning_rate": 1.3531239212978944e-06, "loss": 0.7228, "step": 3023 }, { "epoch": 2.8173345759552655, "loss_cot": 0.45522430539131165, "loss_nocot": 0.4077697992324829, "step": 3023 }, { "epoch": 2.8182665424044733, "grad_norm": 0.7088220912969216, "learning_rate": 1.3462202278218847e-06, "loss": 0.7936, "step": 3024 }, { "epoch": 2.8182665424044733, "loss_cot": 0.5175012350082397, "loss_nocot": 0.2376996874809265, "step": 3024 }, { "epoch": 2.819198508853681, "grad_norm": 0.6475850592224218, "learning_rate": 1.3393165343458752e-06, "loss": 0.7551, "step": 3025 }, { "epoch": 2.819198508853681, "loss_cot": 0.520014762878418, "loss_nocot": 0.2652401626110077, "step": 3025 }, { "epoch": 2.8201304753028893, "grad_norm": 0.6556472752804003, "learning_rate": 1.3324128408698655e-06, "loss": 0.7809, "step": 3026 }, { "epoch": 2.8201304753028893, "loss_cot": 0.45600464940071106, "loss_nocot": 0.19500720500946045, "step": 3026 }, { "epoch": 2.821062441752097, "grad_norm": 0.6449302267716853, "learning_rate": 1.3255091473938558e-06, "loss": 0.726, "step": 3027 }, { "epoch": 2.821062441752097, "loss_cot": 0.510341227054596, "loss_nocot": 0.324518620967865, "step": 3027 }, { "epoch": 2.821994408201305, "grad_norm": 0.694010810577678, "learning_rate": 1.3186054539178461e-06, "loss": 0.8409, "step": 3028 }, { "epoch": 2.821994408201305, "loss_cot": 0.4841807782649994, "loss_nocot": 0.25653302669525146, "step": 3028 }, { "epoch": 2.8229263746505127, "grad_norm": 0.6601408445265362, "learning_rate": 1.3117017604418364e-06, "loss": 0.7527, "step": 3029 }, { "epoch": 2.8229263746505127, "loss_cot": 0.5065640807151794, "loss_nocot": 0.23088660836219788, "step": 3029 }, { "epoch": 2.8238583410997204, "grad_norm": 0.7065948776003143, "learning_rate": 1.304798066965827e-06, "loss": 0.7259, "step": 3030 }, { "epoch": 2.8238583410997204, "loss_cot": 0.4919198751449585, "loss_nocot": 0.19634655117988586, "step": 3030 }, { "epoch": 2.8247903075489282, "grad_norm": 0.646849822694683, "learning_rate": 1.2978943734898173e-06, "loss": 0.7445, "step": 3031 }, { "epoch": 2.8247903075489282, "loss_cot": 0.5120723843574524, "loss_nocot": 0.2577645182609558, "step": 3031 }, { "epoch": 2.825722273998136, "grad_norm": 0.6679169122171186, "learning_rate": 1.2909906800138076e-06, "loss": 0.7509, "step": 3032 }, { "epoch": 2.825722273998136, "loss_cot": 0.44844770431518555, "loss_nocot": 0.2084861844778061, "step": 3032 }, { "epoch": 2.826654240447344, "grad_norm": 0.6140810892552772, "learning_rate": 1.2840869865377979e-06, "loss": 0.7238, "step": 3033 }, { "epoch": 2.826654240447344, "loss_cot": 0.4636180102825165, "loss_nocot": 0.2272477000951767, "step": 3033 }, { "epoch": 2.8275862068965516, "grad_norm": 0.6445179014414415, "learning_rate": 1.277183293061788e-06, "loss": 0.7183, "step": 3034 }, { "epoch": 2.8275862068965516, "loss_cot": 0.5032673478126526, "loss_nocot": 0.1681111752986908, "step": 3034 }, { "epoch": 2.8285181733457594, "grad_norm": 0.600549130106888, "learning_rate": 1.2702795995857787e-06, "loss": 0.7273, "step": 3035 }, { "epoch": 2.8285181733457594, "loss_cot": 0.5076488256454468, "loss_nocot": 0.24432343244552612, "step": 3035 }, { "epoch": 2.829450139794967, "grad_norm": 0.6214610926548332, "learning_rate": 1.2633759061097688e-06, "loss": 0.7057, "step": 3036 }, { "epoch": 2.829450139794967, "loss_cot": 0.5005809664726257, "loss_nocot": 0.30912697315216064, "step": 3036 }, { "epoch": 2.8303821062441754, "grad_norm": 0.7072426434020079, "learning_rate": 1.2564722126337591e-06, "loss": 0.7851, "step": 3037 }, { "epoch": 2.8303821062441754, "loss_cot": 0.4732549786567688, "loss_nocot": 0.2604967951774597, "step": 3037 }, { "epoch": 2.831314072693383, "grad_norm": 0.6430378175451954, "learning_rate": 1.2495685191577494e-06, "loss": 0.7594, "step": 3038 }, { "epoch": 2.831314072693383, "loss_cot": 0.5021936297416687, "loss_nocot": 0.3779330253601074, "step": 3038 }, { "epoch": 2.832246039142591, "grad_norm": 19.205213836426623, "learning_rate": 1.24266482568174e-06, "loss": 0.801, "step": 3039 }, { "epoch": 2.832246039142591, "loss_cot": 0.48961302638053894, "loss_nocot": 0.24999311566352844, "step": 3039 }, { "epoch": 2.8331780055917988, "grad_norm": 0.6036267424192081, "learning_rate": 1.2357611322057302e-06, "loss": 0.6959, "step": 3040 }, { "epoch": 2.8331780055917988, "loss_cot": 0.4878377318382263, "loss_nocot": 0.3469337224960327, "step": 3040 }, { "epoch": 2.8341099720410066, "grad_norm": 0.6733571917670745, "learning_rate": 1.2288574387297203e-06, "loss": 0.7641, "step": 3041 }, { "epoch": 2.8341099720410066, "loss_cot": 0.4573741555213928, "loss_nocot": 0.36602550745010376, "step": 3041 }, { "epoch": 2.8350419384902144, "grad_norm": 0.6556133208102869, "learning_rate": 1.2219537452537109e-06, "loss": 0.7525, "step": 3042 }, { "epoch": 2.8350419384902144, "loss_cot": 0.45958033204078674, "loss_nocot": 0.23560383915901184, "step": 3042 }, { "epoch": 2.835973904939422, "grad_norm": 0.6663294920789352, "learning_rate": 1.2150500517777012e-06, "loss": 0.7736, "step": 3043 }, { "epoch": 2.835973904939422, "loss_cot": 0.49181097745895386, "loss_nocot": 0.2641967833042145, "step": 3043 }, { "epoch": 2.83690587138863, "grad_norm": 0.6811853568045081, "learning_rate": 1.2081463583016915e-06, "loss": 0.8221, "step": 3044 }, { "epoch": 2.83690587138863, "loss_cot": 0.47060760855674744, "loss_nocot": 0.2672170400619507, "step": 3044 }, { "epoch": 2.8378378378378377, "grad_norm": 0.6990839128800469, "learning_rate": 1.2012426648256818e-06, "loss": 0.7706, "step": 3045 }, { "epoch": 2.8378378378378377, "loss_cot": 0.515607476234436, "loss_nocot": 0.2741355895996094, "step": 3045 }, { "epoch": 2.8387698042870455, "grad_norm": 0.657672324980105, "learning_rate": 1.194338971349672e-06, "loss": 0.8056, "step": 3046 }, { "epoch": 2.8387698042870455, "loss_cot": 0.4782230854034424, "loss_nocot": 0.23221909999847412, "step": 3046 }, { "epoch": 2.8397017707362533, "grad_norm": 0.632229198860624, "learning_rate": 1.1874352778736626e-06, "loss": 0.7275, "step": 3047 }, { "epoch": 2.8397017707362533, "loss_cot": 0.47447189688682556, "loss_nocot": 0.24102091789245605, "step": 