1
|
{"args": {"mode": "sdil", "dataset": "mnist", "depth": 3, "width": 256, "act": "tanh", "residual": 0, "epochs": 15, "batch_size": 128, "eta": 0.05, "eta_A": 0.02, "eta_P": 0.002, "momentum": 0.9, "w_scale": 1.0, "a_scale": 1.0, "pert_sigma": 0.01, "pert_every": 4, "pert_ndirs": 8, "use_residual": 0, "learn_A": 1, "learn_P": 1, "p_neutral": 1, "p_warmup_steps": 200, "p_warmup_eta": 0.05, "nuis_rho": 0.02, "predictor_mode": "diagonal", "normalize_delta": 0, "settle_steps": 0, "kappa": 0.0, "feedback": "error", "seed": 0, "device": "cuda", "log_every": 100, "max_steps": 0, "probe_bs": 512, "outdir": "results", "tag": "diag_nuis_low_rho0p02_res0_s0", "n_in": 784}, "provenance": {"git_commit": "54633b2e0f51a8f48d4ba627d778c87927f54ca1", "git_dirty": false}, "steps": [{"step": 0, "epoch": 0, "train_loss": 2.3603768348693848, "cos_r_negg": [-0.01925944909453392, -0.02566162496805191, 0.03369072079658508], "cos_apical_negg": [-0.019273214042186737, -0.025740373879671097, 0.03344225510954857], "cos_Ac_negg": [-0.019259434193372726, -0.02566162496805191, 0.03369072079658508], "r_norm": [4.897989273071289, 4.826717376708984, 4.823838233947754], "ldr": {"dL_sdil": -0.009076356887817383, "dL_bp": -0.2385098934173584, "ratio": 0.03805442515516557}}, {"step": 100, "epoch": 0, "train_loss": 0.206071138381958, "cos_r_negg": [0.4681476652622223, 0.4429267644882202, 0.38471874594688416], "cos_apical_negg": [0.26263806223869324, 0.2645108997821808, 0.2631727457046509], "cos_Ac_negg": [0.46821776032447815, 0.4429766535758972, 0.3847416937351227], "r_norm": [0.8438946008682251, 0.8258217573165894, 0.8231493830680847]}, {"step": 200, "epoch": 0, "train_loss": 0.33237993717193604, "cos_r_negg": [0.48675966262817383, 0.4554031491279602, 0.42761093378067017], "cos_apical_negg": [0.2616196870803833, 0.2735486626625061, 0.2730584144592285], "cos_Ac_negg": [0.4869941473007202, 0.4553951025009155, 0.4277513027191162], "r_norm": [0.7278070449829102, 0.707707405090332, 0.7060608863830566]}, {"step": 300, "epoch": 0, "train_loss": 0.19734743237495422, "cos_r_negg": [0.5285393595695496, 0.52535480260849, 0.4794597029685974], "cos_apical_negg": [0.23711776733398438, 0.29444169998168945, 0.2775915265083313], "cos_Ac_negg": [0.5286089181900024, 0.5253909826278687, 0.4794451594352722], "r_norm": [0.6054061651229858, 0.591116726398468, 0.5910351872444153]}, {"step": 400, "epoch": 0, "train_loss": 0.15375865995883942, "cos_r_negg": [0.5338476300239563, 0.5296660661697388, 0.4938103258609772], "cos_apical_negg": [0.2340439260005951, 0.28611883521080017, 0.33072173595428467], "cos_Ac_negg": [0.5339211821556091, 0.5297133326530457, 0.49383288621902466], "r_norm": [0.5766323804855347, 0.5654773712158203, 0.5646674036979675]}, {"epoch_end": 0, "step": 469, "test_acc": 0.9449, "test_loss": 0.19892386169433593}, {"step": 500, "epoch": 1, "train_loss": 0.1472272425889969, "cos_r_negg": [0.526983380317688, 0.5274121761322021, 0.49484068155288696], "cos_apical_negg": [0.2006608545780182, 0.2437020242214203, 0.28972962498664856], "cos_Ac_negg": [0.5270229578018188, 0.5274916887283325, 0.49490851163864136], "r_norm": [0.4700573980808258, 0.4561854600906372, 0.4551491439342499], "ldr": {"dL_sdil": -0.007757142186164856, "dL_bp": -0.006305679678916931, "ratio": 1.2301833555074002}}, {"step": 600, "epoch": 1, "train_loss": 0.07822880148887634, "cos_r_negg": [0.5186655521392822, 0.5267373323440552, 0.45328375697135925], "cos_apical_negg": [0.20669317245483398, 0.2607686519622803, 0.3002426028251648], "cos_Ac_negg": [0.518663763999939, 0.5267905592918396, 0.4531635642051697], "r_norm": [0.48179900646209717, 0.4725462794303894, 0.47014787793159485]}, {"step": 700, "epoch": 1, "train_loss": 0.21658703684806824, "cos_r_negg": [0.5297616720199585, 0.5559932589530945, 0.48670634627342224], "cos_apical_negg": [0.19816885888576508, 