3047 }, { "epoch": 2.8406337371854615, "grad_norm": 0.6735063851096093, "learning_rate": 1.1805315843976527e-06, "loss": 0.7778, "step": 3048 }, { "epoch": 2.8406337371854615, "loss_cot": 0.558652937412262, "loss_nocot": 0.24289995431900024, "step": 3048 }, { "epoch": 2.8415657036346693, "grad_norm": 0.6778854720896936, "learning_rate": 1.1736278909216432e-06, "loss": 0.822, "step": 3049 }, { "epoch": 2.8415657036346693, "loss_cot": 0.5528510808944702, "loss_nocot": 0.2526664137840271, "step": 3049 }, { "epoch": 2.842497670083877, "grad_norm": 0.629277878080053, "learning_rate": 1.1667241974456335e-06, "loss": 0.7518, "step": 3050 }, { "epoch": 2.842497670083877, "loss_cot": 0.47398650646209717, "loss_nocot": 0.20455554127693176, "step": 3050 }, { "epoch": 2.843429636533085, "grad_norm": 0.6212051075224524, "learning_rate": 1.1598205039696239e-06, "loss": 0.7259, "step": 3051 }, { "epoch": 2.843429636533085, "loss_cot": 0.57756507396698, "loss_nocot": 0.3268250823020935, "step": 3051 }, { "epoch": 2.8443616029822927, "grad_norm": 0.6467931639956529, "learning_rate": 1.1529168104936142e-06, "loss": 0.7814, "step": 3052 }, { "epoch": 2.8443616029822927, "loss_cot": 0.4747235178947449, "loss_nocot": 0.28019583225250244, "step": 3052 }, { "epoch": 2.8452935694315005, "grad_norm": 0.6325386462375623, "learning_rate": 1.1460131170176045e-06, "loss": 0.7378, "step": 3053 }, { "epoch": 2.8452935694315005, "loss_cot": 0.49092763662338257, "loss_nocot": 0.2833361029624939, "step": 3053 }, { "epoch": 2.8462255358807083, "grad_norm": 0.6400785749750811, "learning_rate": 1.139109423541595e-06, "loss": 0.7586, "step": 3054 }, { "epoch": 2.8462255358807083, "loss_cot": 0.4561436176300049, "loss_nocot": 0.2860344648361206, "step": 3054 }, { "epoch": 2.847157502329916, "grad_norm": 0.6333215367114927, "learning_rate": 1.132205730065585e-06, "loss": 0.7684, "step": 3055 }, { "epoch": 2.847157502329916, "loss_cot": 0.49732622504234314, "loss_nocot": 0.2127913534641266, "step": 3055 }, { "epoch": 2.848089468779124, "grad_norm": 0.6237881531398354, "learning_rate": 1.1253020365895754e-06, "loss": 0.7467, "step": 3056 }, { "epoch": 2.848089468779124, "loss_cot": 0.47885775566101074, "loss_nocot": 0.24282798171043396, "step": 3056 }, { "epoch": 2.8490214352283316, "grad_norm": 0.6382365749191161, "learning_rate": 1.118398343113566e-06, "loss": 0.728, "step": 3057 }, { "epoch": 2.8490214352283316, "loss_cot": 0.5361573696136475, "loss_nocot": 0.2532033324241638, "step": 3057 }, { "epoch": 2.8499534016775394, "grad_norm": 0.6422035876879204, "learning_rate": 1.1114946496375562e-06, "loss": 0.728, "step": 3058 }, { "epoch": 2.8499534016775394, "loss_cot": 0.4686863124370575, "loss_nocot": 0.20020553469657898, "step": 3058 }, { "epoch": 2.8508853681267476, "grad_norm": 0.6932576246593887, "learning_rate": 1.1045909561615465e-06, "loss": 0.7583, "step": 3059 }, { "epoch": 2.8508853681267476, "loss_cot": 0.47789090871810913, "loss_nocot": 0.3126169741153717, "step": 3059 }, { "epoch": 2.8518173345759554, "grad_norm": 0.6515650979630214, "learning_rate": 1.0976872626855368e-06, "loss": 0.7171, "step": 3060 }, { "epoch": 2.8518173345759554, "loss_cot": 0.48609018325805664, "loss_nocot": 0.2587181627750397, "step": 3060 }, { "epoch": 2.852749301025163, "grad_norm": 0.6314022345768406, "learning_rate": 1.0907835692095272e-06, "loss": 0.7168, "step": 3061 }, { "epoch": 2.852749301025163, "loss_cot": 0.5267335176467896, "loss_nocot": 0.3769506812095642, "step": 3061 }, { "epoch": 2.853681267474371, "grad_norm": 0.6615168495950211, "learning_rate": 1.0838798757335175e-06, "loss": 0.768, "step": 3062 }, { "epoch": 2.853681267474371, "loss_cot": 0.5184235572814941, "loss_nocot": 0.24413876235485077, "step": 3062 }, { "epoch": 2.854613233923579, "grad_norm": 0.6747440942210421, "learning_rate": 1.0769761822575078e-06, "loss": 0.7787, "step": 3063 }, { "epoch": 2.854613233923579, "loss_cot": 0.5644956827163696, "loss_nocot": 0.3803083896636963, "step": 3063 }, { "epoch": 2.8555452003727866, "grad_norm": 0.6125203845171882, "learning_rate": 1.0700724887814983e-06, "loss": 0.7438, "step": 3064 }, { "epoch": 2.8555452003727866, "loss_cot": 0.48581212759017944, "loss_nocot": 0.23522964119911194, "step": 3064 }, { "epoch": 2.8564771668219944, "grad_norm": 0.5970058685504369, "learning_rate": 1.0631687953054886e-06, "loss": 0.7197, "step": 3065 }, { "epoch": 2.8564771668219944, "loss_cot": 0.4878242015838623, "loss_nocot": 0.2345418483018875, "step": 3065 }, { "epoch": 2.857409133271202, "grad_norm": 0.6278350531911401, "learning_rate": 1.0562651018294787e-06, "loss": 0.7545, "step": 3066 }, { "epoch": 2.857409133271202, "loss_cot": 0.4831674098968506, "loss_nocot": 0.19764888286590576, "step": 3066 }, { "epoch": 2.85834109972041, "grad_norm": 0.6304334676758092, "learning_rate": 1.0493614083534692e-06, "loss": 0.7136, "step": 3067 }, { "epoch": 2.85834109972041, "loss_cot": 0.5087752342224121, "loss_nocot": 0.24519674479961395, "step": 3067 }, { "epoch": 2.8592730661696177, "grad_norm": 0.6440266681878296, "learning_rate": 1.0424577148774595e-06, "loss": 0.7529, "step": 3068 }, { "epoch": 2.8592730661696177, "loss_cot": 0.47104042768478394, "loss_nocot": 0.25627732276916504, "step": 3068 }, { "epoch": 2.8602050326188255, "grad_norm": 0.6628099697252439, "learning_rate": 1.0355540214014498e-06, "loss": 0.7762, "step": 3069 }, { "epoch": 2.8602050326188255, "loss_cot": 0.49574029445648193, "loss_nocot": 0.20545393228530884, "step": 3069 }, { "epoch": 2.8611369990680338, "grad_norm": 0.6359353308470719, "learning_rate": 1.0286503279254402e-06, "loss": 0.7471, "step": 3070 }, { "epoch": 2.8611369990680338, "loss_cot": 0.47254276275634766, "loss_nocot": 0.29909878969192505, "step": 3070 }, { "epoch": 2.862068965517241, "grad_norm": 0.6463783409780863, "learning_rate": 1.0217466344494305e-06, "loss": 0.7534, "step": 3071 }, { "epoch": 2.862068965517241, "loss_cot": 0.5631399154663086, "loss_nocot": 0.22054117918014526, "step": 3071 }, { "epoch": 2.8630009319664493, "grad_norm": 0.6346887442381445, "learning_rate": 1.014842940973421e-06, "loss": 0.7545, "step": 3072 }, { "epoch": 2.8630009319664493, "loss_cot": 0.4774181842803955, "loss_nocot": 0.24539443850517273, "step": 3072 }, { "epoch": 2.863932898415657, "grad_norm": 0.6268349713533561, "learning_rate": 1.007939247497411e-06, "loss": 0.7523, "step": 3073 }, { "epoch": 2.863932898415657, "loss_cot": 0.5292536020278931, "loss_nocot": 0.25285032391548157, "step": 3073 }, { "epoch": 2.864864864864865, "grad_norm": 0.6393092469959841, "learning_rate": 1.0010355540214016e-06, "loss": 0.7571, "step": 3074 }, { "epoch": 2.864864864864865, "loss_cot": 0.4871505796909332, "loss_nocot": 0.2565830945968628, "step": 3074 }, { "epoch": 2.8657968313140727, "grad_norm": 0.6684387849395803, "learning_rate": 9.94131860545392e-07, "loss": 0.7663, "step": 3075 }, { "epoch": 2.8657968313140727, "loss_cot": 0.48727545142173767, "loss_nocot": 0.2047964185476303, "step": 3075 }, { "epoch": 2.8667287977632805, "grad_norm": 0.6383110591297696, "learning_rate": 9.872281670693822e-07, "loss": 0.7648, "step": 3076 }, { "epoch": 2.8667287977632805, "loss_cot": 0.5105003118515015, "loss_nocot": 0.24981901049613953, "step": 3076 }, { "epoch": 2.8676607642124883, "grad_norm": 0.6951099937594286, "learning_rate": 9.803244735933725e-07, "loss": 0.7668, "step": 3077 }, { "epoch": 2.8676607642124883, "loss_cot": 0.5113239884376526, "loss_nocot": 0.32588350772857666, "step": 3077 }, { "epoch": 2.868592730661696, "grad_norm": 0.6631162837623071, "learning_rate": 9.734207801173628e-07, "loss": 0.7767, "step": 3078 }, { "epoch": 2.868592730661696, "loss_cot": 0.4964536428451538, "loss_nocot": 0.18087413907051086, "step": 3078 }, { "epoch": 2.869524697110904, "grad_norm": 0.6492767558400027, "learning_rate": 9.665170866413534e-07, "loss": 0.7404, "step": 3079 }, { "epoch": 2.869524697110904, "loss_cot": 0.5058268308639526, "loss_nocot": 0.27944105863571167, "step": 3079 }, { "epoch": 2.8704566635601116, "grad_norm": 0.6287870154207101, "learning_rate": 9.596133931653435e-07, "loss": 0.747, "step": 3080 }, { "epoch": 2.8704566635601116, "loss_cot": 0.5057730674743652, "loss_nocot": 0.3116571605205536, "step": 3080 }, { "epoch": 2.87138863000932, "grad_norm": 0.6291913242107363, "learning_rate": 9.527096996893339e-07, "loss": 0.767, "step": 3081 }, { "epoch": 2.87138863000932, "loss_cot": 0.4440537095069885, "loss_nocot": 0.2887527346611023, "step": 3081 }, { "epoch": 2.872320596458527, "grad_norm": 0.651775154396942, "learning_rate": 9.458060062133243e-07, "loss": 0.7549, "step": 3082 }, { "epoch": 2.872320596458527, "loss_cot": 0.48208338022232056, "loss_nocot": 0.24939051270484924, "step": 3082 }, { "epoch": 2.8732525629077355, "grad_norm": 0.6407426287076595, "learning_rate": 9.389023127373145e-07, "loss": 0.7257, "step": 3083 }, { "epoch": 2.8732525629077355, "loss_cot": 0.4949629306793213, "loss_nocot": 0.31884336471557617, "step": 3083 }, { "epoch": 2.8741845293569432, "grad_norm": 0.6011706913416518, "learning_rate": 9.319986192613049e-07, "loss": 0.7318, "step": 3084 }, { "epoch": 2.8741845293569432, "loss_cot": 0.49508464336395264, "loss_nocot": 0.22598148882389069, "step": 3084 }, { "epoch": 2.875116495806151, "grad_norm": 0.6394231123772833, "learning_rate": 9.250949257852952e-07, "loss": 0.7358, "step": 3085 }, { "epoch": 2.875116495806151, "loss_cot": 0.49037402868270874, "loss_nocot": 0.24036698043346405, "step": 3085 }, { "epoch": 2.876048462255359, "grad_norm": 0.6265981698485869, "learning_rate": 9.181912323092855e-07, "loss": 0.6903, "step": 3086 }, { "epoch": 2.876048462255359, "loss_cot": 0.4415532946586609, "loss_nocot": 0.26522111892700195, "step": 3086 }, { "epoch": 2.8769804287045666, "grad_norm": 0.6557129885217777, "learning_rate": 9.112875388332759e-07, "loss": 0.7504, "step": 3087 }, { "epoch": 2.8769804287045666, "loss_cot": 0.4666719138622284, "loss_nocot": 0.2731752395629883, "step": 3087 }, { "epoch": 2.8779123951537744, "grad_norm": 0.6531707633225192, "learning_rate": 9.043838453572662e-07, "loss": 0.7435, "step": 3088 }, { "epoch": 2.8779123951537744, "loss_cot": 0.45867836475372314, "loss_nocot": 0.32214680314064026, "step": 3088 }, { "epoch": 2.878844361602982, "grad_norm": 0.6719347055068066, "learning_rate": 8.974801518812564e-07, "loss": 0.7726, "step": 3089 }, { "epoch": 2.878844361602982, "loss_cot": 0.48012036085128784, "loss_nocot": 0.2690027952194214, "step": 3089 }, { "epoch": 2.87977632805219, "grad_norm": 0.6478717257136779, "learning_rate": 8.905764584052469e-07, "loss": 0.7697, "step": 3090 }, { "epoch": 2.87977632805219, "loss_cot": 0.45392078161239624, "loss_nocot": 0.2744932770729065, "step": 3090 }, { "epoch": 2.8807082945013978, "grad_norm": 0.6444831184002026, "learning_rate": 8.836727649292372e-07, "loss": 0.7636, "step": 3091 }, { "epoch": 2.8807082945013978, "loss_cot": 0.47880059480667114, "loss_nocot": 0.2062404453754425, "step": 3091 }, { "epoch": 2.881640260950606, "grad_norm": 0.5994940474943147, "learning_rate": 8.767690714532276e-07, "loss": 0.7073, "step": 3092 }, { "epoch": 2.881640260950606, "loss_cot": 0.5262400507926941, "loss_nocot": 0.41593706607818604, "step": 3092 }, { "epoch": 2.8825722273998133, "grad_norm": 0.683262360531267, "learning_rate": 8.698653779772179e-07, "loss": 0.8218, "step": 3093 }, { "epoch": 2.8825722273998133, "loss_cot": 0.46660009026527405, "loss_nocot": 0.2610958218574524, "step": 3093 }, { "epoch": 2.8835041938490216, "grad_norm": 0.6649501723026112, "learning_rate": 8.629616845012082e-07, "loss": 0.7569, "step": 3094 }, { "epoch": 2.8835041938490216, "loss_cot": 0.4355660080909729, "loss_nocot": 0.350914865732193, "step": 3094 }, { "epoch": 2.8844361602982294, "grad_norm": 0.6756307216896315, "learning_rate": 8.560579910251986e-07, "loss": 0.7554, "step": 3095 }, { "epoch": 2.8844361602982294, "loss_cot": 0.5030264258384705, "loss_nocot": 0.229354590177536, "step": 3095 }, { "epoch": 2.885368126747437, "grad_norm": 0.676182841724996, "learning_rate": 8.491542975491888e-07, "loss": 0.7682, "step": 3096 }, { "epoch": 2.885368126747437, "loss_cot": 0.5345447063446045, "loss_nocot": 0.23139937222003937, "step": 3096 }, { "epoch": 2.886300093196645, "grad_norm": 0.6510720854565356, "learning_rate": 8.422506040731792e-07, "loss": 0.7369, "step": 3097 }, { "epoch": 2.886300093196645, "loss_cot": 0.48767417669296265, "loss_nocot": 0.2288392186164856, "step": 3097 }, { "epoch": 2.8872320596458527, "grad_norm": 0.6524898980468051, "learning_rate": 8.353469105971695e-07, "loss": 0.7582, "step": 3098 }, { "epoch": 2.8872320596458527, "loss_cot": 0.43180257081985474, "loss_nocot": 0.2733066976070404, "step": 3098 }, { "epoch": 2.8881640260950605, "grad_norm": 0.6671451509115821, "learning_rate": 8.284432171211599e-07, "loss": 0.7441, "step": 3099 }, { "epoch": 2.8881640260950605, "loss_cot": 0.5291131734848022, "loss_nocot": 0.20872071385383606, "step": 3099 }, { "epoch": 2.8890959925442683, "grad_norm": 0.5954910909989639, "learning_rate": 8.215395236451503e-07, "loss": 0.7131, "step": 3100 }, { "epoch": 2.8890959925442683, "loss_cot": 0.49452513456344604, "loss_nocot": 0.25503870844841003, "step": 3100 }, { "epoch": 2.890027958993476, "grad_norm": 0.6913876169277015, "learning_rate": 8.146358301691405e-07, "loss": 0.7705, "step": 3101 }, { "epoch": 2.890027958993476, "loss_cot": 0.5034850239753723, "loss_nocot": 0.23658686876296997, "step": 3101 }, { "epoch": 2.890959925442684, "grad_norm": 0.6802863893056983, "learning_rate": 8.07732136693131e-07, "loss": 0.7371, "step": 3102 }, { "epoch": 2.890959925442684, "loss_cot": 0.44743382930755615, "loss_nocot": 0.2998221814632416, "step": 3102 }, { "epoch": 2.891891891891892, "grad_norm": 0.6839004643861557, "learning_rate": 8.008284432171212e-07, "loss": 0.7918, "step": 3103 }, { "epoch": 2.891891891891892, "loss_cot": 0.4423450827598572, "loss_nocot": 0.22469571232795715, "step": 3103 }, { "epoch": 2.8928238583410995, "grad_norm": 0.6575205006169124, "learning_rate": 7.939247497411115e-07, "loss": 0.7419, "step": 3104 }, { "epoch": 2.8928238583410995, "loss_cot": 0.5101178288459778, "loss_nocot": 0.20951727032661438, "step": 3104 }, { "epoch": 2.8937558247903077, "grad_norm": 0.640089780115005, "learning_rate": 7.870210562651019e-07, "loss": 0.7484, "step": 3105 }, { "epoch": 2.8937558247903077, "loss_cot": 0.5045552253723145, "loss_nocot": 0.20607046782970428, "step": 3105 }, { "epoch": 2.8946877912395155, "grad_norm": 0.6351620230550127, "learning_rate": 7.801173627890922e-07, "loss": 0.7268, "step": 3106 }, { "epoch": 2.8946877912395155, "loss_cot": 0.4384033679962158, "loss_nocot": 0.2768300473690033, "step": 3106 }, { "epoch": 2.8956197576887233, "grad_norm": 0.6391408734930417, "learning_rate": 7.732136693130826e-07, "loss": 0.7297, "step": 3107 }, { "epoch": 2.8956197576887233, "loss_cot": 0.5083770751953125, "loss_nocot": 0.2121942937374115, "step": 3107 }, { "epoch": 2.896551724137931, "grad_norm": 0.6336241596054197, "learning_rate": 7.663099758370728e-07, "loss": 0.7418, "step": 3108 }, { "epoch": 2.896551724137931, "loss_cot": 0.4614982604980469, "loss_nocot": 0.28611359000205994, "step": 3108 }, { "epoch": 2.897483690587139, "grad_norm": 0.6522417145652595, "learning_rate": 7.594062823610632e-07, "loss": 0.7676, "step": 3109 }, { "epoch": 2.897483690587139, "loss_cot": 0.46947264671325684, "loss_nocot": 0.2747013568878174, "step": 3109 }, { "epoch": 2.8984156570363466, "grad_norm": 0.7307180801836595, "learning_rate": 7.525025888850536e-07, "loss": 0.8024, "step": 3110 }, { "epoch": 2.8984156570363466, "loss_cot": 0.511512279510498, "loss_nocot": 0.26802825927734375, "step": 3110 }, { "epoch": 2.8993476234855544, "grad_norm": 0.6048317253921751, "learning_rate": 7.455988954090439e-07, "loss": 0.7228, "step": 3111 }, { "epoch": 2.8993476234855544, "loss_cot": 0.46689850091934204, "loss_nocot": 0.2464444935321808, "step": 3111 }, { "epoch": 2.900279589934762, "grad_norm": 0.6871885682836045, "learning_rate": 7.386952019330343e-07, "loss": 0.7381, "step": 3112 }, { "epoch": 2.900279589934762, "loss_cot": 0.4451332986354828, "loss_nocot": 0.23284225165843964, "step": 3112 }, { "epoch": 2.90121155638397, "grad_norm": 0.6246835245741766, "learning_rate": 7.317915084570246e-07, "loss": 0.7369, "step": 3113 }, { "epoch": 2.90121155638397, "loss_cot": 0.44805458188056946, "loss_nocot": 0.26972246170043945, "step": 3113 }, { "epoch": 2.9021435228331782, "grad_norm": 0.6424748282463728, "learning_rate": 7.248878149810148e-07, "loss": 0.7085, "step": 3114 }, { "epoch": 2.9021435228331782, "loss_cot": 0.48388880491256714, "loss_nocot": 0.25316447019577026, "step": 3114 }, { "epoch": 2.9030754892823856, "grad_norm": 0.6421271370466225, "learning_rate": 7.179841215050052e-07, "loss": 0.7365, "step": 3115 }, { "epoch": 2.9030754892823856, "loss_cot": 0.5537012815475464, "loss_nocot": 0.2475874125957489, "step": 3115 }, { "epoch": 2.904007455731594, "grad_norm": 0.6323197723856309, "learning_rate": 7.110804280289955e-07, "loss": 0.7265, "step": 3116 }, { "epoch": 2.904007455731594, "loss_cot": 0.5468448996543884, "loss_nocot": 0.19803133606910706, "step": 3116 }, { "epoch": 2.9049394221808016, "grad_norm": 0.6471689265126366, "learning_rate": 7.041767345529859e-07, "loss": 0.7302, "step": 3117 }, { "epoch": 2.9049394221808016, "loss_cot": 0.5304775834083557, "loss_nocot": 0.28858837485313416, "step": 3117 }, { "epoch": 2.9058713886300094, "grad_norm": 0.6239248941725805, "learning_rate": 6.972730410769763e-07, "loss": 0.7219, "step": 3118 }, { "epoch": 2.9058713886300094, "loss_cot": 0.5644518733024597, "loss_nocot": 0.25543642044067383, "step": 3118 }, { "epoch": 2.906803355079217, "grad_norm": 0.5958174194365635, "learning_rate": 6.903693476009666e-07, "loss": 0.713, "step": 3119 }, { "epoch": 2.906803355079217, "loss_cot": 0.46832725405693054, "loss_nocot": 0.39034926891326904, "step": 3119 }, { "epoch": 2.907735321528425, "grad_norm": 0.7441416860907561, "learning_rate": 6.83465654124957e-07, "loss": 0.8439, "step": 3120 }, { "epoch": 2.907735321528425, "loss_cot": 0.5373079776763916, "loss_nocot": 0.38028764724731445, "step": 3120 }, { "epoch": 2.9086672879776327, "grad_norm": 0.6347217443416926, "learning_rate": 6.765619606489472e-07, "loss": 0.7359, "step": 3121 }, { "epoch": 2.9086672879776327, "loss_cot": 0.48664385080337524, "loss_nocot": 0.2529417872428894, "step": 3121 }, { "epoch": 2.9095992544268405, "grad_norm": 0.6086724622836847, "learning_rate": 6.696582671729376e-07, "loss": 0.7192, "step": 3122 }, { "epoch": 2.9095992544268405, "loss_cot": 0.511770486831665, "loss_nocot": 0.28397321701049805, "step": 3122 }, { "epoch": 2.9105312208760483, "grad_norm": 0.665918501521443, "learning_rate": 6.627545736969279e-07, "loss": 0.7648, "step": 3123 }, { "epoch": 2.9105312208760483, "loss_cot": 0.5134268999099731, "loss_nocot": 0.20928369462490082, "step": 3123 }, { "epoch": 2.911463187325256, "grad_norm": 0.6359815741461834, "learning_rate": 6.558508802209182e-07, "loss": 0.6713, "step": 3124 }, { "epoch": 2.911463187325256, "loss_cot": 0.4443737268447876, "loss_nocot": 0.21579554677009583, "step": 3124 }, { "epoch": 2.9123951537744643, "grad_norm": 0.648580009681958, "learning_rate": 6.489471867449086e-07, "loss": 0.7314, "step": 3125 }, { "epoch": 2.9123951537744643, "loss_cot": 0.43726855516433716, "loss_nocot": 0.23698559403419495, "step": 3125 }, { "epoch": 2.9133271202236717, "grad_norm": 0.64033044427404, "learning_rate": 6.420434932688989e-07, "loss": 0.6991, "step": 3126 }, { "epoch": 2.9133271202236717, "loss_cot": 0.44202321767807007, "loss_nocot": 0.20473764836788177, "step": 3126 }, { "epoch": 2.91425908667288, "grad_norm": 0.6375798430085302, "learning_rate": 6.351397997928894e-07, "loss": 0.7179, "step": 3127 }, { "epoch": 2.91425908667288, "loss_cot": 0.4746084213256836, "loss_nocot": 0.25310930609703064, "step": 3127 }, { "epoch": 2.9151910531220877, "grad_norm": 0.5997823533008039, "learning_rate": 6.282361063168796e-07, "loss": 0.6933, "step": 3128 }, { "epoch": 2.9151910531220877, "loss_cot": 0.4356973171234131, "loss_nocot": 0.2601366639137268, "step": 3128 }, { "epoch": 2.9161230195712955, "grad_norm": 0.6978294144891429, "learning_rate": 6.2133241284087e-07, "loss": 0.7915, "step": 3129 }, { "epoch": 2.9161230195712955, "loss_cot": 0.5068337917327881, "loss_nocot": 0.22084906697273254, "step": 3129 }, { "epoch": 2.9170549860205033, "grad_norm": 0.6563648893849592, "learning_rate": 6.144287193648602e-07, "loss": 0.7856, "step": 3130 }, { "epoch": 2.9170549860205033, "loss_cot": 0.48701488971710205, "loss_nocot": 0.2678709626197815, "step": 3130 }, { "epoch": 2.917986952469711, "grad_norm": 0.6259160514223425, "learning_rate": 6.075250258888506e-07, "loss": 0.6993, "step": 3131 }, { "epoch": 2.917986952469711, "loss_cot": 0.4825044572353363, "loss_nocot": 0.2723691463470459, "step": 3131 }, { "epoch": 2.918918918918919, "grad_norm": 0.6798652770569633, "learning_rate": 6.006213324128409e-07, "loss": 0.7894, "step": 3132 }, { "epoch": 2.918918918918919, "loss_cot": 0.4757324457168579, "loss_nocot": 0.37627333402633667, "step": 3132 }, { "epoch": 2.9198508853681266, "grad_norm": 0.64891882407232, "learning_rate": 5.937176389368313e-07, "loss": 0.7652, "step": 3133 }, { "epoch": 2.9198508853681266, "loss_cot": 0.4840536415576935, "loss_nocot": 0.23859214782714844, "step": 3133 }, { "epoch": 2.9207828518173344, "grad_norm": 0.6261901890114439, "learning_rate": 5.868139454608216e-07, "loss": 0.7279, "step": 3134 }, { "epoch": 2.9207828518173344, "loss_cot": 0.4581694006919861, "loss_nocot": 0.20711086690425873, "step": 3134 }, { "epoch": 2.9217148182665422, "grad_norm": 0.6319078292797871, "learning_rate": 5.799102519848119e-07, "loss": 0.7329, "step": 3135 }, { "epoch": 2.9217148182665422, "loss_cot": 0.49302464723587036, "loss_nocot": 0.2768383324146271, "step": 3135 }, { "epoch": 2.9226467847157505, "grad_norm": 0.6751892317694491, "learning_rate": 5.730065585088022e-07, "loss": 0.7654, "step": 3136 }, { "epoch": 2.9226467847157505, "loss_cot": 0.4662579596042633, "loss_nocot": 0.2963847815990448, "step": 3136 }, { "epoch": 2.923578751164958, "grad_norm": 0.6879609673399286, "learning_rate": 5.661028650327925e-07, "loss": 0.7333, "step": 3137 }, { "epoch": 2.923578751164958, "loss_cot": 0.4824056625366211, "loss_nocot": 0.2881406545639038, "step": 3137 }, { "epoch": 2.924510717614166, "grad_norm": 0.7101202165609781, "learning_rate": 5.59199171556783e-07, "loss": 0.7911, "step": 3138 }, { "epoch": 2.924510717614166, "loss_cot": 0.44744953513145447, "loss_nocot": 0.25312426686286926, "step": 3138 }, { "epoch": 2.925442684063374, "grad_norm": 0.6464736094661124, "learning_rate": 5.522954780807733e-07, "loss": 0.7177, "step": 3139 }, { "epoch": 2.925442684063374, "loss_cot": 0.49798864126205444, "loss_nocot": 0.2853454351425171, "step": 3139 }, { "epoch": 2.9263746505125816, "grad_norm": 0.6739264245324146, "learning_rate": 5.453917846047636e-07, "loss": 0.7338, "step": 3140 }, { "epoch": 2.9263746505125816, "loss_cot": 0.5094897747039795, "loss_nocot": 0.19449353218078613, "step": 3140 }, { "epoch": 2.9273066169617894, "grad_norm": 0.6063544297467185, "learning_rate": 5.384880911287539e-07, "loss": 0.7016, "step": 3141 }, { "epoch": 2.9273066169617894, "loss_cot": 0.5367487668991089, "loss_nocot": 0.25901320576667786, "step": 3141 }, { "epoch": 2.928238583410997, "grad_norm": 0.6640659970888625, "learning_rate": 5.315843976527443e-07, "loss": 0.7468, "step": 3142 }, { "epoch": 2.928238583410997, "loss_cot": 0.4785696864128113, "loss_nocot": 0.22622501850128174, "step": 3142 }, { "epoch": 2.929170549860205, "grad_norm": 0.6856011785487297, "learning_rate": 5.246807041767346e-07, "loss": 0.7704, "step": 3143 }, { "epoch": 2.929170549860205, "loss_cot": 0.5369791984558105, "loss_nocot": 0.2428267002105713, "step": 3143 }, { "epoch": 2.9301025163094128, "grad_norm": 0.6524497352782318, "learning_rate": 5.177770107007249e-07, "loss": 0.796, "step": 3144 }, { "epoch": 2.9301025163094128, "loss_cot": 0.4780281186103821, "loss_nocot": 0.21600866317749023, "step": 3144 }, { "epoch": 2.9310344827586206, "grad_norm": 0.6398631279891774, "learning_rate": 5.108733172247152e-07, "loss": 0.7832, "step": 3145 }, { "epoch": 2.9310344827586206, "loss_cot": 0.5217844843864441, "loss_nocot": 0.20016233623027802, "step": 3145 }, { "epoch": 2.9319664492078283, "grad_norm": 0.6082790432850103, "learning_rate": 5.039696237487055e-07, "loss": 0.7875, "step": 3146 }, { "epoch": 2.9319664492078283, "loss_cot": 