0.2939818799495697, 0.3034880459308624], "cos_Ac_negg": [0.5298179388046265, 0.556054949760437, 0.48665502667427063], "r_norm": [0.46541786193847656, 0.4562772512435913, 0.45401731133461]}, {"step": 800, "epoch": 1, "train_loss": 0.1682123839855194, "cos_r_negg": [0.5429261922836304, 0.5628002285957336, 0.5304246544837952], "cos_apical_negg": [0.20251761376857758, 0.2674803137779236, 0.3079812228679657], "cos_Ac_negg": [0.542924165725708, 0.5628063678741455, 0.5304079055786133], "r_norm": [0.419233500957489, 0.40934354066848755, 0.40891626477241516]}, {"step": 900, "epoch": 1, "train_loss": 0.20421729981899261, "cos_r_negg": [0.5431697368621826, 0.579277753829956, 0.5153729915618896], "cos_apical_negg": [0.19254359602928162, 0.26994097232818604, 0.32042673230171204], "cos_Ac_negg": [0.5431655645370483, 0.5792593955993652, 0.5153427720069885], "r_norm": [0.4034919738769531, 0.392557829618454, 0.3928130269050598]}, {"epoch_end": 1, "step": 938, "test_acc": 0.9518, "test_loss": 0.1722327033996582}, {"step": 1000, "epoch": 2, "train_loss": 0.041068803519010544, "cos_r_negg": [0.5078740119934082, 0.550865888595581, 0.5254982113838196], "cos_apical_negg": [0.14767752587795258, 0.22598004341125488, 0.2837088406085968], "cos_Ac_negg": [0.507811427116394, 0.5508331656455994, 0.5254217982292175], "r_norm": [0.33645105361938477, 0.3285433053970337, 0.3294784724712372], "ldr": {"dL_sdil": -0.006873175501823425, "dL_bp": -0.005714923143386841, "ratio": 1.202671554695689}}, {"step": 1100, "epoch": 2, "train_loss": 0.11744073033332825, "cos_r_negg": [0.5406942367553711, 0.5750820636749268, 0.5276658535003662], "cos_apical_negg": [0.17650026082992554, 0.260485976934433, 0.3302422761917114], "cos_Ac_negg": [0.5406332015991211, 0.5750493407249451, 0.5275596380233765], "r_norm": [0.35915249586105347, 0.35092929005622864, 0.3507956266403198]}, {"step": 1200, "epoch": 2, "train_loss": 0.1697431206703186, "cos_r_negg": [0.48784440755844116, 0.5374298095703125, 0.5122506618499756], "cos_apical_negg": [0.16910775005817413, 0.23454412817955017, 0.3069744110107422], "cos_Ac_negg": [0.48777857422828674, 0.5373592376708984, 0.5121716856956482], "r_norm": [0.41340339183807373, 0.40443333983421326, 0.4033299386501312]}, {"step": 1300, "epoch": 2, "train_loss": 0.14309418201446533, "cos_r_negg": [0.4753113389015198, 0.5426746010780334, 0.49981796741485596], "cos_apical_negg": [0.17476284503936768, 0.23367735743522644, 0.27802371978759766], "cos_Ac_negg": [0.47528213262557983, 0.5426498651504517, 0.49971646070480347], "r_norm": [0.3467801511287689, 0.3394143879413605, 0.337238073348999]}, {"step": 1400, "epoch": 2, "train_loss": 0.1667533814907074, "cos_r_negg": [0.45972293615341187, 0.5054548382759094, 0.5182697772979736], "cos_apical_negg": [0.13602866232395172, 0.207316055893898, 0.26495563983917236], "cos_Ac_negg": [0.45968353748321533, 0.505387544631958, 0.5181490182876587], "r_norm": [0.31786465644836426, 0.3079378008842468, 0.30868756771087646]}, {"epoch_end": 2, "step": 1407, "test_acc": 0.9631, "test_loss": 0.134154386138916}, {"step": 1500, "epoch": 3, "train_loss": 0.06395118683576584, "cos_r_negg": [0.4347681999206543, 0.4764384925365448, 0.4741770029067993], "cos_apical_negg": [0.13339635729789734, 0.20873010158538818, 0.2309040129184723], "cos_Ac_negg": [0.4347454607486725, 0.47638610005378723, 0.47409844398498535], "r_norm": [0.3315296173095703, 0.32385939359664917, 0.3227711319923401], "ldr": {"dL_sdil": -0.005825206637382507, "dL_bp": -0.005550175905227661, "ratio": 1.0495535162941048}}, {"step": 1600, "epoch": 3, "train_loss": 0.09140448272228241, "cos_r_negg": [0.4630548357963562, 0.5250738859176636, 0.5203036069869995], "cos_apical_negg": [0.13214173913002014, 0.22044754028320312, 0.2836686074733734], "cos_Ac_negg": [0.4630080461502075, 0.5249927043914795, 