0.5285219550132751, "loss_nocot": 0.2151196002960205, "step": 3146 }, { "epoch": 2.9328984156570366, "grad_norm": 0.6476556138240094, "learning_rate": 4.97065930272696e-07, "loss": 0.7427, "step": 3147 }, { "epoch": 2.9328984156570366, "loss_cot": 0.44003403186798096, "loss_nocot": 0.24240705370903015, "step": 3147 }, { "epoch": 2.933830382106244, "grad_norm": 0.6706104843942615, "learning_rate": 4.901622367966863e-07, "loss": 0.7416, "step": 3148 }, { "epoch": 2.933830382106244, "loss_cot": 0.5012872219085693, "loss_nocot": 0.24250084161758423, "step": 3148 }, { "epoch": 2.934762348555452, "grad_norm": 0.6514286868492678, "learning_rate": 4.832585433206767e-07, "loss": 0.722, "step": 3149 }, { "epoch": 2.934762348555452, "loss_cot": 0.5034436583518982, "loss_nocot": 0.29259565472602844, "step": 3149 }, { "epoch": 2.93569431500466, "grad_norm": 0.6651222816270219, "learning_rate": 4.7635484984466693e-07, "loss": 0.7486, "step": 3150 }, { "epoch": 2.93569431500466, "loss_cot": 0.4890096187591553, "loss_nocot": 0.20563668012619019, "step": 3150 }, { "epoch": 2.9366262814538677, "grad_norm": 0.6290148620278593, "learning_rate": 4.6945115636865724e-07, "loss": 0.7403, "step": 3151 }, { "epoch": 2.9366262814538677, "loss_cot": 0.5072430372238159, "loss_nocot": 0.2606586515903473, "step": 3151 }, { "epoch": 2.9375582479030755, "grad_norm": 0.6725403105097619, "learning_rate": 4.625474628926476e-07, "loss": 0.7762, "step": 3152 }, { "epoch": 2.9375582479030755, "loss_cot": 0.4627310037612915, "loss_nocot": 0.23372209072113037, "step": 3152 }, { "epoch": 2.9384902143522833, "grad_norm": 0.6232079929242167, "learning_rate": 4.5564376941663797e-07, "loss": 0.6962, "step": 3153 }, { "epoch": 2.9384902143522833, "loss_cot": 0.4815872609615326, "loss_nocot": 0.21690011024475098, "step": 3153 }, { "epoch": 2.939422180801491, "grad_norm": 0.6612543722897756, "learning_rate": 4.487400759406282e-07, "loss": 0.7813, "step": 3154 }, { "epoch": 2.939422180801491, "loss_cot": 0.4752740263938904, "loss_nocot": 0.2663606107234955, "step": 3154 }, { "epoch": 2.940354147250699, "grad_norm": 0.6319129160432465, "learning_rate": 4.418363824646186e-07, "loss": 0.7454, "step": 3155 }, { "epoch": 2.940354147250699, "loss_cot": 0.4280714988708496, "loss_nocot": 0.26803550124168396, "step": 3155 }, { "epoch": 2.9412861136999067, "grad_norm": 0.6606145744617533, "learning_rate": 4.3493268898860895e-07, "loss": 0.7278, "step": 3156 }, { "epoch": 2.9412861136999067, "loss_cot": 0.47954824566841125, "loss_nocot": 0.2564866840839386, "step": 3156 }, { "epoch": 2.9422180801491145, "grad_norm": 0.686768843456594, "learning_rate": 4.280289955125993e-07, "loss": 0.7801, "step": 3157 }, { "epoch": 2.9422180801491145, "loss_cot": 0.44617271423339844, "loss_nocot": 0.23545540869235992, "step": 3157 }, { "epoch": 2.9431500465983227, "grad_norm": 0.6398075308814113, "learning_rate": 4.211253020365896e-07, "loss": 0.7512, "step": 3158 }, { "epoch": 2.9431500465983227, "loss_cot": 0.5003578662872314, "loss_nocot": 0.2705751061439514, "step": 3158 }, { "epoch": 2.94408201304753, "grad_norm": 0.6368468606854627, "learning_rate": 4.142216085605799e-07, "loss": 0.723, "step": 3159 }, { "epoch": 2.94408201304753, "loss_cot": 0.46034443378448486, "loss_nocot": 0.27387720346450806, "step": 3159 }, { "epoch": 2.9450139794967383, "grad_norm": 0.6581991638240868, "learning_rate": 4.0731791508457024e-07, "loss": 0.7668, "step": 3160 }, { "epoch": 2.9450139794967383, "loss_cot": 0.5175763964653015, "loss_nocot": 0.2993854880332947, "step": 3160 }, { "epoch": 2.945945945945946, "grad_norm": 0.6603332337247186, "learning_rate": 4.004142216085606e-07, "loss": 0.7392, "step": 3161 }, { "epoch": 2.945945945945946, "loss_cot": 0.47167083621025085, "loss_nocot": 0.34635478258132935, "step": 3161 }, { "epoch": 2.946877912395154, "grad_norm": 0.6733295467867093, "learning_rate": 3.9351052813255096e-07, "loss": 0.7427, "step": 3162 }, { "epoch": 2.946877912395154, "loss_cot": 0.4967539310455322, "loss_nocot": 0.2585870027542114, "step": 3162 }, { "epoch": 2.9478098788443616, "grad_norm": 0.612742263493075, "learning_rate": 3.866068346565413e-07, "loss": 0.7258, "step": 3163 }, { "epoch": 2.9478098788443616, "loss_cot": 0.47436538338661194, "loss_nocot": 0.23752360045909882, "step": 3163 }, { "epoch": 2.9487418452935694, "grad_norm": 0.613344379830514, "learning_rate": 3.797031411805316e-07, "loss": 0.726, "step": 3164 }, { "epoch": 2.9487418452935694, "loss_cot": 0.4494750499725342, "loss_nocot": 0.27671748399734497, "step": 3164 }, { "epoch": 2.949673811742777, "grad_norm": 0.6314245489597593, "learning_rate": 3.7279944770452194e-07, "loss": 0.7258, "step": 3165 }, { "epoch": 2.949673811742777, "loss_cot": 0.4694928526878357, "loss_nocot": 0.30297160148620605, "step": 3165 }, { "epoch": 2.950605778191985, "grad_norm": 0.6543826714084243, "learning_rate": 3.658957542285123e-07, "loss": 0.7724, "step": 3166 }, { "epoch": 2.950605778191985, "loss_cot": 0.5166161060333252, "loss_nocot": 0.28102219104766846, "step": 3166 }, { "epoch": 2.951537744641193, "grad_norm": 0.6477516222807387, "learning_rate": 3.589920607525026e-07, "loss": 0.7723, "step": 3167 }, { "epoch": 2.951537744641193, "loss_cot": 0.4992956817150116, "loss_nocot": 0.4449065625667572, "step": 3167 }, { "epoch": 2.9524697110904006, "grad_norm": 0.7241678472564015, "learning_rate": 3.5208836727649297e-07, "loss": 0.835, "step": 3168 }, { "epoch": 2.9524697110904006, "loss_cot": 0.4846625030040741, "loss_nocot": 0.2917497158050537, "step": 3168 }, { "epoch": 2.953401677539609, "grad_norm": 0.6258145565765351, "learning_rate": 3.451846738004833e-07, "loss": 0.7529, "step": 3169 }, { "epoch": 2.953401677539609, "loss_cot": 0.5220719575881958, "loss_nocot": 0.21940429508686066, "step": 3169 }, { "epoch": 2.954333643988816, "grad_norm": 0.6337684515402306, "learning_rate": 3.382809803244736e-07, "loss": 0.7627, "step": 3170 }, { "epoch": 2.954333643988816, "loss_cot": 0.5339083671569824, "loss_nocot": 0.21483278274536133, "step": 3170 }, { "epoch": 2.9552656104380244, "grad_norm": 0.6539553460446572, "learning_rate": 3.3137728684846395e-07, "loss": 0.7842, "step": 3171 }, { "epoch": 2.9552656104380244, "loss_cot": 0.4743473529815674, "loss_nocot": 0.26396068930625916, "step": 3171 }, { "epoch": 2.956197576887232, "grad_norm": 0.6361496169333974, "learning_rate": 3.244735933724543e-07, "loss": 0.7662, "step": 3172 }, { "epoch": 2.956197576887232, "loss_cot": 0.5546666383743286, "loss_nocot": 0.1722812056541443, "step": 3172 }, { "epoch": 2.95712954333644, "grad_norm": 0.6409825029171993, "learning_rate": 3.175698998964447e-07, "loss": 0.76, "step": 3173 }, { "epoch": 2.95712954333644, "loss_cot": 0.4251405894756317, "loss_nocot": 0.2788817882537842, "step": 3173 }, { "epoch": 2.9580615097856477, "grad_norm": 0.7045642059396743, "learning_rate": 3.10666206420435e-07, "loss": 0.7791, "step": 3174 }, { "epoch": 2.9580615097856477, "loss_cot": 0.5241667032241821, "loss_nocot": 0.28670620918273926, "step": 3174 }, { "epoch": 2.9589934762348555, "grad_norm": 0.6603743005959092, "learning_rate": 3.037625129444253e-07, "loss": 0.7468, "step": 3175 }, { "epoch": 2.9589934762348555, "loss_cot": 0.48346462845802307, "loss_nocot": 0.29527485370635986, "step": 3175 }, { "epoch": 2.9599254426840633, "grad_norm": 0.6662945486633383, "learning_rate": 2.9685881946841566e-07, "loss": 0.7271, "step": 3176 }, { "epoch": 2.9599254426840633, "loss_cot": 0.46086597442626953, "loss_nocot": 0.32311519980430603, "step": 3176 }, { "epoch": 2.960857409133271, "grad_norm": 0.6684584368168234, "learning_rate": 2.8995512599240596e-07, "loss": 0.8167, "step": 3177 }, { "epoch": 2.960857409133271, "loss_cot": 0.47890251874923706, "loss_nocot": 0.31844860315322876, "step": 3177 }, { "epoch": 2.961789375582479, "grad_norm": 0.6718614901702298, "learning_rate": 2.8305143251639627e-07, "loss": 0.7635, "step": 3178 }, { "epoch": 2.961789375582479, "loss_cot": 0.5148971080780029, "loss_nocot": 0.24542726576328278, "step": 3178 }, { "epoch": 2.9627213420316867, "grad_norm": 0.6450430009800775, "learning_rate": 2.7614773904038664e-07, "loss": 0.7436, "step": 3179 }, { "epoch": 2.9627213420316867, "loss_cot": 0.45677751302719116, "loss_nocot": 0.28576046228408813, "step": 3179 }, { "epoch": 2.963653308480895, "grad_norm": 0.6162561366997973, "learning_rate": 2.6924404556437694e-07, "loss": 0.7745, "step": 3180 }, { "epoch": 2.963653308480895, "loss_cot": 0.5065208673477173, "loss_nocot": 0.25232192873954773, "step": 3180 }, { "epoch": 2.9645852749301023, "grad_norm": 0.6619521321767472, "learning_rate": 2.623403520883673e-07, "loss": 0.7451, "step": 3181 }, { "epoch": 2.9645852749301023, "loss_cot": 0.4688296914100647, "loss_nocot": 0.2947796881198883, "step": 3181 }, { "epoch": 2.9655172413793105, "grad_norm": 0.6505153703868466, "learning_rate": 2.554366586123576e-07, "loss": 0.79, "step": 3182 }, { "epoch": 2.9655172413793105, "loss_cot": 0.5053836107254028, "loss_nocot": 0.21633878350257874, "step": 3182 }, { "epoch": 2.9664492078285183, "grad_norm": 0.6146957334429511, "learning_rate": 2.48532965136348e-07, "loss": 0.7506, "step": 3183 }, { "epoch": 2.9664492078285183, "loss_cot": 0.5160561800003052, "loss_nocot": 0.2597635090351105, "step": 3183 }, { "epoch": 2.967381174277726, "grad_norm": 0.6634836517516185, "learning_rate": 2.4162927166033834e-07, "loss": 0.7996, "step": 3184 }, { "epoch": 2.967381174277726, "loss_cot": 0.4416009187698364, "loss_nocot": 0.2642807066440582, "step": 3184 }, { "epoch": 2.968313140726934, "grad_norm": 0.6497982031548709, "learning_rate": 2.3472557818432862e-07, "loss": 0.7359, "step": 3185 }, { "epoch": 2.968313140726934, "loss_cot": 0.4551342725753784, "loss_nocot": 0.2696961462497711, "step": 3185 }, { "epoch": 2.9692451071761417, "grad_norm": 0.6502215696398717, "learning_rate": 2.2782188470831898e-07, "loss": 0.7244, "step": 3186 }, { "epoch": 2.9692451071761417, "loss_cot": 0.47707289457321167, "loss_nocot": 0.3645652234554291, "step": 3186 }, { "epoch": 2.9701770736253494, "grad_norm": 0.695294198068531, "learning_rate": 2.209181912323093e-07, "loss": 0.816, "step": 3187 }, { "epoch": 2.9701770736253494, "loss_cot": 0.5052405595779419, "loss_nocot": 0.3025807738304138, "step": 3187 }, { "epoch": 2.9711090400745572, "grad_norm": 0.6514413003042254, "learning_rate": 2.1401449775629965e-07, "loss": 0.7787, "step": 3188 }, { "epoch": 2.9711090400745572, "loss_cot": 0.4697068929672241, "loss_nocot": 0.2934737801551819, "step": 3188 }, { "epoch": 2.972041006523765, "grad_norm": 0.6625388906299027, "learning_rate": 2.0711080428028996e-07, "loss": 0.742, "step": 3189 }, { "epoch": 2.972041006523765, "loss_cot": 0.43210142850875854, "loss_nocot": 0.3079039454460144, "step": 3189 }, { "epoch": 2.972972972972973, "grad_norm": 0.7079712494847674, "learning_rate": 2.002071108042803e-07, "loss": 0.7591, "step": 3190 }, { "epoch": 2.972972972972973, "loss_cot": 0.49819692969322205, "loss_nocot": 0.2296144962310791, "step": 3190 }, { "epoch": 2.973904939422181, "grad_norm": 0.6450496667641009, "learning_rate": 1.9330341732827066e-07, "loss": 0.7791, "step": 3191 }, { "epoch": 2.973904939422181, "loss_cot": 0.5611374974250793, "loss_nocot": 0.25213345885276794, "step": 3191 }, { "epoch": 2.9748369058713884, "grad_norm": 0.7239396224205719, "learning_rate": 1.8639972385226097e-07, "loss": 0.7404, "step": 3192 }, { "epoch": 2.9748369058713884, "loss_cot": 0.508735716342926, "loss_nocot": 0.34496045112609863, "step": 3192 }, { "epoch": 2.9757688723205966, "grad_norm": 0.632358232084202, "learning_rate": 1.794960303762513e-07, "loss": 0.7407, "step": 3193 }, { "epoch": 2.9757688723205966, "loss_cot": 0.5154492855072021, "loss_nocot": 0.2538251280784607, "step": 3193 }, { "epoch": 2.9767008387698044, "grad_norm": 0.6473688305065689, "learning_rate": 1.7259233690024164e-07, "loss": 0.7533, "step": 3194 }, { "epoch": 2.9767008387698044, "loss_cot": 0.5175548791885376, "loss_nocot": 0.236263707280159, "step": 3194 }, { "epoch": 2.977632805219012, "grad_norm": 0.6376058841621135, "learning_rate": 1.6568864342423198e-07, "loss": 0.7122, "step": 3195 }, { "epoch": 2.977632805219012, "loss_cot": 0.4907068908214569, "loss_nocot": 0.3288765549659729, "step": 3195 }, { "epoch": 