0.5201841592788696], "r_norm": [0.3129541277885437, 0.3022066354751587, 0.30283039808273315]}, {"step": 1700, "epoch": 3, "train_loss": 0.06026475504040718, "cos_r_negg": [0.43740707635879517, 0.49217793345451355, 0.4837079644203186], "cos_apical_negg": [0.1464240401983261, 0.21427947282791138, 0.29652056097984314], "cos_Ac_negg": [0.43735408782958984, 0.4920836091041565, 0.4835726320743561], "r_norm": [0.3232586681842804, 0.3133507966995239, 0.31499576568603516]}, {"step": 1800, "epoch": 3, "train_loss": 0.038792576640844345, "cos_r_negg": [0.4113686680793762, 0.46835997700691223, 0.48693421483039856], "cos_apical_negg": [0.11118613183498383, 0.18830563127994537, 0.23896212875843048], "cos_Ac_negg": [0.4112994074821472, 0.46827012300491333, 0.4868676960468292], "r_norm": [0.24922126531600952, 0.2421068549156189, 0.2417508065700531]}, {"epoch_end": 3, "step": 1876, "test_acc": 0.9657, "test_loss": 0.12998302383422852}, {"step": 1900, "epoch": 4, "train_loss": 0.09116171300411224, "cos_r_negg": [0.4054185748100281, 0.458378404378891, 0.4776462912559509], "cos_apical_negg": [0.12753790616989136, 0.20597206056118011, 0.21349479258060455], "cos_Ac_negg": [0.40535789728164673, 0.45829713344573975, 0.47761425375938416], "r_norm": [0.27217990159988403, 0.2658555209636688, 0.2657337486743927]}, {"step": 2000, "epoch": 4, "train_loss": 0.16241157054901123, "cos_r_negg": [0.40267765522003174, 0.4554517865180969, 0.4866638779640198], "cos_apical_negg": [0.09805499017238617, 0.18514610826969147, 0.2427842617034912], "cos_Ac_negg": [0.40264204144477844, 0.45538997650146484, 0.4865497946739197], "r_norm": [0.2589050829410553, 0.2514130771160126, 0.2510063052177429], "ldr": {"dL_sdil": -0.005476370453834534, "dL_bp": -0.00536104291677475, "ratio": 1.0215121458361998}}, {"step": 2100, "epoch": 4, "train_loss": 0.01772943325340748, "cos_r_negg": [0.44070112705230713, 0.4932866096496582, 0.553056001663208], "cos_apical_negg": [0.16076679527759552, 0.2079952359199524, 0.3001341223716736], "cos_Ac_negg": [0.4406587481498718, 0.4932495951652527, 0.5529830455780029], "r_norm": [0.2952989637851715, 0.2919972836971283, 0.28878647089004517]}, {"step": 2200, "epoch": 4, "train_loss": 0.057878486812114716, "cos_r_negg": [0.3757783770561218, 0.42753899097442627, 0.45231103897094727], "cos_apical_negg": [0.10571407526731491, 0.1683899313211441, 0.2443653643131256], "cos_Ac_negg": [0.3757992684841156, 0.42747724056243896, 0.4522625207901001], "r_norm": [0.287088543176651, 0.27858322858810425, 0.2778674364089966]}, {"step": 2300, "epoch": 4, "train_loss": 0.22512993216514587, "cos_r_negg": [0.36532062292099, 0.42891421914100647, 0.4331624507904053], "cos_apical_negg": [0.09902752935886383, 0.14983227849006653, 0.23736990988254547], "cos_Ac_negg": [0.3652558922767639, 0.4288051426410675, 0.43303361535072327], "r_norm": [0.2867211103439331, 0.27858883142471313, 0.27877819538116455]}, {"epoch_end": 4, "step": 2345, "test_acc": 0.9668, "test_loss": 0.1339680564880371}, {"step": 2400, "epoch": 5, "train_loss": 0.08477146923542023, "cos_r_negg": [0.41073328256607056, 0.4612548351287842, 0.4929535984992981], "cos_apical_negg": [0.08546945452690125, 0.16547246277332306, 0.2646588683128357], "cos_Ac_negg": [0.410677433013916, 0.4611518383026123, 0.49284693598747253], "r_norm": [0.2526025176048279, 0.24683891236782074, 0.24579359591007233]}, {"step": 2500, "epoch": 5, "train_loss": 0.025092322379350662, "cos_r_negg": [0.3764820694923401, 0.43139785528182983, 0.4772835373878479], "cos_apical_negg": [0.08639393001794815, 0.1544605791568756, 0.24907028675079346], "cos_Ac_negg": [0.37641221284866333, 0.43128007650375366, 0.4771392345428467], "r_norm": [0.21813178062438965, 0.21333324909210205, 0.21203911304473877], "ldr": {"dL_sdil": -0.0030814483761787415, "dL_bp": -0.002756349742412567, "ratio": 1.1179453495192606}}, {"step": 2600, "epoch": 5, "train_loss": 0.06760348379611969, "cos_r_negg": [0.38867685198783875, 0.448198139667511, 0.47526270151138306], "cos_apical_negg": [0.09218351542949677, 0.14963187277317047, 0.2465364933013916], "cos_Ac_negg": [0.38863271474838257, 0.44811707735061646, 0.4751494526863098], "r_norm": [0.25988900661468506, 0.25497108697891235, 0.2504923939704895]}, {"step": 2700, "epoch": 5, "train_loss": 0.06910201907157898, "cos_r_negg": [0.40041670203208923, 0.4457572102546692, 0.4869686961174011], "cos_apical_negg": [0.08335276693105698, 0.14289376139640808, 0.2409048080444336], "cos_Ac_negg": [0.4003782272338867, 0.4456818997859955, 0.486863911151886], "r_norm": [0.2247849553823471, 0.22020334005355835, 0.21887263655662537]}, {"step": 2800, "epoch": 5, "train_loss": 0.0953345000743866, "cos_r_negg": [0.38028910756111145, 0.4324725866317749, 0.47883039712905884], "cos_apical_negg": [0.09604420512914658, 0.1389172524213791, 0.1950380504131317], "cos_Ac_negg": [0.38023999333381653, 0.43236660957336426, 0.4787330627441406], "r_norm": [0.2579306364059448, 0.2504432499408722, 0.24913740158081055]}, {"epoch_end": 5, "step": 2814, "test_acc": 0.9644, "test_loss": 0.14248134422302247}, {"step": 2900, "epoch": 6, "train_loss": 0.01733783632516861, "cos_r_negg": [0.34765544533729553, 0.4037877917289734, 0.4658434987068176], "cos_apical_negg": [0.0725863128900528, 0.17288920283317566, 0.21283870935440063], "cos_Ac_negg": [0.34756898880004883, 0.4036415219306946, 0.46571725606918335], "r_norm": [0.2390182614326477, 0.23241755366325378, 0.2319326102733612]}, {"step": 3000, "epoch": 6, "train_loss": 0.23049652576446533, "cos_r_negg": [0.36030441522598267, 0.41825050115585327, 0.47125720977783203], "cos_apical_negg": [0.07580869644880295, 0.14458076655864716, 0.21424773335456848], "cos_Ac_negg": [0.3602030277252197, 0.4181329607963562, 0.4712256193161011], "r_norm": [0.232564777135849, 0.22713430225849152, 0.22508463263511658], "ldr": {"dL_sdil": -0.0049345046281814575, "dL_bp": -0.005487807095050812, "ratio": 0.8991760356576034}}, {"step": 3100, "epoch": 6, "train_loss": 0.06224461644887924, "cos_r_negg": [0.37403592467308044, 0.4602539837360382, 0.4656350612640381], "cos_apical_negg": [0.084104984998703, 0.18456366658210754, 0.23997732996940613], "cos_Ac_negg": [0.3739563226699829, 0.46012061834335327, 0.46556568145751953], "r_norm": [0.2350768744945526, 0.22893840074539185, 0.22728988528251648]}, {"step": 3200, "epoch": 6, "train_loss": 0.0449090451002121, "cos_r_negg": [0.35728710889816284, 0.41038230061531067, 0.4553821086883545], "cos_apical_negg": [0.07288661599159241, 0.1684381067752838, 0.22839972376823425], "cos_Ac_negg": [0.3572527766227722, 0.4102838635444641, 0.45527946949005127], "r_norm": [0.24285468459129333, 0.23665675520896912, 0.2350439578294754]}, {"epoch_end": 6, "step": 3283, "test_acc": 0.9672, "test_loss": 0.13613516082763671}, {"step": 3300, "epoch": 7, "train_loss": 0.029432538896799088, "cos_r_negg": [0.3691403269767761, 0.41885921359062195, 0.4724518060684204], "cos_apical_negg": [0.08806461095809937, 0.15996243059635162, 0.230827197432518], "cos_Ac_negg": [0.36912912130355835, 0.41879940032958984, 0.4724229574203491], "r_norm": [0.2313859462738037, 0.22590097784996033, 0.2239949256181717]}, {"step": 3400, "epoch": 7, "train_loss": 0.09313170611858368, "cos_r_negg": [0.3199690878391266, 0.3703828752040863, 0.393064022064209], "cos_apical_negg": [0.07493884861469269, 0.13648273050785065, 0.15313021838665009], "cos_Ac_negg": [0.3199384808540344, 0.37025684118270874, 0.39303058385849], "r_norm": [0.23286309838294983, 0.2264416515827179, 0.22547772526741028]}, {"step": 3500, "epoch": 7, "train_loss": 0.010211452841758728, "cos_r_negg": [0.3271755576133728, 0.3839573264122009, 0.40030205249786377], "cos_apical_negg": [0.06485243886709213, 0.13228990137577057, 0.17978887259960175], "cos_Ac_negg": [0.3271646499633789, 0.3838975727558136, 0.4002265930175781], "r_norm": [0.22983810305595398, 0.22434550523757935, 0.22287964820861816], "ldr": {"dL_sdil": -0.00641883909702301, "dL_bp": -0.007397115230560303, "ratio": 0.8677489665842083}}, {"step": 3600, "epoch": 7, "train_loss": 0.0180648360401392, "cos_r_negg": [0.3579770624637604, 0.3948354125022888, 0.43406233191490173], "cos_apical_negg": [0.06698261201381683, 0.1468813121318817, 0.25213533639907837], "cos_Ac_negg": [0.35793596506118774, 0.39472973346710205, 0.4339659810066223], "r_norm": [0.24397656321525574, 0.23807041347026825, 0.23590627312660217]}, {"step": 3700, "epoch": 7, "train_loss": 0.02788790501654148, "cos_r_negg": [0.35952135920524597, 0.3989863991737366, 0.44728466868400574], "cos_apical_negg": [0.07870279997587204, 0.14041903614997864, 0.25244852900505066], "cos_Ac_negg": [0.3594464659690857, 0.3988378942012787, 0.4472004771232605], "r_norm": [0.24892956018447876, 0.24216148257255554, 0.2400968372821808]}, {"epoch_end": 7, "step": 3752, "test_acc": 0.9686, "test_loss": 0.13276984481811524}, {"step": 3800, "epoch": 8, "train_loss": 0.02665073610842228, "cos_r_negg": [0.3220789134502411, 0.36207181215286255, 0.4071982502937317], "cos_apical_negg": [0.06650383025407791, 0.11593539267778397, 0.18757429718971252], "cos_Ac_negg": [0.32200467586517334, 0.3619110584259033, 0.4070832133293152], "r_norm": [0.2055143117904663, 0.20011088252067566, 0.19833213090896606]}, {"step": 3900, "epoch": 8, "train_loss": 0.13355880975723267, "cos_r_negg": [0.3140375316143036, 0.3537817597389221, 0.41636207699775696], "cos_apical_negg": [0.061907924711704254, 0.1273750215768814, 0.18623270094394684], "cos_Ac_negg": [0.31402575969696045, 0.3536485731601715, 0.4162844121456146], "r_norm": [0.22917672991752625, 0.22195549309253693, 0.22086377441883087]}, {"step": 4000, "epoch": 8, "train_loss": 0.04349532723426819, "cos_r_negg": [0.31868577003479004, 0.3747909367084503, 0.4304412603378296], "cos_apical_negg": [0.08351548761129379, 0.11740659177303314, 0.20919513702392578], "cos_Ac_negg": [0.31867071986198425, 0.37468305230140686, 0.43036019802093506], "r_norm": [0.20098544657230377, 0.19529084861278534, 0.19426798820495605], "ldr": {"dL_sdil": -0.004782721400260925, "dL_bp": -0.005733594298362732, "ratio": 0.8341576245857969}}, {"step": 4100, "epoch": 8, "train_loss": 0.012566429562866688, "cos_r_negg": [0.3185289800167084, 0.35179272294044495, 0.3757590651512146], "cos_apical_negg": [0.059507105499506, 0.11047831177711487, 0.15767443180084229], "cos_Ac_negg": [0.31850719451904297, 0.35168856382369995, 0.3757178485393524], "r_norm": [0.2059113085269928, 0.20031198859214783, 0.198930025100708]}, {"step": 4200, "epoch": 8, "train_loss": 0.0665077418088913, "cos_r_negg": [0.2978224456310272, 0.33452531695365906, 0.3787321448326111], "cos_apical_negg": [0.06658408045768738, 0.12088974565267563, 0.17964455485343933], "cos_Ac_negg": [0.2977486848831177, 0.3344022035598755, 0.3787045180797577], "r_norm": [0.20869377255439758, 0.20384074747562408, 0.20140281319618225]}, {"epoch_end": 8, "step": 4221, "test_acc": 0.9683, "test_loss": 0.14483663024902343}, {"step": 4300, "epoch": 9, "train_loss": 0.03931870311498642, "cos_r_negg": [0.2826802730560303, 0.33147820830345154, 0.4041232168674469], "cos_apical_negg": [0.06308436393737793, 0.11510062217712402, 0.15491870045661926], "cos_Ac_negg": [0.28264129161834717, 0.33136460185050964, 0.4040958881378174], "r_norm": [0.2176712155342102, 0.21093179285526276, 0.20935454964637756]}, {"step": 4400, "epoch": 9, "train_loss": 0.023374365642666817, "cos_r_negg": [0.3270260691642761, 0.3662740886211395, 0.4073263108730316], "cos_apical_negg": [0.07388993352651596, 0.13460934162139893, 0.1963604986667633], "cos_Ac_negg": [0.32702016830444336, 0.3661465346813202, 0.40726691484451294], "r_norm": [0.22733575105667114, 0.2197837233543396, 0.21842718124389648]}, {"step": 4500, "epoch": 9, "train_loss": 0.12062329053878784, "cos_r_negg": [0.3130398392677307, 0.35118821263313293, 0.40689733624458313], "cos_apical_negg": [0.07170061022043228, 0.13534925878047943, 0.22704070806503296], "cos_Ac_negg": [0.31298938393592834, 0.35103684663772583, 0.4067959785461426], "r_norm": [0.2059287428855896, 0.20092462003231049, 0.19870661199092865], "ldr": {"dL_sdil": -0.005284205079078674, "dL_bp": -0.00652487576007843, "ratio": 0.8098552789938727}}, {"step": 4600, "epoch": 9, "train_loss": 0.024062493816018105, "cos_r_negg": [0.27017152309417725, 0.3290991187095642, 0.35464465618133545], "cos_apical_negg": [0.06068180501461029, 0.10684116184711456, 0.1582408845424652], "cos_Ac_negg": [0.27016592025756836, 0.3290368616580963, 0.3546128571033478], "r_norm": [0.2156028002500534, 0.20901551842689514, 0.20716522634029388]}, {"epoch_end": 9, "step": 4690, "test_acc": 0.9695, "test_loss": 0.14785444831848144}, {"step": 4700, "epoch": 10, "train_loss": 0.008161413483321667, "cos_r_negg": [0.2580244243144989, 0.29799771308898926, 0.33508923649787903], "cos_apical_negg": [0.05917653441429138, 0.10824452340602875, 0.14844365417957306], "cos_Ac_negg": [0.2579764723777771, 0.2978969216346741, 0.3350910246372223], "r_norm": [0.20591787993907928, 0.19990742206573486, 0.1984596848487854]}, {"step": 4800, "epoch": 10, "train_loss": 0.0478949099779129, "cos_r_negg": [0.2587451934814453, 0.31345027685165405, 0.3682030439376831], "cos_apical_negg": [0.06689292192459106, 0.12296228855848312, 0.15581010282039642], "cos_Ac_negg": [0.25869759917259216, 0.3133394420146942, 0.3681696057319641], "r_norm": [0.19997137784957886, 0.1951225996017456, 0.19302034378051758]}, {"step": 4900, "epoch": 10, "train_loss": 0.016231359913945198, "cos_r_negg": [0.2460336834192276, 0.28084877133369446, 0.32604533433914185], "cos_apical_negg": [0.06351970136165619, 0.13150522112846375, 0.12353996932506561], "cos_Ac_negg": [0.2459530234336853, 0.2806828022003174, 0.3260475993156433], "r_norm": [0.23257997632026672, 0.2268572747707367, 0.22457227110862732]}, {"step": 5000, "epoch": 10, "train_loss": 0.006949783768504858, "cos_r_negg": [0.2522090971469879, 0.29522794485092163, 0.33196166157722473], "cos_apical_negg": [0.06330932676792145, 0.11816816031932831, 0.17218172550201416], "cos_Ac_negg": [0.25216856598854065, 0.29511621594429016, 0.33194196224212646], "r_norm": [0.1951100081205368, 0.188955619931221, 0.1878432333469391], "ldr": {"dL_sdil": -0.005989968776702881, "dL_bp": -0.007699951529502869, "ratio": 0.7779229198718879}}, {"step": 5100, "epoch": 10, "train_loss": 0.04045986384153366, "cos_r_negg": [0.27094173431396484, 0.32451125979423523, 0.3775748312473297], "cos_apical_negg": [0.05169527232646942, 0.09858563542366028, 0.18976131081581116], "cos_Ac_negg": [0.2708813548088074, 0.3243916928768158, 0.37751856446266174], "r_norm": [0.1989247053861618, 0.19375018775463104, 0.19190067052841187]}, {"epoch_end": 10, "step": 5159, "test_acc": 0.9693, "test_loss": 0.14779638671875}, {"step": 5200, "epoch": 11, "train_loss": 0.002651508431881666, "cos_r_negg": [0.2496313452720642, 0.28159278631210327, 0.35537096858024597], "cos_apical_negg": [0.04971758648753166, 0.09500518441200256, 0.1748282015323639], "cos_Ac_negg": [0.24960198998451233, 0.2814895510673523, 0.355343759059906], "r_norm": [0.19997933506965637, 0.19511821866035461, 0.19288817048072815]}, {"step": 5300, "epoch": 11, "train_loss": 0.03633364289999008, "cos_r_negg": [0.2568783164024353, 0.29175281524658203, 0.350791871547699], "cos_apical_negg": [0.0692330151796341, 0.09364697337150574, 0.19000670313835144], "cos_Ac_negg": [0.25686150789260864, 0.29163771867752075, 0.35071372985839844], "r_norm": [0.22654028236865997, 0.21995390951633453, 0.2184176743030548]}, {"step": 5400, "epoch": 11, "train_loss": 0.033560846000909805, "cos_r_negg": [0.23786437511444092, 0.2767171561717987, 0.3369234800338745], "cos_apical_negg": [0.050773985683918, 0.09891113638877869, 0.1714353859424591], "cos_Ac_negg": [0.23784521222114563, 0.27660128474235535, 0.33687642216682434], "r_norm": [0.2021322101354599, 0.1962040662765503, 0.19472111761569977]}, {"step": 5500, "epoch": 11, "train_loss": 0.04395921155810356, "cos_r_negg": [0.21185636520385742, 0.26318007707595825, 0.3347349762916565], "cos_apical_negg": [0.08126802742481232, 0.0925680547952652, 0.16087763011455536], "cos_Ac_negg": [0.21180152893066406, 0.26308244466781616, 0.3347211182117462], "r_norm": [0.21441692113876343, 0.20836228132247925, 0.2062130868434906], "ldr": {"dL_sdil": -0.005746632814407349, "dL_bp": -0.008455976843833923, "ratio": 0.6795941995273768}}, {"step": 5600, "epoch": 11, "train_loss": 0.015303989872336388, "cos_r_negg": [0.22986271977424622, 0.2702818512916565, 0.3128160536289215], "cos_apical_negg": [0.050982698798179626, 0.09545817971229553, 0.13293741643428802], "cos_Ac_negg": [0.2298513650894165, 0.27018457651138306, 0.3127765655517578], "r_norm": [0.20144091546535492, 0.19484953582286835, 0.19381265342235565]}, {"epoch_end": 11, "step": 5628, "test_acc": 0.9699, "test_loss": 0.15268256072998046}, {"step": 5700, "epoch": 12, "train_loss": 0.003603791818022728, "cos_r_negg": [0.22636467218399048, 0.2707720994949341, 0.32874518632888794], "cos_apical_negg": [0.04032183811068535, 0.096725694835186, 0.14258968830108643], "cos_Ac_negg": [0.22631829977035522, 0.2706739902496338, 0.3286795914173126], "r_norm": [0.19349460303783417, 0.18741345405578613, 0.18626046180725098]}, {"step": 5800, "epoch": 12, "train_loss": 0.020854540169239044, "cos_r_negg": [0.21486562490463257, 0.2630091905593872, 0.3170546293258667], "cos_apical_negg": [0.06276147067546844, 0.09671137481927872, 0.15367133915424347], "cos_Ac_negg": [0.21481385827064514, 0.26289957761764526, 0.3170144557952881], "r_norm": [0.19152942299842834, 0.18530118465423584, 0.18406842648983002]}, {"step": 5900, "epoch": 12, "train_loss": 0.008579861372709274, "cos_r_negg": [0.23036068677902222, 0.268257200717926, 0.32172608375549316], "cos_apical_negg": [0.04922834411263466, 0.09663659334182739, 0.1473350077867508], "cos_Ac_negg": [0.23033815622329712, 0.2681354880332947, 0.32169950008392334], "r_norm": [0.19517508149147034, 0.18891669809818268, 0.18755337595939636]}, {"step": 6000, "epoch": 12, "train_loss": 0.023891856893897057, "cos_r_negg": [0.21371719241142273, 0.24589970707893372, 0.3007495701313019], "cos_apical_negg": [0.05639013648033142, 0.09345866739749908, 0.1516299694776535], "cos_Ac_negg": [0.21364545822143555, 0.24576793611049652, 0.30071553587913513], "r_norm": [0.19958920776844025, 0.19289015233516693, 0.19160467386245728], "ldr": {"dL_sdil": -0.005817905068397522, "dL_bp": -0.010013014078140259, "ratio": 0.5810343442039877}}, {"epoch_end": 12, "step": 6097, "test_acc": 0.9689, "test_loss": 0.15575114250183106}, {"step": 6100, "epoch": 13, "train_loss": 0.031186243519186974, "cos_r_negg": [0.23160181939601898, 0.2642801105976105, 0.32137686014175415], "cos_apical_negg": [0.06791743636131287, 0.10517482459545135, 0.14122797548770905], "cos_Ac_negg": [0.23152336478233337, 0.2641903758049011, 0.3214069604873657], "r_norm": [0.2154746651649475, 0.2092437744140625, 0.20703613758087158]}, {"step": 6200, "epoch": 13, "train_loss": 0.006884851958602667, "cos_r_negg": [0.2182973176240921, 0.24919408559799194, 0.3115878403186798], "cos_apical_negg": [0.0568549670279026, 0.0780751183629036, 0.12147295475006104], "cos_Ac_negg": [0.2182532548904419, 0.24912229180335999, 0.3115708827972412], "r_norm": [0.19051426649093628, 0.18517754971981049, 0.18321485817432404]}, {"step": 6300, "epoch": 13, "train_loss": 0.03043420985341072, "cos_r_negg": [0.20692133903503418, 0.2380739152431488, 0.2872515916824341], "cos_apical_negg": [0.056095898151397705, 0.09552943706512451, 0.12139946967363358], "cos_Ac_negg": [0.2069166749715805, 0.23799897730350494, 0.2872368395328522], "r_norm": [0.1792515069246292, 0.17412413656711578, 0.17261335253715515]}, {"step": 6400, "epoch": 13, "train_loss": 0.018544811755418777, "cos_r_negg": [0.2081642597913742, 0.24410881102085114, 0.30179691314697266], "cos_apical_negg": [0.05687960609793663, 0.09739081561565399, 0.14163720607757568], "cos_Ac_negg": [0.20812173187732697, 0.24404558539390564, 0.301847904920578], "r_norm": [0.20159514248371124, 0.19521547853946686, 0.19361643493175507]}, {"step": 6500, "epoch": 13, "train_loss": 0.00039314196328632534, "cos_r_negg": [0.1892247200012207, 0.2203974425792694, 0.27506309747695923], "cos_apical_negg": [0.04459456354379654, 0.07980211079120636, 0.13723260164260864], "cos_Ac_negg": [0.1891787201166153, 0.22031477093696594, 0.2750839591026306], "r_norm": [0.18581117689609528, 0.17956629395484924, 0.17843253910541534], "ldr": {"dL_sdil": -0.005495429039001465, "dL_bp": -0.008063137531280518, "ratio": 0.6815497091153707}}, {"epoch_end": 13, "step": 6566, "test_acc": 0.9692, "test_loss": 0.16447142143249513}, {"step": 6600, "epoch": 14, "train_loss": 0.0031038797460496426, "cos_r_negg": [0.19721244275569916, 0.23586884140968323, 0.298753559589386], "cos_apical_negg": [0.05631585419178009, 0.08089663088321686, 0.14550811052322388], "cos_Ac_negg": [0.19716256856918335, 0.23576107621192932, 0.29876089096069336], "r_norm": [0.18716417253017426, 0.18181508779525757, 0.18002164363861084]}, {"step": 6700, "epoch": 14, "train_loss": 0.005571616813540459, "cos_r_negg": [0.19782164692878723, 0.23288075625896454, 0.2836465537548065], "cos_apical_negg": [0.047006845474243164, 0.08577421307563782, 0.14684957265853882], "cos_Ac_negg": [0.19777968525886536, 0.23278269171714783, 0.2836758494377136], "r_norm": [0.19478219747543335, 0.18811435997486115, 0.18674880266189575]}, {"step": 6800, "epoch": 14, "train_loss": 0.024110812693834305, "cos_r_negg": [0.18011140823364258, 0.21659880876541138, 0.26940786838531494], "cos_apical_negg": [0.04869562387466431, 0.08290772140026093, 0.12963669002056122], "cos_Ac_negg": [0.18003004789352417, 0.21650764346122742, 0.2693968415260315], "r_norm": [0.193019300699234, 0.18687675893306732, 0.18526864051818848]}, {"step": 6900, "epoch": 14, "train_loss": 0.024755142629146576, "cos_r_negg": [0.16172689199447632, 0.19865772128105164, 0.26105427742004395], "cos_apical_negg": [0.0629316121339798, 0.08489827811717987, 0.11592637002468109], "cos_Ac_negg": [0.1616540253162384, 0.19857871532440186, 0.2610599994659424], "r_norm": [0.19401678442955017, 0.18787765502929688, 0.18621554970741272]}, {"step": 7000, "epoch": 14, "train_loss": 0.02067204751074314, "cos_r_negg": [0.1930568516254425, 0.23053166270256042, 0.29817941784858704], "cos_apical_negg": [0.05957508087158203, 0.08531548082828522, 0.16373056173324585], "cos_Ac_negg": [0.19296862185001373, 0.2304086685180664, 0.2981274724006653], "r_norm": [0.18739569187164307, 0.1816098988056183, 0.18000106513500214], "ldr": {"dL_sdil": -0.005046382546424866, "dL_bp": -0.00739249587059021, "ratio": 0.682635828922278}}, {"epoch_end": 14, "step": 7035, "test_acc": 0.969, "test_loss": 0.17767958984375}], "final": {"test_acc": 0.969, "test_loss": 0.17767958984375, "wall_s": 42.838538646698, "cos_r_negg": [0.18309010565280914, 0.2141142189502716, 0.2727559804916382], "cos_apical_negg": [0.06834009289741516, 0.08814489841461182, 0.13101357221603394], "cos_Ac_negg": [0.18302752077579498, 0.21398913860321045, 0.27272993326187134]}}
|