2.97856477166822, "grad_norm": 0.6835546810910109, "learning_rate": 1.5878494994822234e-07, "loss": 0.8018, "step": 3196 }, { "epoch": 2.97856477166822, "loss_cot": 0.5049007534980774, "loss_nocot": 0.20978492498397827, "step": 3196 }, { "epoch": 2.9794967381174278, "grad_norm": 0.6558896245377105, "learning_rate": 1.5188125647221265e-07, "loss": 0.7558, "step": 3197 }, { "epoch": 2.9794967381174278, "loss_cot": 0.48799997568130493, "loss_nocot": 0.28468042612075806, "step": 3197 }, { "epoch": 2.9804287045666356, "grad_norm": 0.7063475778062758, "learning_rate": 1.4497756299620298e-07, "loss": 0.8158, "step": 3198 }, { "epoch": 2.9804287045666356, "loss_cot": 0.4746326506137848, "loss_nocot": 0.26078566908836365, "step": 3198 }, { "epoch": 2.9813606710158433, "grad_norm": 0.6129955473887345, "learning_rate": 1.3807386952019332e-07, "loss": 0.7482, "step": 3199 }, { "epoch": 2.9813606710158433, "loss_cot": 0.48140302300453186, "loss_nocot": 0.24812108278274536, "step": 3199 }, { "epoch": 2.982292637465051, "grad_norm": 0.6905281553840789, "learning_rate": 1.3117017604418365e-07, "loss": 0.7726, "step": 3200 }, { "epoch": 2.982292637465051, "loss_cot": 0.5748745203018188, "loss_nocot": 0.2609052062034607, "step": 3200 }, { "epoch": 2.983224603914259, "grad_norm": 0.6590725194417202, "learning_rate": 1.24266482568174e-07, "loss": 0.7634, "step": 3201 }, { "epoch": 2.983224603914259, "loss_cot": 0.4454694986343384, "loss_nocot": 0.23998002707958221, "step": 3201 }, { "epoch": 2.984156570363467, "grad_norm": 0.6612912328861333, "learning_rate": 1.1736278909216431e-07, "loss": 0.754, "step": 3202 }, { "epoch": 2.984156570363467, "loss_cot": 0.49668586254119873, "loss_nocot": 0.3349694609642029, "step": 3202 }, { "epoch": 2.9850885368126745, "grad_norm": 0.6743111082024837, "learning_rate": 1.1045909561615465e-07, "loss": 0.7492, "step": 3203 }, { "epoch": 2.9850885368126745, "loss_cot": 0.4767317473888397, "loss_nocot": 0.2597637176513672, "step": 3203 }, { "epoch": 2.9860205032618827, "grad_norm": 0.6471004957464914, "learning_rate": 1.0355540214014498e-07, "loss": 0.7566, "step": 3204 }, { "epoch": 2.9860205032618827, "loss_cot": 0.48559245467185974, "loss_nocot": 0.21642044186592102, "step": 3204 }, { "epoch": 2.9869524697110905, "grad_norm": 0.7463655676713818, "learning_rate": 9.665170866413533e-08, "loss": 0.7645, "step": 3205 }, { "epoch": 2.9869524697110905, "loss_cot": 0.47732555866241455, "loss_nocot": 0.24407634139060974, "step": 3205 }, { "epoch": 2.9878844361602983, "grad_norm": 0.6380293987578759, "learning_rate": 8.974801518812565e-08, "loss": 0.7312, "step": 3206 }, { "epoch": 2.9878844361602983, "loss_cot": 0.5538513660430908, "loss_nocot": 0.31298941373825073, "step": 3206 }, { "epoch": 2.988816402609506, "grad_norm": 0.6550096545227325, "learning_rate": 8.284432171211599e-08, "loss": 0.8138, "step": 3207 }, { "epoch": 2.988816402609506, "loss_cot": 0.45296624302864075, "loss_nocot": 0.265249639749527, "step": 3207 }, { "epoch": 2.989748369058714, "grad_norm": 0.6793774028081244, "learning_rate": 7.594062823610632e-08, "loss": 0.7192, "step": 3208 }, { "epoch": 2.989748369058714, "loss_cot": 0.49235689640045166, "loss_nocot": 0.22990037500858307, "step": 3208 }, { "epoch": 2.9906803355079217, "grad_norm": 0.6314218532405127, "learning_rate": 6.903693476009666e-08, "loss": 0.7462, "step": 3209 }, { "epoch": 2.9906803355079217, "loss_cot": 0.5004119873046875, "loss_nocot": 0.26455363631248474, "step": 3209 }, { "epoch": 2.9916123019571295, "grad_norm": 0.6212430722077303, "learning_rate": 6.2133241284087e-08, "loss": 0.7339, "step": 3210 }, { "epoch": 2.9916123019571295, "loss_cot": 0.4976810812950134, "loss_nocot": 0.23512756824493408, "step": 3210 }, { "epoch": 2.9925442684063372, "grad_norm": 0.630641552831134, "learning_rate": 5.522954780807732e-08, "loss": 0.7224, "step": 3211 }, { "epoch": 2.9925442684063372, "loss_cot": 0.4915234446525574, "loss_nocot": 0.25759774446487427, "step": 3211 }, { "epoch": 2.993476234855545, "grad_norm": 0.6544768966348492, "learning_rate": 4.8325854332067665e-08, "loss": 0.777, "step": 3212 }, { "epoch": 2.993476234855545, "loss_cot": 0.5137064456939697, "loss_nocot": 0.31043100357055664, "step": 3212 }, { "epoch": 2.9944082013047533, "grad_norm": 0.6849399713285031, "learning_rate": 4.1422160856057994e-08, "loss": 0.8004, "step": 3213 }, { "epoch": 2.9944082013047533, "loss_cot": 0.4843445122241974, "loss_nocot": 0.30838021636009216, "step": 3213 }, { "epoch": 2.9953401677539606, "grad_norm": 0.6690443421406448, "learning_rate": 3.451846738004833e-08, "loss": 0.7621, "step": 3214 }, { "epoch": 2.9953401677539606, "loss_cot": 0.5027201175689697, "loss_nocot": 0.29596930742263794, "step": 3214 }, { "epoch": 2.996272134203169, "grad_norm": 0.6621155939587414, "learning_rate": 2.761477390403866e-08, "loss": 0.7482, "step": 3215 }, { "epoch": 2.996272134203169, "loss_cot": 0.5321040153503418, "loss_nocot": 0.2600725293159485, "step": 3215 }, { "epoch": 2.9972041006523766, "grad_norm": 0.6634303455223339, "learning_rate": 2.0711080428028997e-08, "loss": 0.7368, "step": 3216 }, { "epoch": 2.9972041006523766, "loss_cot": 0.5218710899353027, "loss_nocot": 0.21018362045288086, "step": 3216 }, { "epoch": 2.9981360671015844, "grad_norm": 0.7115708896086609, "learning_rate": 1.380738695201933e-08, "loss": 0.7559, "step": 3217 }, { "epoch": 2.9981360671015844, "loss_cot": 0.49070996046066284, "loss_nocot": 0.3584457039833069, "step": 3217 }, { "epoch": 2.999068033550792, "grad_norm": 0.6438634633535625, "learning_rate": 6.903693476009665e-09, "loss": 0.7414, "step": 3218 }, { "epoch": 2.999068033550792, "loss_cot": 0.5256683826446533, "loss_nocot": 0.23372657597064972, "step": 3218 }, { "epoch": 3.0, "grad_norm": 0.6512905856598039, "learning_rate": 0.0, "loss": 0.794, "step": 3219 }, { "epoch": 3.0, "step": 3219, "total_flos": 0.0, "train_loss": 0.9124189101231324, "train_runtime": 114112.8338, "train_samples_per_second": 0.451, "train_steps_per_second": 0.028 } ], "logging_steps": 1, "max_steps": 3219, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 0.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }