Download training_log.jsonl from xwang112358/BioBlobs: direct link, hf CLI and curl.
- Browser
- Download file 298 kB
-
https://huggingface.co/xwang112358/BioBlobs/resolve/main/training_log.jsonl
- Command line
-
hf download hf://xwang112358/BioBlobs/training_log.jsonl
-
curl -L -o training_log.jsonl https://huggingface.co/xwang112358/BioBlobs/resolve/main/training_log.jsonl
298 kB
| {"step": 50, "epoch": 1, "loss": 5.946370601654053, "task_loss": 5.475771903991699, "partitioner_loss": 0.47059887647628784, "running_macro_f1": 0.00034791597886424055, "running_accuracy": 0.0065234375, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 100, "epoch": 1, "loss": 5.95667839050293, "task_loss": 5.48417329788208, "partitioner_loss": 0.4725048840045929, "running_macro_f1": 0.00050786442068872, "running_accuracy": 0.00765625, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 150, "epoch": 1, "loss": 5.943821430206299, "task_loss": 5.468868255615234, "partitioner_loss": 0.47495317459106445, "running_macro_f1": 0.0005306014974525882, "running_accuracy": 0.007265625, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 200, "epoch": 1, "loss": 5.953897953033447, "task_loss": 5.484381198883057, "partitioner_loss": 0.4695168137550354, "running_macro_f1": 0.00027547999415800334, "running_accuracy": 0.0084375, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 250, "epoch": 1, "loss": 5.935414791107178, "task_loss": 5.465215682983398, "partitioner_loss": 0.4701991677284241, "running_macro_f1": 0.0002541952773252354, "running_accuracy": 0.006796875, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 300, "epoch": 1, "loss": 5.965804100036621, "task_loss": 5.4960174560546875, "partitioner_loss": 0.46978676319122314, "running_macro_f1": 0.0003861086984053164, "running_accuracy": 0.0062245537112433445, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 350, "epoch": 1, "loss": 5.926497936248779, "task_loss": 5.453854084014893, "partitioner_loss": 0.4726438820362091, "running_macro_f1": 0.0003475269676178255, "running_accuracy": 0.0059765625, "lr": 2.3e-10, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"epoch": 1, "split": "val", "val_macro_f1": 7.786394907530281e-05, "val_accuracy": 0.00902737332556785} | |
| {"step": 400, "epoch": 2, "loss": 5.570196151733398, "task_loss": 5.556733131408691, "partitioner_loss": 0.013462843373417854, "running_macro_f1": 0.0008959057225538902, "running_accuracy": 0.0064453125, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 450, "epoch": 2, "loss": 5.494950294494629, "task_loss": 5.482285976409912, "partitioner_loss": 0.012664129957556725, "running_macro_f1": 0.002544520020149252, "running_accuracy": 0.0277734375, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 500, "epoch": 2, "loss": 5.353296756744385, "task_loss": 5.339695930480957, "partitioner_loss": 0.013600988313555717, "running_macro_f1": 0.00480351802350981, "running_accuracy": 0.0326171875, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 550, "epoch": 2, "loss": 4.863199234008789, "task_loss": 4.848926067352295, "partitioner_loss": 0.014273107051849365, "running_macro_f1": 0.007820298412910027, "running_accuracy": 0.040390625, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 600, "epoch": 2, "loss": 4.751924514770508, "task_loss": 4.737266540527344, "partitioner_loss": 0.014658160507678986, "running_macro_f1": 0.013345707429723847, "running_accuracy": 0.05774350140933292, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 650, "epoch": 2, "loss": 4.712491989135742, "task_loss": 4.693803310394287, "partitioner_loss": 0.018688563257455826, "running_macro_f1": 0.01621370346953617, "running_accuracy": 0.0415234375, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 700, "epoch": 2, "loss": 2.9014713764190674, "task_loss": 2.8560631275177, "partitioner_loss": 0.045408353209495544, "running_macro_f1": 0.03224007875152383, "running_accuracy": 0.0972265625, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"step": 750, "epoch": 2, "loss": 4.322027206420898, "task_loss": 4.28126335144043, "partitioner_loss": 0.040764082223176956, "running_macro_f1": 0.04422718008392105, "running_accuracy": 0.1134375, "lr": 0.00023, "codebook_loss": 0.0, "codebook_perplexity": 0.0, "codebook_active": 0.0, "codebook_commit": null} | |
| {"epoch": 2, "split": "val", "val_macro_f1": 0.023522300045937528, "val_accuracy": 0.051349252572316054} | |
| {"step": 800, "epoch": 3, "loss": 4.745540618896484, "task_loss": 4.677987098693848, "partitioner_loss": 0.04934784024953842, "running_macro_f1": 0.029921387072079142, "running_accuracy": 0.0766796875, "lr": 0.0002299421023740663, "codebook_loss": 0.072822704911232, "codebook_perplexity": 1.0, "codebook_active": 1.0, "codebook_commit": 0.291290819644928} | |
| {"step": 850, "epoch": 3, "loss": 3.3287746906280518, "task_loss": 3.268510580062866, "partitioner_loss": 0.044382959604263306, "running_macro_f1": 0.045772281075848534, "running_accuracy": 0.1163671875, "lr": 0.0002299421023740663, "codebook_loss": 0.06352463364601135, "codebook_perplexity": 1.0, "codebook_active": 1.0, "codebook_commit": 0.2540985345840454} | |
| {"step": 900, "epoch": 3, "loss": 3.1902055740356445, "task_loss": 3.1196296215057373, "partitioner_loss": 0.05548807978630066, "running_macro_f1": 0.04940224536969267, "running_accuracy": 0.1156640625, "lr": 0.0002299421023740663, "codebook_loss": 0.060351770371198654, "codebook_perplexity": 1.0, "codebook_active": 1.0, "codebook_commit": 0.24140708148479462} | |
| {"step": 950, "epoch": 3, "loss": 4.148188591003418, "task_loss": 4.092403411865234, "partitioner_loss": 0.040991321206092834, "running_macro_f1": 0.0560100893953405, "running_accuracy": 0.1532421875, "lr": 0.0002299421023740663, "codebook_loss": 0.059175945818424225, "codebook_perplexity": 1.0, "codebook_active": 1.0, "codebook_commit": 0.2367037832736969} | |
| {"step": 1000, "epoch": 3, "loss": 3.9714462757110596, "task_loss": 3.9086365699768066, "partitioner_loss": 0.049852870404720306, "running_macro_f1": 0.08577983357659412, "running_accuracy": 0.1969934231130598, "lr": 0.0002299421023740663, "codebook_loss": 0.051827140152454376, "codebook_perplexity": 1.0, "codebook_active": 1.0, "codebook_commit": 0.2073085606098175} | |
| {"step": 1050, "epoch": 3, "loss": 3.032819986343384, "task_loss": 2.959179639816284, "partitioner_loss": 0.06200307607650757, "running_macro_f1": 0.11492595381402423, "running_accuracy": 0.2559375, "lr": 0.0002299421023740663, "codebook_loss": 0.046549201011657715, "codebook_perplexity": 27.185270309448242, "codebook_active": 66.0, "codebook_commit": 0.18619680404663086} | |
| {"step": 1100, "epoch": 3, "loss": 2.359062910079956, "task_loss": 2.2891385555267334, "partitioner_loss": 0.057373832911252975, "running_macro_f1": 0.12045358384066143, "running_accuracy": 0.2897265625, "lr": 0.0002299421023740663, "codebook_loss": 0.050202541053295135, "codebook_perplexity": 56.7814826965332, "codebook_active": 153.0, "codebook_commit": 0.20081016421318054} | |
| {"epoch": 3, "split": "val", "val_macro_f1": 0.04929801387536564, "val_accuracy": 0.09289458357600466} | |
| {"step": 1150, "epoch": 4, "loss": 2.4731850624084473, "task_loss": 2.41363787651062, "partitioner_loss": 0.0500442236661911, "running_macro_f1": 0.1556431700339807, "running_accuracy": 0.3199609375, "lr": 0.00022976846779426672, "codebook_loss": 0.03801192343235016, "codebook_perplexity": 190.92044067382812, "codebook_active": 407.0, "codebook_commit": 0.15204769372940063} | |
| {"step": 1200, "epoch": 4, "loss": 2.159519672393799, "task_loss": 2.0879080295562744, "partitioner_loss": 0.06329278647899628, "running_macro_f1": 0.17646639158741126, "running_accuracy": 0.3580097087378641, "lr": 0.00022976846779426672, "codebook_loss": 0.033275630325078964, "codebook_perplexity": 186.95294189453125, "codebook_active": 461.0, "codebook_commit": 0.13310252130031586} | |
| {"step": 1250, "epoch": 4, "loss": 1.943405270576477, "task_loss": 1.8707013130187988, "partitioner_loss": 0.06313550472259521, "running_macro_f1": 0.19187134103190226, "running_accuracy": 0.398125, "lr": 0.00022976846779426672, "codebook_loss": 0.03827383369207382, "codebook_perplexity": 80.74371337890625, "codebook_active": 180.0, "codebook_commit": 0.1530953347682953} | |
| {"step": 1300, "epoch": 4, "loss": 3.1527016162872314, "task_loss": 3.076145887374878, "partitioner_loss": 0.06383918225765228, "running_macro_f1": 0.2141395326902025, "running_accuracy": 0.4202734375, "lr": 0.00022976846779426672, "codebook_loss": 0.050865963101387024, "codebook_perplexity": 71.91981506347656, "codebook_active": 149.0, "codebook_commit": 0.2034638524055481} | |
| {"step": 1350, "epoch": 4, "loss": 3.250349283218384, "task_loss": 3.179659843444824, "partitioner_loss": 0.05907842516899109, "running_macro_f1": 0.231203787637522, "running_accuracy": 0.417109375, "lr": 0.00022976846779426672, "codebook_loss": 0.04644390940666199, "codebook_perplexity": 81.06275939941406, "codebook_active": 158.0, "codebook_commit": 0.18577563762664795} | |
| {"step": 1400, "epoch": 4, "loss": 1.655790090560913, "task_loss": 1.5846604108810425, "partitioner_loss": 0.061427854001522064, "running_macro_f1": 0.23781820484243427, "running_accuracy": 0.4606640625, "lr": 0.00022976846779426672, "codebook_loss": 0.038807451725006104, "codebook_perplexity": 91.556640625, "codebook_active": 200.0, "codebook_commit": 0.15522980690002441} | |
| {"step": 1450, "epoch": 4, "loss": 2.093055009841919, "task_loss": 2.018383741378784, "partitioner_loss": 0.0632411539554596, "running_macro_f1": 0.23555903924063937, "running_accuracy": 0.425859375, "lr": 0.00022976846779426672, "codebook_loss": 0.045719921588897705, "codebook_perplexity": 66.95466613769531, "codebook_active": 154.0, "codebook_commit": 0.18287968635559082} | |
| {"step": 1500, "epoch": 4, "loss": 2.7480244636535645, "task_loss": 2.681201934814453, "partitioner_loss": 0.05420135706663132, "running_macro_f1": 0.2613831600064996, "running_accuracy": 0.493828125, "lr": 0.00022976846779426672, "codebook_loss": 0.05048435926437378, "codebook_perplexity": 93.34364318847656, "codebook_active": 193.0, "codebook_commit": 0.20193743705749512} | |
| {"epoch": 4, "split": "val", "val_macro_f1": 0.146273042812207, "val_accuracy": 0.30033003300330036} | |
| {"step": 1550, "epoch": 5, "loss": 1.3997581005096436, "task_loss": 1.3275812864303589, "partitioner_loss": 0.062083855271339417, "running_macro_f1": 0.28153455352673235, "running_accuracy": 0.5257421875, "lr": 0.00022947927109590475, "codebook_loss": 0.04037170857191086, "codebook_perplexity": 96.5466537475586, "codebook_active": 240.0, "codebook_commit": 0.16148683428764343} | |
| {"step": 1600, "epoch": 5, "loss": 2.492664337158203, "task_loss": 2.4092726707458496, "partitioner_loss": 0.07316042482852936, "running_macro_f1": 0.30714804780117927, "running_accuracy": 0.5576171875, "lr": 0.00022947927109590475, "codebook_loss": 0.040925316512584686, "codebook_perplexity": 154.55001831054688, "codebook_active": 279.0, "codebook_commit": 0.16370126605033875} | |
| {"step": 1650, "epoch": 5, "loss": 1.4691829681396484, "task_loss": 1.391951322555542, "partitioner_loss": 0.06795652210712433, "running_macro_f1": 0.3045766219406705, "running_accuracy": 0.5419921875, "lr": 0.00022947927109590475, "codebook_loss": 0.03710038959980011, "codebook_perplexity": 72.17352294921875, "codebook_active": 196.0, "codebook_commit": 0.14840155839920044} | |
| {"step": 1700, "epoch": 5, "loss": 2.516294479370117, "task_loss": 2.4487855434417725, "partitioner_loss": 0.060846008360385895, "running_macro_f1": 0.33863210729727494, "running_accuracy": 0.6087926714688381, "lr": 0.00022947927109590475, "codebook_loss": 0.026651054620742798, "codebook_perplexity": 302.8975524902344, "codebook_active": 489.0, "codebook_commit": 0.10660421848297119} | |
| {"step": 1750, "epoch": 5, "loss": 1.634484887123108, "task_loss": 1.5601476430892944, "partitioner_loss": 0.06508766859769821, "running_macro_f1": 0.3141062719092652, "running_accuracy": 0.5772265625, "lr": 0.00022947927109590475, "codebook_loss": 0.03699842840433121, "codebook_perplexity": 122.96891784667969, "codebook_active": 254.0, "codebook_commit": 0.14799371361732483} | |
| {"step": 1800, "epoch": 5, "loss": 1.183197259902954, "task_loss": 1.1053645610809326, "partitioner_loss": 0.06982110440731049, "running_macro_f1": 0.32919792286097627, "running_accuracy": 0.59125, "lr": 0.00022947927109590475, "codebook_loss": 0.03204631805419922, "codebook_perplexity": 101.0655517578125, "codebook_active": 221.0, "codebook_commit": 0.12818527221679688} | |
| {"step": 1850, "epoch": 5, "loss": 1.155734658241272, "task_loss": 1.0803061723709106, "partitioner_loss": 0.06637837737798691, "running_macro_f1": 0.3605525337634637, "running_accuracy": 0.628671875, "lr": 0.00022947927109590475, "codebook_loss": 0.036200400441884995, "codebook_perplexity": 119.85395812988281, "codebook_active": 250.0, "codebook_commit": 0.14480160176753998} | |
| {"epoch": 5, "split": "val", "val_macro_f1": 0.18379969939002572, "val_accuracy": 0.3670161133760435} | |
| {"step": 1900, "epoch": 6, "loss": 1.0686990022659302, "task_loss": 0.998137891292572, "partitioner_loss": 0.062304481863975525, "running_macro_f1": 0.36814987490202544, "running_accuracy": 0.6585546875, "lr": 0.00022907480347554148, "codebook_loss": 0.03302677720785141, "codebook_perplexity": 126.31315612792969, "codebook_active": 247.0, "codebook_commit": 0.13210710883140564} | |
| {"step": 1950, "epoch": 6, "loss": 0.7938200235366821, "task_loss": 0.7349227666854858, "partitioner_loss": 0.049641985446214676, "running_macro_f1": 0.41273898561176225, "running_accuracy": 0.6863671875, "lr": 0.00022907480347554148, "codebook_loss": 0.03702118247747421, "codebook_perplexity": 117.10433959960938, "codebook_active": 222.0, "codebook_commit": 0.14808472990989685} | |
| {"step": 2000, "epoch": 6, "loss": 0.9283822178840637, "task_loss": 0.8666094541549683, "partitioner_loss": 0.053375326097011566, "running_macro_f1": 0.38331532852547334, "running_accuracy": 0.640625, "lr": 0.00022907480347554148, "codebook_loss": 0.033589936792850494, "codebook_perplexity": 88.0172119140625, "codebook_active": 228.0, "codebook_commit": 0.13435974717140198} | |
| {"step": 2050, "epoch": 6, "loss": 1.2213165760040283, "task_loss": 1.1535006761550903, "partitioner_loss": 0.05962420627474785, "running_macro_f1": 0.3780163253916952, "running_accuracy": 0.6585499530222362, "lr": 0.00022907480347554148, "codebook_loss": 0.03276669979095459, "codebook_perplexity": 109.04691314697266, "codebook_active": 224.0, "codebook_commit": 0.13106679916381836} | |
| {"step": 2100, "epoch": 6, "loss": 1.0888651609420776, "task_loss": 1.015980839729309, "partitioner_loss": 0.06561709940433502, "running_macro_f1": 0.3748154612305365, "running_accuracy": 0.6522265625, "lr": 0.00022907480347554148, "codebook_loss": 0.02906882017850876, "codebook_perplexity": 205.72955322265625, "codebook_active": 395.0, "codebook_commit": 0.11627528071403503} | |
| {"step": 2150, "epoch": 6, "loss": 1.8876631259918213, "task_loss": 1.8139894008636475, "partitioner_loss": 0.06416831910610199, "running_macro_f1": 0.4009373426803585, "running_accuracy": 0.692421875, "lr": 0.00022907480347554148, "codebook_loss": 0.03802156448364258, "codebook_perplexity": 120.07476043701172, "codebook_active": 252.0, "codebook_commit": 0.1520862579345703} | |
| {"step": 2200, "epoch": 6, "loss": 0.8303743004798889, "task_loss": 0.7568694353103638, "partitioner_loss": 0.0657605528831482, "running_macro_f1": 0.39496674279572913, "running_accuracy": 0.6748828125, "lr": 0.00022907480347554148, "codebook_loss": 0.030977321788668633, "codebook_perplexity": 113.54732513427734, "codebook_active": 277.0, "codebook_commit": 0.12390928715467453} | |
| {"step": 2250, "epoch": 6, "loss": 2.0827157497406006, "task_loss": 2.01949405670166, "partitioner_loss": 0.054267168045043945, "running_macro_f1": 0.39337144247693434, "running_accuracy": 0.6607421875, "lr": 0.00022907480347554148, "codebook_loss": 0.03581816703081131, "codebook_perplexity": 106.6694107055664, "codebook_active": 218.0, "codebook_commit": 0.14327266812324524} | |
| {"epoch": 6, "split": "val", "val_macro_f1": 0.20765003716041278, "val_accuracy": 0.3984663172199573} | |
| {"step": 2300, "epoch": 7, "loss": 1.497503638267517, "task_loss": 1.4344873428344727, "partitioner_loss": 0.054062776267528534, "running_macro_f1": 0.39556231111203527, "running_accuracy": 0.6887890625, "lr": 0.00022855547219778534, "codebook_loss": 0.035814493894577026, "codebook_perplexity": 107.82489776611328, "codebook_active": 223.0, "codebook_commit": 0.1432579755783081} | |
| {"step": 2350, "epoch": 7, "loss": 0.8556468486785889, "task_loss": 0.7929239869117737, "partitioner_loss": 0.05282212421298027, "running_macro_f1": 0.43409722434709874, "running_accuracy": 0.7426171875, "lr": 0.00022855547219778534, "codebook_loss": 0.03960307314991951, "codebook_perplexity": 118.20731353759766, "codebook_active": 249.0, "codebook_commit": 0.15841229259967804} | |
| {"step": 2400, "epoch": 7, "loss": 0.8127869963645935, "task_loss": 0.7467331886291504, "partitioner_loss": 0.05846140533685684, "running_macro_f1": 0.42866912989475303, "running_accuracy": 0.7222439711869715, "lr": 0.00022855547219778534, "codebook_loss": 0.030369512736797333, "codebook_perplexity": 122.44442749023438, "codebook_active": 286.0, "codebook_commit": 0.12147805094718933} | |
| {"step": 2450, "epoch": 7, "loss": 0.8696414828300476, "task_loss": 0.8083682060241699, "partitioner_loss": 0.05183207988739014, "running_macro_f1": 0.438782822129017, "running_accuracy": 0.711875, "lr": 0.00022855547219778534, "codebook_loss": 0.03776488080620766, "codebook_perplexity": 132.3104248046875, "codebook_active": 267.0, "codebook_commit": 0.15105952322483063} | |
| {"step": 2500, "epoch": 7, "loss": 1.034279227256775, "task_loss": 0.9620295763015747, "partitioner_loss": 0.06353070586919785, "running_macro_f1": 0.42362738528300825, "running_accuracy": 0.6968359375, "lr": 0.00022855547219778534, "codebook_loss": 0.03487585484981537, "codebook_perplexity": 117.06626892089844, "codebook_active": 232.0, "codebook_commit": 0.13950341939926147} | |
| {"step": 2550, "epoch": 7, "loss": 1.6604015827178955, "task_loss": 1.577841877937317, "partitioner_loss": 0.07283288985490799, "running_macro_f1": 0.42715342738100237, "running_accuracy": 0.716484375, "lr": 0.00022855547219778534, "codebook_loss": 0.038906872272491455, "codebook_perplexity": 95.99578857421875, "codebook_active": 219.0, "codebook_commit": 0.15562748908996582} | |
| {"step": 2600, "epoch": 7, "loss": 0.7362223863601685, "task_loss": 0.6717959046363831, "partitioner_loss": 0.05559581518173218, "running_macro_f1": 0.43673029177271294, "running_accuracy": 0.734375, "lr": 0.00022855547219778534, "codebook_loss": 0.03532274067401886, "codebook_perplexity": 125.20773315429688, "codebook_active": 247.0, "codebook_commit": 0.14129096269607544} | |
| {"epoch": 7, "split": "val", "val_macro_f1": 0.2265534724614902, "val_accuracy": 0.36342457775189285} | |
| {"step": 2650, "epoch": 8, "loss": 0.5353257656097412, "task_loss": 0.4724207818508148, "partitioner_loss": 0.05336587131023407, "running_macro_f1": 0.42976844402797004, "running_accuracy": 0.7283203125, "lr": 0.00022792180018521127, "codebook_loss": 0.038156501948833466, "codebook_perplexity": 137.74295043945312, "codebook_active": 260.0, "codebook_commit": 0.15262600779533386} | |
| {"step": 2700, "epoch": 8, "loss": 1.355290412902832, "task_loss": 1.2872951030731201, "partitioner_loss": 0.059106506407260895, "running_macro_f1": 0.4271926157970511, "running_accuracy": 0.7053515625, "lr": 0.00022792180018521127, "codebook_loss": 0.03555542230606079, "codebook_perplexity": 83.14583587646484, "codebook_active": 183.0, "codebook_commit": 0.14222168922424316} | |
| {"step": 2750, "epoch": 8, "loss": 1.432646632194519, "task_loss": 1.3645274639129639, "partitioner_loss": 0.05971290543675423, "running_macro_f1": 0.44459648719321676, "running_accuracy": 0.7206640625, "lr": 0.00022792180018521127, "codebook_loss": 0.03362501785159111, "codebook_perplexity": 37.72159957885742, "codebook_active": 119.0, "codebook_commit": 0.13450007140636444} | |
| {"step": 2800, "epoch": 8, "loss": 0.7104718685150146, "task_loss": 0.6408912539482117, "partitioner_loss": 0.06132199615240097, "running_macro_f1": 0.46086282839032583, "running_accuracy": 0.7549326652051362, "lr": 0.00022792180018521127, "codebook_loss": 0.033034637570381165, "codebook_perplexity": 119.06837463378906, "codebook_active": 261.0, "codebook_commit": 0.13213855028152466} | |
| {"step": 2850, "epoch": 8, "loss": 1.1244311332702637, "task_loss": 1.0587106943130493, "partitioner_loss": 0.05574033409357071, "running_macro_f1": 0.44775333536635975, "running_accuracy": 0.7344921875, "lr": 0.00022792180018521127, "codebook_loss": 0.03992015868425369, "codebook_perplexity": 132.86996459960938, "codebook_active": 278.0, "codebook_commit": 0.15968063473701477} | |
| {"step": 2900, "epoch": 8, "loss": 1.6100765466690063, "task_loss": 1.5408421754837036, "partitioner_loss": 0.05955573916435242, "running_macro_f1": 0.47367373584042494, "running_accuracy": 0.7519140625, "lr": 0.00022792180018521127, "codebook_loss": 0.03871454298496246, "codebook_perplexity": 114.54342651367188, "codebook_active": 252.0, "codebook_commit": 0.15485817193984985} | |
| {"step": 2950, "epoch": 8, "loss": 2.0506155490875244, "task_loss": 1.9857186079025269, "partitioner_loss": 0.054967425763607025, "running_macro_f1": 0.4810438358516555, "running_accuracy": 0.757890625, "lr": 0.00022792180018521127, "codebook_loss": 0.0397176630795002, "codebook_perplexity": 103.69241333007812, "codebook_active": 241.0, "codebook_commit": 0.1588706523180008} | |
| {"step": 3000, "epoch": 8, "loss": 1.1098453998565674, "task_loss": 1.0430301427841187, "partitioner_loss": 0.058403871953487396, "running_macro_f1": 0.47882541854428295, "running_accuracy": 0.774375, "lr": 0.00022792180018521127, "codebook_loss": 0.03364570438861847, "codebook_perplexity": 139.5836944580078, "codebook_active": 257.0, "codebook_commit": 0.13458281755447388} | |
| {"epoch": 8, "split": "val", "val_macro_f1": 0.23000766328787067, "val_accuracy": 0.4396233741021161} | |
| {"step": 3050, "epoch": 9, "loss": 0.9621619582176208, "task_loss": 0.8998947143554688, "partitioner_loss": 0.051863472908735275, "running_macro_f1": 0.4741762984468857, "running_accuracy": 0.771640625, "lr": 0.00022717442549182183, "codebook_loss": 0.041614945977926254, "codebook_perplexity": 88.42888641357422, "codebook_active": 226.0, "codebook_commit": 0.16645978391170502} | |
| {"step": 3100, "epoch": 9, "loss": 0.717353105545044, "task_loss": 0.6502532362937927, "partitioner_loss": 0.05870649218559265, "running_macro_f1": 0.49571421447096137, "running_accuracy": 0.7830078125, "lr": 0.00022717442549182183, "codebook_loss": 0.0335737019777298, "codebook_perplexity": 96.47450256347656, "codebook_active": 198.0, "codebook_commit": 0.1342948079109192} | |
| {"step": 3150, "epoch": 9, "loss": 0.8540711402893066, "task_loss": 0.7959311604499817, "partitioner_loss": 0.048031602054834366, "running_macro_f1": 0.4820078681651236, "running_accuracy": 0.7761328125, "lr": 0.00022717442549182183, "codebook_loss": 0.04043346643447876, "codebook_perplexity": 106.99385833740234, "codebook_active": 243.0, "codebook_commit": 0.16173386573791504} | |
| {"step": 3200, "epoch": 9, "loss": 1.6817052364349365, "task_loss": 1.597382664680481, "partitioner_loss": 0.07505248486995697, "running_macro_f1": 0.5011377266339648, "running_accuracy": 0.7753125, "lr": 0.00022717442549182183, "codebook_loss": 0.03708018362522125, "codebook_perplexity": 81.38429260253906, "codebook_active": 180.0, "codebook_commit": 0.148320734500885} | |
| {"step": 3250, "epoch": 9, "loss": 0.5639029145240784, "task_loss": 0.49835634231567383, "partitioner_loss": 0.058301523327827454, "running_macro_f1": 0.48893563791852823, "running_accuracy": 0.7817882868775446, "lr": 0.00022717442549182183, "codebook_loss": 0.028980150818824768, "codebook_perplexity": 122.33855438232422, "codebook_active": 272.0, "codebook_commit": 0.11592060327529907} | |
| {"step": 3300, "epoch": 9, "loss": 1.8605742454528809, "task_loss": 1.791102647781372, "partitioner_loss": 0.05933259427547455, "running_macro_f1": 0.46466724429518663, "running_accuracy": 0.780078125, "lr": 0.00022717442549182183, "codebook_loss": 0.0405561625957489, "codebook_perplexity": 48.948081970214844, "codebook_active": 138.0, "codebook_commit": 0.1622246503829956} | |
| {"step": 3350, "epoch": 9, "loss": 0.942996621131897, "task_loss": 0.8808513879776001, "partitioner_loss": 0.052954576909542084, "running_macro_f1": 0.5125959531397253, "running_accuracy": 0.784140625, "lr": 0.00022717442549182183, "codebook_loss": 0.03676266595721245, "codebook_perplexity": 131.33262634277344, "codebook_active": 286.0, "codebook_commit": 0.1470506638288498} | |
| {"step": 3400, "epoch": 9, "loss": 1.0342148542404175, "task_loss": 0.9740073680877686, "partitioner_loss": 0.0518466979265213, "running_macro_f1": 0.48249090065144234, "running_accuracy": 0.776015625, "lr": 0.00022717442549182183, "codebook_loss": 0.0334428995847702, "codebook_perplexity": 138.6895751953125, "codebook_active": 272.0, "codebook_commit": 0.1337715983390808} | |
| {"epoch": 9, "split": "val", "val_macro_f1": 0.24630628507288213, "val_accuracy": 0.4602019025431955} | |
| {"step": 3450, "epoch": 10, "loss": 0.5444261431694031, "task_loss": 0.48007211089134216, "partitioner_loss": 0.05675002187490463, "running_macro_f1": 0.5062374342110441, "running_accuracy": 0.801796875, "lr": 0.000226314100660581, "codebook_loss": 0.030416077002882957, "codebook_perplexity": 122.33903503417969, "codebook_active": 276.0, "codebook_commit": 0.12166430801153183} | |
| {"step": 3500, "epoch": 10, "loss": 1.5600531101226807, "task_loss": 1.4990237951278687, "partitioner_loss": 0.0532696470618248, "running_macro_f1": 0.5305322010380409, "running_accuracy": 0.823984375, "lr": 0.000226314100660581, "codebook_loss": 0.031038818880915642, "codebook_perplexity": 146.64437866210938, "codebook_active": 296.0, "codebook_commit": 0.12415527552366257} | |
| {"step": 3550, "epoch": 10, "loss": 0.5430906414985657, "task_loss": 0.48032885789871216, "partitioner_loss": 0.05436112731695175, "running_macro_f1": 0.5146278486757941, "running_accuracy": 0.8004296875, "lr": 0.000226314100660581, "codebook_loss": 0.03360270708799362, "codebook_perplexity": 120.01499938964844, "codebook_active": 248.0, "codebook_commit": 0.1344108283519745} | |
| {"step": 3600, "epoch": 10, "loss": 0.8610647320747375, "task_loss": 0.7964497208595276, "partitioner_loss": 0.05657587945461273, "running_macro_f1": 0.5158777949520799, "running_accuracy": 0.8007421875, "lr": 0.000226314100660581, "codebook_loss": 0.03215646743774414, "codebook_perplexity": 134.3596649169922, "codebook_active": 289.0, "codebook_commit": 0.12862586975097656} | |
| {"step": 3650, "epoch": 10, "loss": 1.0605329275131226, "task_loss": 1.004372239112854, "partitioner_loss": 0.046938829123973846, "running_macro_f1": 0.5083377264022682, "running_accuracy": 0.8009375, "lr": 0.000226314100660581, "codebook_loss": 0.03688760846853256, "codebook_perplexity": 58.64510726928711, "codebook_active": 132.0, "codebook_commit": 0.14755043387413025} | |
| {"step": 3700, "epoch": 10, "loss": 0.7741259336471558, "task_loss": 0.7123323082923889, "partitioner_loss": 0.05238153785467148, "running_macro_f1": 0.4959799120512593, "running_accuracy": 0.7780078125, "lr": 0.000226314100660581, "codebook_loss": 0.03764842450618744, "codebook_perplexity": 140.1646270751953, "codebook_active": 268.0, "codebook_commit": 0.15059369802474976} | |
| {"step": 3750, "epoch": 10, "loss": 0.8015251159667969, "task_loss": 0.744364857673645, "partitioner_loss": 0.04690210521221161, "running_macro_f1": 0.5112835675348825, "running_accuracy": 0.7968359375, "lr": 0.000226314100660581, "codebook_loss": 0.04103262722492218, "codebook_perplexity": 91.00190734863281, "codebook_active": 177.0, "codebook_commit": 0.16413050889968872} | |
| {"epoch": 10, "split": "val", "val_macro_f1": 0.27804842998688256, "val_accuracy": 0.5365948359541837} | |
| {"step": 3800, "epoch": 11, "loss": 1.2311327457427979, "task_loss": 1.1685501337051392, "partitioner_loss": 0.05270230025053024, "running_macro_f1": 0.5080011664844805, "running_accuracy": 0.8093485750078296, "lr": 0.00022534169196566722, "codebook_loss": 0.039521291851997375, "codebook_perplexity": 107.83065795898438, "codebook_active": 210.0, "codebook_commit": 0.1580851674079895} | |
| {"step": 3850, "epoch": 11, "loss": 0.6514888405799866, "task_loss": 0.5830865502357483, "partitioner_loss": 0.061386704444885254, "running_macro_f1": 0.535544234842108, "running_accuracy": 0.832109375, "lr": 0.00022534169196566722, "codebook_loss": 0.028062377125024796, "codebook_perplexity": 72.24655151367188, "codebook_active": 193.0, "codebook_commit": 0.11224950850009918} | |
| {"step": 3900, "epoch": 11, "loss": 0.5862264633178711, "task_loss": 0.5148236751556396, "partitioner_loss": 0.06368862092494965, "running_macro_f1": 0.501022395081936, "running_accuracy": 0.8135546875, "lr": 0.00022534169196566722, "codebook_loss": 0.030856501311063766, "codebook_perplexity": 161.38189697265625, "codebook_active": 294.0, "codebook_commit": 0.12342600524425507} | |
| {"step": 3950, "epoch": 11, "loss": 0.9043617248535156, "task_loss": 0.8354160189628601, "partitioner_loss": 0.06141522154211998, "running_macro_f1": 0.5018933700557884, "running_accuracy": 0.79734375, "lr": 0.00022534169196566722, "codebook_loss": 0.030122144147753716, "codebook_perplexity": 64.6396484375, "codebook_active": 150.0, "codebook_commit": 0.12048857659101486} | |
| {"step": 4000, "epoch": 11, "loss": 0.5869062542915344, "task_loss": 0.5249492526054382, "partitioner_loss": 0.05340404063463211, "running_macro_f1": 0.5243143814748874, "running_accuracy": 0.81640625, "lr": 0.00022534169196566722, "codebook_loss": 0.034211866557598114, "codebook_perplexity": 171.2574462890625, "codebook_active": 313.0, "codebook_commit": 0.13684746623039246} | |
| {"step": 4050, "epoch": 11, "loss": 1.1206756830215454, "task_loss": 1.0555604696273804, "partitioner_loss": 0.05308717116713524, "running_macro_f1": 0.5022813512696914, "running_accuracy": 0.7963122455371124, "lr": 0.00022534169196566722, "codebook_loss": 0.048112545162439346, "codebook_perplexity": 120.81610107421875, "codebook_active": 233.0, "codebook_commit": 0.19245018064975739} | |
| {"step": 4100, "epoch": 11, "loss": 0.5867599844932556, "task_loss": 0.5279970765113831, "partitioner_loss": 0.0507814884185791, "running_macro_f1": 0.555464377091831, "running_accuracy": 0.8355859375, "lr": 0.00022534169196566722, "codebook_loss": 0.0319257453083992, "codebook_perplexity": 98.54095458984375, "codebook_active": 260.0, "codebook_commit": 0.1277029812335968} | |
| {"step": 4150, "epoch": 11, "loss": 0.6657342910766602, "task_loss": 0.6030286550521851, "partitioner_loss": 0.05493273213505745, "running_macro_f1": 0.5277168357935957, "running_accuracy": 0.788125, "lr": 0.00022534169196566722, "codebook_loss": 0.031091731041669846, "codebook_perplexity": 109.0174789428711, "codebook_active": 268.0, "codebook_commit": 0.12436692416667938} | |
| {"epoch": 11, "split": "val", "val_macro_f1": 0.28296555921201094, "val_accuracy": 0.5075713453698311} | |
| {"step": 4200, "epoch": 12, "loss": 1.2188332080841064, "task_loss": 1.1616605520248413, "partitioner_loss": 0.04809156060218811, "running_macro_f1": 0.5299343654533415, "running_accuracy": 0.81328125, "lr": 0.0002242581785402087, "codebook_loss": 0.03632457181811333, "codebook_perplexity": 58.23838424682617, "codebook_active": 150.0, "codebook_commit": 0.1452982872724533} | |
| {"step": 4250, "epoch": 12, "loss": 1.3234025239944458, "task_loss": 1.2638441324234009, "partitioner_loss": 0.0495433583855629, "running_macro_f1": 0.5305512092650434, "running_accuracy": 0.820625, "lr": 0.0002242581785402087, "codebook_loss": 0.040060222148895264, "codebook_perplexity": 101.8304443359375, "codebook_active": 248.0, "codebook_commit": 0.16024088859558105} | |
| {"step": 4300, "epoch": 12, "loss": 0.918895959854126, "task_loss": 0.807074248790741, "partitioner_loss": 0.10416672378778458, "running_macro_f1": 0.5643627984286785, "running_accuracy": 0.81625, "lr": 0.0002242581785402087, "codebook_loss": 0.03061997890472412, "codebook_perplexity": 103.4260482788086, "codebook_active": 282.0, "codebook_commit": 0.12247991561889648} | |
| {"step": 4350, "epoch": 12, "loss": 0.7467291355133057, "task_loss": 0.6784690022468567, "partitioner_loss": 0.06026361137628555, "running_macro_f1": 0.5664618756169292, "running_accuracy": 0.8422265625, "lr": 0.0002242581785402087, "codebook_loss": 0.03198590874671936, "codebook_perplexity": 154.7185821533203, "codebook_active": 295.0, "codebook_commit": 0.12794363498687744} | |
| {"step": 4400, "epoch": 12, "loss": 1.4651646614074707, "task_loss": 1.3797801733016968, "partitioner_loss": 0.07407909631729126, "running_macro_f1": 0.5813456687252104, "running_accuracy": 0.8475, "lr": 0.0002242581785402087, "codebook_loss": 0.045221347361803055, "codebook_perplexity": 29.28116798400879, "codebook_active": 96.0, "codebook_commit": 0.18088538944721222} | |
| {"step": 4450, "epoch": 12, "loss": 0.3854336738586426, "task_loss": 0.31802329421043396, "partitioner_loss": 0.0594477541744709, "running_macro_f1": 0.5539026700162603, "running_accuracy": 0.8483984375, "lr": 0.0002242581785402087, "codebook_loss": 0.03185040503740311, "codebook_perplexity": 131.5989227294922, "codebook_active": 294.0, "codebook_commit": 0.12740162014961243} | |
| {"step": 4500, "epoch": 12, "loss": 0.5525310635566711, "task_loss": 0.4922023415565491, "partitioner_loss": 0.05227699130773544, "running_macro_f1": 0.5405405235494677, "running_accuracy": 0.8231640625, "lr": 0.0002242581785402087, "codebook_loss": 0.03220709413290024, "codebook_perplexity": 131.48941040039062, "codebook_active": 298.0, "codebook_commit": 0.12882837653160095} | |
| {"epoch": 12, "split": "val", "val_macro_f1": 0.26921418267485325, "val_accuracy": 0.5293146961754999} | |
| {"step": 4550, "epoch": 13, "loss": 0.488425612449646, "task_loss": 0.4328746497631073, "partitioner_loss": 0.04562609642744064, "running_macro_f1": 0.49121049536393685, "running_accuracy": 0.8173347948637645, "lr": 0.00022306465139037947, "codebook_loss": 0.03969939798116684, "codebook_perplexity": 121.95002746582031, "codebook_active": 223.0, "codebook_commit": 0.15879759192466736} | |
| {"step": 4600, "epoch": 13, "loss": 0.6348322033882141, "task_loss": 0.5716592669487, "partitioner_loss": 0.05276517942547798, "running_macro_f1": 0.5244310834108211, "running_accuracy": 0.8318359375, "lr": 0.00022306465139037947, "codebook_loss": 0.04163087159395218, "codebook_perplexity": 86.3511962890625, "codebook_active": 189.0, "codebook_commit": 0.16652348637580872} | |
| {"step": 4650, "epoch": 13, "loss": 0.505431592464447, "task_loss": 0.4455409348011017, "partitioner_loss": 0.050425849854946136, "running_macro_f1": 0.5654353614158847, "running_accuracy": 0.84296875, "lr": 0.00022306465139037947, "codebook_loss": 0.03785921260714531, "codebook_perplexity": 140.96627807617188, "codebook_active": 292.0, "codebook_commit": 0.15143685042858124} | |
| {"step": 4700, "epoch": 13, "loss": 0.5998309254646301, "task_loss": 0.5340590476989746, "partitioner_loss": 0.0546916127204895, "running_macro_f1": 0.5719485810110648, "running_accuracy": 0.83578125, "lr": 0.00022306465139037947, "codebook_loss": 0.044321149587631226, "codebook_perplexity": 98.63806915283203, "codebook_active": 237.0, "codebook_commit": 0.1772845983505249} | |
| {"step": 4750, "epoch": 13, "loss": 0.5446137189865112, "task_loss": 0.47548821568489075, "partitioner_loss": 0.05958901345729828, "running_macro_f1": 0.5438710216964698, "running_accuracy": 0.828984375, "lr": 0.00022306465139037947, "codebook_loss": 0.03814604878425598, "codebook_perplexity": 90.61056518554688, "codebook_active": 250.0, "codebook_commit": 0.15258419513702393} | |
| {"step": 4800, "epoch": 13, "loss": 0.4281453490257263, "task_loss": 0.36679574847221375, "partitioner_loss": 0.05219009518623352, "running_macro_f1": 0.5450036727595545, "running_accuracy": 0.8304494206075791, "lr": 0.00022306465139037947, "codebook_loss": 0.036637961864471436, "codebook_perplexity": 103.033935546875, "codebook_active": 287.0, "codebook_commit": 0.14655184745788574} | |
| {"step": 4850, "epoch": 13, "loss": 0.47341588139533997, "task_loss": 0.40675440430641174, "partitioner_loss": 0.05729449912905693, "running_macro_f1": 0.5287394754165866, "running_accuracy": 0.814453125, "lr": 0.00022306465139037947, "codebook_loss": 0.03746793419122696, "codebook_perplexity": 122.92542266845703, "codebook_active": 290.0, "codebook_commit": 0.14987173676490784} | |
| {"step": 4900, "epoch": 13, "loss": 0.81606125831604, "task_loss": 0.7539229989051819, "partitioner_loss": 0.05116262659430504, "running_macro_f1": 0.5639625557756777, "running_accuracy": 0.84296875, "lr": 0.00022306465139037947, "codebook_loss": 0.043902527540922165, "codebook_perplexity": 93.2248764038086, "codebook_active": 237.0, "codebook_commit": 0.17561011016368866} | |
| {"epoch": 13, "split": "val", "val_macro_f1": 0.2785740168951077, "val_accuracy": 0.5451368666278392} | |
| {"step": 4950, "epoch": 14, "loss": 0.35076186060905457, "task_loss": 0.29206642508506775, "partitioner_loss": 0.050238531082868576, "running_macro_f1": 0.5729662276447994, "running_accuracy": 0.846953125, "lr": 0.00022176231229684834, "codebook_loss": 0.03382762521505356, "codebook_perplexity": 145.08248901367188, "codebook_active": 324.0, "codebook_commit": 0.13531050086021423} | |
| {"step": 5000, "epoch": 14, "loss": 0.33042529225349426, "task_loss": 0.26932409405708313, "partitioner_loss": 0.05336150527000427, "running_macro_f1": 0.5869418132006545, "running_accuracy": 0.856796875, "lr": 0.00022176231229684834, "codebook_loss": 0.03095875307917595, "codebook_perplexity": 117.27226257324219, "codebook_active": 269.0, "codebook_commit": 0.1238350123167038} | |
| {"step": 5050, "epoch": 14, "loss": 0.4296734929084778, "task_loss": 0.37198543548583984, "partitioner_loss": 0.047342415899038315, "running_macro_f1": 0.5855571757863722, "running_accuracy": 0.863046875, "lr": 0.00022176231229684834, "codebook_loss": 0.04138258844614029, "codebook_perplexity": 158.33877563476562, "codebook_active": 319.0, "codebook_commit": 0.16553035378456116} | |
| {"step": 5100, "epoch": 14, "loss": 1.3366358280181885, "task_loss": 1.2773444652557373, "partitioner_loss": 0.04926032945513725, "running_macro_f1": 0.5256326869172387, "running_accuracy": 0.8213671875, "lr": 0.00022176231229684834, "codebook_loss": 0.040124084800481796, "codebook_perplexity": 114.82789611816406, "codebook_active": 260.0, "codebook_commit": 0.16049633920192719} | |
| {"step": 5150, "epoch": 14, "loss": 4.109792709350586, "task_loss": 4.045361042022705, "partitioner_loss": 0.055123522877693176, "running_macro_f1": 0.5465160834466555, "running_accuracy": 0.8263388662699656, "lr": 0.00022176231229684834, "codebook_loss": 0.037233058363199234, "codebook_perplexity": 177.34234619140625, "codebook_active": 311.0, "codebook_commit": 0.14893223345279694} | |
| {"step": 5200, "epoch": 14, "loss": 0.38289862871170044, "task_loss": 0.3271784782409668, "partitioner_loss": 0.0470324270427227, "running_macro_f1": 0.5544946550044997, "running_accuracy": 0.854765625, "lr": 0.00022176231229684834, "codebook_loss": 0.03475093096494675, "codebook_perplexity": 142.34896850585938, "codebook_active": 316.0, "codebook_commit": 0.139003723859787} | |
| {"step": 5250, "epoch": 14, "loss": 0.5074122548103333, "task_loss": 0.44925594329833984, "partitioner_loss": 0.048084042966365814, "running_macro_f1": 0.5650487620408965, "running_accuracy": 0.833125, "lr": 0.00022176231229684834, "codebook_loss": 0.040289100259542465, "codebook_perplexity": 144.50454711914062, "codebook_active": 256.0, "codebook_commit": 0.16115640103816986} | |
| {"epoch": 14, "split": "val", "val_macro_f1": 0.3048915425011853, "val_accuracy": 0.5511551155115512} | |
| {"step": 5300, "epoch": 15, "loss": 0.4324704706668854, "task_loss": 0.3675946891307831, "partitioner_loss": 0.055910028517246246, "running_macro_f1": 0.5850777200353455, "running_accuracy": 0.8512109375, "lr": 0.000220352472604688, "codebook_loss": 0.03586307913064957, "codebook_perplexity": 149.3556671142578, "codebook_active": 314.0, "codebook_commit": 0.14345231652259827} | |
| {"step": 5350, "epoch": 15, "loss": 0.42752814292907715, "task_loss": 0.3701535165309906, "partitioner_loss": 0.04749007523059845, "running_macro_f1": 0.5925416732496174, "running_accuracy": 0.85921875, "lr": 0.000220352472604688, "codebook_loss": 0.0395381860435009, "codebook_perplexity": 124.93946838378906, "codebook_active": 241.0, "codebook_commit": 0.1581527441740036} | |
| {"step": 5400, "epoch": 15, "loss": 0.578161358833313, "task_loss": 0.5141249299049377, "partitioner_loss": 0.05586770176887512, "running_macro_f1": 0.5815983922721512, "running_accuracy": 0.8577734375, "lr": 0.000220352472604688, "codebook_loss": 0.03267483785748482, "codebook_perplexity": 205.91769409179688, "codebook_active": 411.0, "codebook_commit": 0.13069935142993927} | |
| {"step": 5450, "epoch": 15, "loss": 0.3636365234851837, "task_loss": 0.30242684483528137, "partitioner_loss": 0.05147867277264595, "running_macro_f1": 0.5961725050510174, "running_accuracy": 0.8627734375, "lr": 0.000220352472604688, "codebook_loss": 0.0389239564538002, "codebook_perplexity": 135.1603240966797, "codebook_active": 291.0, "codebook_commit": 0.1556958258152008} | |
| {"step": 5500, "epoch": 15, "loss": 0.39516279101371765, "task_loss": 0.32859963178634644, "partitioner_loss": 0.05780600756406784, "running_macro_f1": 0.5742416189182239, "running_accuracy": 0.8585969307860946, "lr": 0.000220352472604688, "codebook_loss": 0.035028547048568726, "codebook_perplexity": 165.8240966796875, "codebook_active": 330.0, "codebook_commit": 0.1401141881942749} | |
| {"step": 5550, "epoch": 15, "loss": 0.4474445581436157, "task_loss": 0.3926781117916107, "partitioner_loss": 0.047008153051137924, "running_macro_f1": 0.5554220629584083, "running_accuracy": 0.8482421875, "lr": 0.000220352472604688, "codebook_loss": 0.03103313222527504, "codebook_perplexity": 204.7609405517578, "codebook_active": 378.0, "codebook_commit": 0.12413252890110016} | |
| {"step": 5600, "epoch": 15, "loss": 0.2697359025478363, "task_loss": 0.20150086283683777, "partitioner_loss": 0.05928758531808853, "running_macro_f1": 0.5599119092188144, "running_accuracy": 0.832734375, "lr": 0.000220352472604688, "codebook_loss": 0.03578987717628479, "codebook_perplexity": 170.26722717285156, "codebook_active": 321.0, "codebook_commit": 0.14315950870513916} | |
| {"step": 5650, "epoch": 15, "loss": 0.47470661997795105, "task_loss": 0.4133754074573517, "partitioner_loss": 0.05191805586218834, "running_macro_f1": 0.5345237463568043, "running_accuracy": 0.8445703125, "lr": 0.000220352472604688, "codebook_loss": 0.037652574479579926, "codebook_perplexity": 151.15521240234375, "codebook_active": 310.0, "codebook_commit": 0.1506102979183197} | |
| {"epoch": 15, "split": "val", "val_macro_f1": 0.29114129366918695, "val_accuracy": 0.5167928557561638} | |
| {"step": 5700, "epoch": 16, "loss": 0.41064712405204773, "task_loss": 0.3549000024795532, "partitioner_loss": 0.04495992138981819, "running_macro_f1": 0.5549105551804411, "running_accuracy": 0.8323828125, "lr": 0.00021883655190296146, "codebook_loss": 0.0431487150490284, "codebook_perplexity": 162.669189453125, "codebook_active": 302.0, "codebook_commit": 0.1725948601961136} | |
| {"step": 5750, "epoch": 16, "loss": 0.378703773021698, "task_loss": 0.3185330331325531, "partitioner_loss": 0.05292925983667374, "running_macro_f1": 0.5844470664197592, "running_accuracy": 0.8430551205762605, "lr": 0.00021883655190296146, "codebook_loss": 0.02896597981452942, "codebook_perplexity": 239.56930541992188, "codebook_active": 403.0, "codebook_commit": 0.11586391925811768} | |
| {"step": 5800, "epoch": 16, "loss": 0.9113652110099792, "task_loss": 0.8436019420623779, "partitioner_loss": 0.05669001489877701, "running_macro_f1": 0.5909164658447406, "running_accuracy": 0.852734375, "lr": 0.00021883655190296146, "codebook_loss": 0.04429285228252411, "codebook_perplexity": 119.08177947998047, "codebook_active": 227.0, "codebook_commit": 0.17717140913009644} | |
| {"step": 5850, "epoch": 16, "loss": 0.46198052167892456, "task_loss": 0.4070325195789337, "partitioner_loss": 0.045088618993759155, "running_macro_f1": 0.5818038730446874, "running_accuracy": 0.85265625, "lr": 0.00021883655190296146, "codebook_loss": 0.03943754732608795, "codebook_perplexity": 177.1398468017578, "codebook_active": 304.0, "codebook_commit": 0.1577501893043518} | |
| {"step": 5900, "epoch": 16, "loss": 0.34016603231430054, "task_loss": 0.2720794975757599, "partitioner_loss": 0.05999026075005531, "running_macro_f1": 0.5713339270540742, "running_accuracy": 0.8588671875, "lr": 0.00021883655190296146, "codebook_loss": 0.03238511085510254, "codebook_perplexity": 131.57400512695312, "codebook_active": 316.0, "codebook_commit": 0.12954044342041016} | |
| {"step": 5950, "epoch": 16, "loss": 0.5946056246757507, "task_loss": 0.5332465767860413, "partitioner_loss": 0.05303780734539032, "running_macro_f1": 0.5894056682696892, "running_accuracy": 0.8623046875, "lr": 0.00021883655190296146, "codebook_loss": 0.03328479081392288, "codebook_perplexity": 202.01316833496094, "codebook_active": 342.0, "codebook_commit": 0.13313916325569153} | |
| {"step": 6000, "epoch": 16, "loss": 0.23493783175945282, "task_loss": 0.17680677771568298, "partitioner_loss": 0.049530670046806335, "running_macro_f1": 0.5729005805955785, "running_accuracy": 0.869765625, "lr": 0.00021883655190296146, "codebook_loss": 0.0344015508890152, "codebook_perplexity": 124.77086639404297, "codebook_active": 288.0, "codebook_commit": 0.1376062035560608} | |
| {"epoch": 16, "split": "val", "val_macro_f1": 0.30655738027982793, "val_accuracy": 0.5507668413900213} | |
| {"step": 6050, "epoch": 17, "loss": 0.7702857255935669, "task_loss": 0.7048660516738892, "partitioner_loss": 0.05630625784397125, "running_macro_f1": 0.6022447853464018, "running_accuracy": 0.8722265625, "lr": 0.00021721607659531622, "codebook_loss": 0.03645382821559906, "codebook_perplexity": 64.24929809570312, "codebook_active": 167.0, "codebook_commit": 0.14581531286239624} | |
| {"step": 6100, "epoch": 17, "loss": 0.3277853727340698, "task_loss": 0.2735043168067932, "partitioner_loss": 0.04549538344144821, "running_macro_f1": 0.6108507938100106, "running_accuracy": 0.86859375, "lr": 0.00021721607659531622, "codebook_loss": 0.035142682492733, "codebook_perplexity": 171.92372131347656, "codebook_active": 339.0, "codebook_commit": 0.140570729970932} | |
| {"step": 6150, "epoch": 17, "loss": 0.33251601457595825, "task_loss": 0.27854132652282715, "partitioner_loss": 0.04170498996973038, "running_macro_f1": 0.6058336944722469, "running_accuracy": 0.86265625, "lr": 0.00021721607659531622, "codebook_loss": 0.04907878488302231, "codebook_perplexity": 79.9741439819336, "codebook_active": 242.0, "codebook_commit": 0.19631513953208923} | |
| {"step": 6200, "epoch": 17, "loss": 0.77671217918396, "task_loss": 0.722307562828064, "partitioner_loss": 0.04443976283073425, "running_macro_f1": 0.5802359869421043, "running_accuracy": 0.8662890625, "lr": 0.00021721607659531622, "codebook_loss": 0.03985939919948578, "codebook_perplexity": 100.26423645019531, "codebook_active": 295.0, "codebook_commit": 0.15943759679794312} | |
| {"step": 6250, "epoch": 17, "loss": 0.3036733865737915, "task_loss": 0.24127940833568573, "partitioner_loss": 0.05519929528236389, "running_macro_f1": 0.6082673737424974, "running_accuracy": 0.8640234375, "lr": 0.00021721607659531622, "codebook_loss": 0.02877880446612835, "codebook_perplexity": 187.00375366210938, "codebook_active": 330.0, "codebook_commit": 0.1151152178645134} | |
| {"step": 6300, "epoch": 17, "loss": 0.8810222148895264, "task_loss": 0.8245463371276855, "partitioner_loss": 0.046751610934734344, "running_macro_f1": 0.5960447752431045, "running_accuracy": 0.8867578125, "lr": 0.00021721607659531622, "codebook_loss": 0.03889695927500725, "codebook_perplexity": 141.10870361328125, "codebook_active": 328.0, "codebook_commit": 0.155587837100029} | |
| {"step": 6350, "epoch": 17, "loss": 0.7821946740150452, "task_loss": 0.7277759313583374, "partitioner_loss": 0.04544149339199066, "running_macro_f1": 0.5875704109837651, "running_accuracy": 0.87609375, "lr": 0.00021721607659531622, "codebook_loss": 0.0359090194106102, "codebook_perplexity": 117.38958740234375, "codebook_active": 297.0, "codebook_commit": 0.1436360776424408} | |
| {"step": 6400, "epoch": 17, "loss": 0.4415808916091919, "task_loss": 0.3746938407421112, "partitioner_loss": 0.057245515286922455, "running_macro_f1": 0.5982202383702915, "running_accuracy": 0.854486376448481, "lr": 0.00021721607659531622, "codebook_loss": 0.03856612369418144, "codebook_perplexity": 172.62542724609375, "codebook_active": 314.0, "codebook_commit": 0.15426449477672577} | |
| {"epoch": 17, "split": "val", "val_macro_f1": 0.29276352595015687, "val_accuracy": 0.566880217433508} | |
| {"step": 6450, "epoch": 18, "loss": 0.38346943259239197, "task_loss": 0.3164992928504944, "partitioner_loss": 0.05789250135421753, "running_macro_f1": 0.5976330218298032, "running_accuracy": 0.8566015625, "lr": 0.00021549267836302527, "codebook_loss": 0.03631053492426872, "codebook_perplexity": 167.46034240722656, "codebook_active": 357.0, "codebook_commit": 0.1452421396970749} | |
| {"step": 6500, "epoch": 18, "loss": 0.2565571367740631, "task_loss": 0.20217837393283844, "partitioner_loss": 0.047629062086343765, "running_macro_f1": 0.5898004822259212, "running_accuracy": 0.864609375, "lr": 0.00021549267836302527, "codebook_loss": 0.02699887566268444, "codebook_perplexity": 190.52584838867188, "codebook_active": 382.0, "codebook_commit": 0.10799550265073776} | |
| {"step": 6550, "epoch": 18, "loss": 0.45327767729759216, "task_loss": 0.38668742775917053, "partitioner_loss": 0.05576997250318527, "running_macro_f1": 0.6091359713186054, "running_accuracy": 0.8759765625, "lr": 0.00021549267836302527, "codebook_loss": 0.04328102245926857, "codebook_perplexity": 112.36367797851562, "codebook_active": 253.0, "codebook_commit": 0.17312408983707428} | |
| {"step": 6600, "epoch": 18, "loss": 0.959932804107666, "task_loss": 0.8860852122306824, "partitioner_loss": 0.06444606184959412, "running_macro_f1": 0.5779993890913523, "running_accuracy": 0.8502734375, "lr": 0.00021549267836302527, "codebook_loss": 0.03760625049471855, "codebook_perplexity": 29.671884536743164, "codebook_active": 114.0, "codebook_commit": 0.1504250019788742} | |
| {"step": 6650, "epoch": 18, "loss": 0.46468397974967957, "task_loss": 0.4112306833267212, "partitioner_loss": 0.04571770131587982, "running_macro_f1": 0.5569119866742975, "running_accuracy": 0.85234375, "lr": 0.00021549267836302527, "codebook_loss": 0.030942318961024284, "codebook_perplexity": 90.11865997314453, "codebook_active": 254.0, "codebook_commit": 0.12376927584409714} | |
| {"step": 6700, "epoch": 18, "loss": 0.36504462361335754, "task_loss": 0.3020056486129761, "partitioner_loss": 0.05594070255756378, "running_macro_f1": 0.5759532045576721, "running_accuracy": 0.8454431569057312, "lr": 0.00021549267836302527, "codebook_loss": 0.02839314192533493, "codebook_perplexity": 127.1408462524414, "codebook_active": 302.0, "codebook_commit": 0.11357256770133972} | |
| {"step": 6750, "epoch": 18, "loss": 0.520587682723999, "task_loss": 0.4591282308101654, "partitioner_loss": 0.053006596863269806, "running_macro_f1": 0.5817167349525352, "running_accuracy": 0.873515625, "lr": 0.00021549267836302527, "codebook_loss": 0.033811233937740326, "codebook_perplexity": 151.0423126220703, "codebook_active": 318.0, "codebook_commit": 0.1352449357509613} | |
| {"step": 6800, "epoch": 18, "loss": 0.3872458040714264, "task_loss": 0.32380494475364685, "partitioner_loss": 0.054231397807598114, "running_macro_f1": 0.6262937719676875, "running_accuracy": 0.880234375, "lr": 0.00021549267836302527, "codebook_loss": 0.03683777153491974, "codebook_perplexity": 135.7464141845703, "codebook_active": 270.0, "codebook_commit": 0.14735108613967896} | |
| {"epoch": 18, "split": "val", "val_macro_f1": 0.3053654486510297, "val_accuracy": 0.5659095321296835} | |
| {"step": 6850, "epoch": 19, "loss": 0.3976232707500458, "task_loss": 0.33988311886787415, "partitioner_loss": 0.048151373863220215, "running_macro_f1": 0.5979267379270404, "running_accuracy": 0.859296875, "lr": 0.00021366809252202238, "codebook_loss": 0.038355130702257156, "codebook_perplexity": 114.46452331542969, "codebook_active": 218.0, "codebook_commit": 0.15342052280902863} | |
| {"step": 6900, "epoch": 19, "loss": 0.21810483932495117, "task_loss": 0.16225303709506989, "partitioner_loss": 0.04785585403442383, "running_macro_f1": 0.60904309776149, "running_accuracy": 0.889375, "lr": 0.00021366809252202238, "codebook_loss": 0.031983792781829834, "codebook_perplexity": 175.6634521484375, "codebook_active": 329.0, "codebook_commit": 0.12793517112731934} | |
| {"step": 6950, "epoch": 19, "loss": 0.4476903975009918, "task_loss": 0.39249950647354126, "partitioner_loss": 0.046284452080726624, "running_macro_f1": 0.6022785685458972, "running_accuracy": 0.873046875, "lr": 0.00021366809252202238, "codebook_loss": 0.03562583774328232, "codebook_perplexity": 65.46263122558594, "codebook_active": 158.0, "codebook_commit": 0.14250335097312927} | |
| {"step": 7000, "epoch": 19, "loss": 0.4763597249984741, "task_loss": 0.418355792760849, "partitioner_loss": 0.049576371908187866, "running_macro_f1": 0.6589693117341283, "running_accuracy": 0.8929296875, "lr": 0.00021366809252202238, "codebook_loss": 0.03371024131774902, "codebook_perplexity": 162.92474365234375, "codebook_active": 305.0, "codebook_commit": 0.1348409652709961} | |
| {"step": 7050, "epoch": 19, "loss": 1.5795772075653076, "task_loss": 1.5218381881713867, "partitioner_loss": 0.04924054816365242, "running_macro_f1": 0.6305179500964189, "running_accuracy": 0.8924609375, "lr": 0.00021366809252202238, "codebook_loss": 0.033993691205978394, "codebook_perplexity": 186.91549682617188, "codebook_active": 357.0, "codebook_commit": 0.13597476482391357} | |
| {"step": 7100, "epoch": 19, "loss": 0.9921632409095764, "task_loss": 0.9392330646514893, "partitioner_loss": 0.04318291321396828, "running_macro_f1": 0.5944773881698246, "running_accuracy": 0.8575790792358283, "lr": 0.00021366809252202238, "codebook_loss": 0.03898918256163597, "codebook_perplexity": 152.8792266845703, "codebook_active": 292.0, "codebook_commit": 0.15595673024654388} | |
| {"step": 7150, "epoch": 19, "loss": 0.5602364540100098, "task_loss": 0.49606165289878845, "partitioner_loss": 0.05283049866557121, "running_macro_f1": 0.5838992882763198, "running_accuracy": 0.87, "lr": 0.00021366809252202238, "codebook_loss": 0.045377217233181, "codebook_perplexity": 115.19219970703125, "codebook_active": 248.0, "codebook_commit": 0.181508868932724} | |
| {"epoch": 19, "split": "val", "val_macro_f1": 0.2911433195314226, "val_accuracy": 0.5480489225393127} | |
| {"step": 7200, "epoch": 20, "loss": 0.36375418305397034, "task_loss": 0.29971954226493835, "partitioner_loss": 0.05507992208003998, "running_macro_f1": 0.5673296633208594, "running_accuracy": 0.8698828125, "lr": 0.00021174415627558585, "codebook_loss": 0.035818882286548615, "codebook_perplexity": 145.79896545410156, "codebook_active": 288.0, "codebook_commit": 0.14327552914619446} | |
| {"step": 7250, "epoch": 20, "loss": 0.34641343355178833, "task_loss": 0.2859014868736267, "partitioner_loss": 0.052021048963069916, "running_macro_f1": 0.5777764488623113, "running_accuracy": 0.872421875, "lr": 0.00021174415627558585, "codebook_loss": 0.03396359086036682, "codebook_perplexity": 145.51107788085938, "codebook_active": 302.0, "codebook_commit": 0.13585436344146729} | |
| {"step": 7300, "epoch": 20, "loss": 0.36256828904151917, "task_loss": 0.3059632182121277, "partitioner_loss": 0.04684489220380783, "running_macro_f1": 0.6007513678828105, "running_accuracy": 0.8612109375, "lr": 0.00021174415627558585, "codebook_loss": 0.03904068470001221, "codebook_perplexity": 90.5708236694336, "codebook_active": 273.0, "codebook_commit": 0.15616273880004883} | |
| {"step": 7350, "epoch": 20, "loss": 0.8440398573875427, "task_loss": 0.7863160967826843, "partitioner_loss": 0.04641369730234146, "running_macro_f1": 0.5613071445650157, "running_accuracy": 0.8576171875, "lr": 0.00021174415627558585, "codebook_loss": 0.045240215957164764, "codebook_perplexity": 172.0692138671875, "codebook_active": 388.0, "codebook_commit": 0.18096086382865906} | |
| {"step": 7400, "epoch": 20, "loss": 0.6545023322105408, "task_loss": 0.5964027047157288, "partitioner_loss": 0.047901272773742676, "running_macro_f1": 0.5826982095504092, "running_accuracy": 0.860234375, "lr": 0.00021174415627558585, "codebook_loss": 0.04079337418079376, "codebook_perplexity": 125.89380645751953, "codebook_active": 265.0, "codebook_commit": 0.16317349672317505} | |
| {"step": 7450, "epoch": 20, "loss": 0.27236974239349365, "task_loss": 0.2149980664253235, "partitioner_loss": 0.0487561896443367, "running_macro_f1": 0.5832650883156776, "running_accuracy": 0.8699107422486689, "lr": 0.00021174415627558585, "codebook_loss": 0.03446197509765625, "codebook_perplexity": 73.90131378173828, "codebook_active": 198.0, "codebook_commit": 0.137847900390625} | |
| {"step": 7500, "epoch": 20, "loss": 0.41052529215812683, "task_loss": 0.348086416721344, "partitioner_loss": 0.05469348654150963, "running_macro_f1": 0.5887734624356343, "running_accuracy": 0.8621875, "lr": 0.00021174415627558585, "codebook_loss": 0.030981484800577164, "codebook_perplexity": 171.0610809326172, "codebook_active": 381.0, "codebook_commit": 0.12392593920230865} | |
| {"step": 7550, "epoch": 20, "loss": 0.6242358088493347, "task_loss": 0.5645177364349365, "partitioner_loss": 0.04905327409505844, "running_macro_f1": 0.5882202504974204, "running_accuracy": 0.8611328125, "lr": 0.00021174415627558585, "codebook_loss": 0.04265932738780975, "codebook_perplexity": 136.98458862304688, "codebook_active": 317.0, "codebook_commit": 0.170637309551239} | |
| {"epoch": 20, "split": "val", "val_macro_f1": 0.30934039079144143, "val_accuracy": 0.6230828965249466} | |
| {"step": 7600, "epoch": 21, "loss": 0.67253577709198, "task_loss": 0.6135079860687256, "partitioner_loss": 0.05168895423412323, "running_macro_f1": 0.6113100767668685, "running_accuracy": 0.8747265625, "lr": 0.0002097228068644308, "codebook_loss": 0.02935539372265339, "codebook_perplexity": 157.83055114746094, "codebook_active": 317.0, "codebook_commit": 0.11742157489061356} | |
| {"step": 7650, "epoch": 21, "loss": 0.2268354594707489, "task_loss": 0.16844773292541504, "partitioner_loss": 0.04966152459383011, "running_macro_f1": 0.6231314280204653, "running_accuracy": 0.8882421875, "lr": 0.0002097228068644308, "codebook_loss": 0.03490486741065979, "codebook_perplexity": 174.62046813964844, "codebook_active": 348.0, "codebook_commit": 0.13961946964263916} | |
| {"step": 7700, "epoch": 21, "loss": 0.35719743371009827, "task_loss": 0.30007264018058777, "partitioner_loss": 0.04876957833766937, "running_macro_f1": 0.6167037346806218, "running_accuracy": 0.9000390625, "lr": 0.0002097228068644308, "codebook_loss": 0.033420953899621964, "codebook_perplexity": 173.5037078857422, "codebook_active": 343.0, "codebook_commit": 0.13368381559848785} | |
| {"step": 7750, "epoch": 21, "loss": 0.3104322850704193, "task_loss": 0.2570905387401581, "partitioner_loss": 0.0446932390332222, "running_macro_f1": 0.6119859523991371, "running_accuracy": 0.8885452552458503, "lr": 0.0002097228068644308, "codebook_loss": 0.034594058990478516, "codebook_perplexity": 167.000244140625, "codebook_active": 327.0, "codebook_commit": 0.13837623596191406} | |
| {"step": 7800, "epoch": 21, "loss": 0.3670041263103485, "task_loss": 0.3144640028476715, "partitioner_loss": 0.04260031878948212, "running_macro_f1": 0.6268447563746151, "running_accuracy": 0.88109375, "lr": 0.0002097228068644308, "codebook_loss": 0.039759326726198196, "codebook_perplexity": 99.21781921386719, "codebook_active": 279.0, "codebook_commit": 0.15903730690479279} | |
| {"step": 7850, "epoch": 21, "loss": 1.992631435394287, "task_loss": 1.9195572137832642, "partitioner_loss": 0.06394126266241074, "running_macro_f1": 0.5834506883853403, "running_accuracy": 0.863515625, "lr": 0.0002097228068644308, "codebook_loss": 0.03653176128864288, "codebook_perplexity": 30.267059326171875, "codebook_active": 105.0, "codebook_commit": 0.14612704515457153} | |
| {"step": 7900, "epoch": 21, "loss": 0.5024834871292114, "task_loss": 0.44130802154541016, "partitioner_loss": 0.051240064203739166, "running_macro_f1": 0.5968652060167252, "running_accuracy": 0.869375, "lr": 0.0002097228068644308, "codebook_loss": 0.03974154219031334, "codebook_perplexity": 69.07232666015625, "codebook_active": 154.0, "codebook_commit": 0.15896616876125336} | |
| {"epoch": 21, "split": "val", "val_macro_f1": 0.31518444847114796, "val_accuracy": 0.5745486313337216} | |
| {"step": 7950, "epoch": 22, "loss": 0.6080686450004578, "task_loss": 0.5465100407600403, "partitioner_loss": 0.05002494156360626, "running_macro_f1": 0.5700632514065505, "running_accuracy": 0.869921875, "lr": 0.00020760607961607176, "codebook_loss": 0.04613465443253517, "codebook_perplexity": 124.64836120605469, "codebook_active": 261.0, "codebook_commit": 0.18453861773014069} | |
| {"step": 8000, "epoch": 22, "loss": 0.4552779793739319, "task_loss": 0.39145705103874207, "partitioner_loss": 0.05490439385175705, "running_macro_f1": 0.6367108793234688, "running_accuracy": 0.89, "lr": 0.00020760607961607176, "codebook_loss": 0.03566613048315048, "codebook_perplexity": 93.91322326660156, "codebook_active": 279.0, "codebook_commit": 0.14266452193260193} | |
| {"step": 8050, "epoch": 22, "loss": 0.6305288076400757, "task_loss": 0.5779087543487549, "partitioner_loss": 0.04333583265542984, "running_macro_f1": 0.600005813365026, "running_accuracy": 0.8771484375, "lr": 0.00020760607961607176, "codebook_loss": 0.037136875092983246, "codebook_perplexity": 125.42559814453125, "codebook_active": 328.0, "codebook_commit": 0.14854750037193298} | |
| {"step": 8100, "epoch": 22, "loss": 0.46117693185806274, "task_loss": 0.40424269437789917, "partitioner_loss": 0.04891549050807953, "running_macro_f1": 0.6281069741629165, "running_accuracy": 0.8907375508925776, "lr": 0.00020760607961607176, "codebook_loss": 0.0320749469101429, "codebook_perplexity": 164.72848510742188, "codebook_active": 333.0, "codebook_commit": 0.1282997876405716} | |
| {"step": 8150, "epoch": 22, "loss": 0.22431932389736176, "task_loss": 0.16745375096797943, "partitioner_loss": 0.04827718436717987, "running_macro_f1": 0.61103417208093, "running_accuracy": 0.8886328125, "lr": 0.00020760607961607176, "codebook_loss": 0.034353580325841904, "codebook_perplexity": 137.5326690673828, "codebook_active": 274.0, "codebook_commit": 0.13741432130336761} | |
| {"step": 8200, "epoch": 22, "loss": 1.0403199195861816, "task_loss": 0.9853523373603821, "partitioner_loss": 0.044898368418216705, "running_macro_f1": 0.6364325279447522, "running_accuracy": 0.8922265625, "lr": 0.00020760607961607176, "codebook_loss": 0.04027709364891052, "codebook_perplexity": 157.7938232421875, "codebook_active": 347.0, "codebook_commit": 0.1611083745956421} | |
| {"step": 8250, "epoch": 22, "loss": 0.26105156540870667, "task_loss": 0.20757216215133667, "partitioner_loss": 0.04493085294961929, "running_macro_f1": 0.6217881829382775, "running_accuracy": 0.8971484375, "lr": 0.00020760607961607176, "codebook_loss": 0.03419424593448639, "codebook_perplexity": 174.25880432128906, "codebook_active": 326.0, "codebook_commit": 0.13677698373794556} | |
| {"step": 8300, "epoch": 22, "loss": 0.13854515552520752, "task_loss": 0.0878681018948555, "partitioner_loss": 0.04262078180909157, "running_macro_f1": 0.6292638703937814, "running_accuracy": 0.8955859375, "lr": 0.00020760607961607176, "codebook_loss": 0.03222508728504181, "codebook_perplexity": 238.50177001953125, "codebook_active": 412.0, "codebook_commit": 0.12890034914016724} | |
| {"epoch": 22, "split": "val", "val_macro_f1": 0.3235446020154593, "val_accuracy": 0.6331780236847214} | |
| {"step": 8350, "epoch": 23, "loss": 0.24260678887367249, "task_loss": 0.18896201252937317, "partitioner_loss": 0.04431556165218353, "running_macro_f1": 0.6286802426499402, "running_accuracy": 0.892109375, "lr": 0.00020539610589542058, "codebook_loss": 0.03731686249375343, "codebook_perplexity": 139.91848754882812, "codebook_active": 294.0, "codebook_commit": 0.14926744997501373} | |
| {"step": 8400, "epoch": 23, "loss": 0.482474148273468, "task_loss": 0.4334580898284912, "partitioner_loss": 0.03840702399611473, "running_macro_f1": 0.6689762857520241, "running_accuracy": 0.9105078125, "lr": 0.00020539610589542058, "codebook_loss": 0.042436156421899796, "codebook_perplexity": 101.29564666748047, "codebook_active": 283.0, "codebook_commit": 0.16974462568759918} | |
| {"step": 8450, "epoch": 23, "loss": 0.5715341567993164, "task_loss": 0.51472407579422, "partitioner_loss": 0.04940182343125343, "running_macro_f1": 0.6288135023883171, "running_accuracy": 0.8875390625, "lr": 0.00020539610589542058, "codebook_loss": 0.029633112251758575, "codebook_perplexity": 212.91241455078125, "codebook_active": 398.0, "codebook_commit": 0.1185324490070343} | |
| {"step": 8500, "epoch": 23, "loss": 0.2861705720424652, "task_loss": 0.2357582300901413, "partitioner_loss": 0.04309737682342529, "running_macro_f1": 0.6305349095775267, "running_accuracy": 0.8768399624177889, "lr": 0.00020539610589542058, "codebook_loss": 0.029259776696562767, "codebook_perplexity": 167.0888214111328, "codebook_active": 341.0, "codebook_commit": 0.11703910678625107} | |
| {"step": 8550, "epoch": 23, "loss": 0.5087887048721313, "task_loss": 0.45295485854148865, "partitioner_loss": 0.04526415467262268, "running_macro_f1": 0.5855596172737488, "running_accuracy": 0.890234375, "lr": 0.00020539610589542058, "codebook_loss": 0.042278725653886795, "codebook_perplexity": 127.06089782714844, "codebook_active": 318.0, "codebook_commit": 0.16911490261554718} | |
| {"step": 8600, "epoch": 23, "loss": 0.35321754217147827, "task_loss": 0.29624143242836, "partitioner_loss": 0.04804237186908722, "running_macro_f1": 0.6130099001446322, "running_accuracy": 0.8777734375, "lr": 0.00020539610589542058, "codebook_loss": 0.03573495149612427, "codebook_perplexity": 215.98065185546875, "codebook_active": 359.0, "codebook_commit": 0.14293980598449707} | |
| {"step": 8650, "epoch": 23, "loss": 0.3930012285709381, "task_loss": 0.3362368643283844, "partitioner_loss": 0.047868020832538605, "running_macro_f1": 0.6190512509709625, "running_accuracy": 0.89953125, "lr": 0.00020539610589542058, "codebook_loss": 0.03558540344238281, "codebook_perplexity": 146.78036499023438, "codebook_active": 319.0, "codebook_commit": 0.14234161376953125} | |
| {"epoch": 23, "split": "val", "val_macro_f1": 0.321942075711313, "val_accuracy": 0.6197825664919433} | |
| {"step": 8700, "epoch": 24, "loss": 0.2746182978153229, "task_loss": 0.2189033329486847, "partitioner_loss": 0.046487875282764435, "running_macro_f1": 0.6320796179025384, "running_accuracy": 0.9035546875, "lr": 0.00020309511095868246, "codebook_loss": 0.0369083508849144, "codebook_perplexity": 150.55406188964844, "codebook_active": 295.0, "codebook_commit": 0.1476334035396576} | |
| {"step": 8750, "epoch": 24, "loss": 0.27627861499786377, "task_loss": 0.22386017441749573, "partitioner_loss": 0.04345083236694336, "running_macro_f1": 0.6458357422866668, "running_accuracy": 0.89015625, "lr": 0.00020309511095868246, "codebook_loss": 0.03587041050195694, "codebook_perplexity": 107.4377212524414, "codebook_active": 224.0, "codebook_commit": 0.14348164200782776} | |
| {"step": 8800, "epoch": 24, "loss": 0.5066034197807312, "task_loss": 0.45028868317604065, "partitioner_loss": 0.04525870829820633, "running_macro_f1": 0.6457074101788195, "running_accuracy": 0.899154400250548, "lr": 0.00020309511095868246, "codebook_loss": 0.04422413557767868, "codebook_perplexity": 140.54611206054688, "codebook_active": 302.0, "codebook_commit": 0.17689654231071472} | |
| {"step": 8850, "epoch": 24, "loss": 0.22688758373260498, "task_loss": 0.17273078858852386, "partitioner_loss": 0.0444219708442688, "running_macro_f1": 0.6396239966090781, "running_accuracy": 0.9094140625, "lr": 0.00020309511095868246, "codebook_loss": 0.03893930837512016, "codebook_perplexity": 156.80943298339844, "codebook_active": 325.0, "codebook_commit": 0.15575723350048065} | |
| {"step": 8900, "epoch": 24, "loss": 0.6498374938964844, "task_loss": 0.5915014147758484, "partitioner_loss": 0.04912882298231125, "running_macro_f1": 0.6333893158369966, "running_accuracy": 0.898046875, "lr": 0.00020309511095868246, "codebook_loss": 0.036829106509685516, "codebook_perplexity": 170.24896240234375, "codebook_active": 345.0, "codebook_commit": 0.14731642603874207} | |
| {"step": 8950, "epoch": 24, "loss": 0.5917534232139587, "task_loss": 0.5403047800064087, "partitioner_loss": 0.04182811826467514, "running_macro_f1": 0.6366307843456399, "running_accuracy": 0.892578125, "lr": 0.00020309511095868246, "codebook_loss": 0.03848228231072426, "codebook_perplexity": 99.84449005126953, "codebook_active": 282.0, "codebook_commit": 0.15392912924289703} | |
| {"step": 9000, "epoch": 24, "loss": 0.27731406688690186, "task_loss": 0.2257450371980667, "partitioner_loss": 0.04233279824256897, "running_macro_f1": 0.6553002130686536, "running_accuracy": 0.89640625, "lr": 0.00020309511095868246, "codebook_loss": 0.0369449257850647, "codebook_perplexity": 137.3719024658203, "codebook_active": 329.0, "codebook_commit": 0.1477797031402588} | |
| {"step": 9050, "epoch": 24, "loss": 0.4714399576187134, "task_loss": 0.40310558676719666, "partitioner_loss": 0.05825306847691536, "running_macro_f1": 0.6345031356664323, "running_accuracy": 0.895703125, "lr": 0.00020309511095868246, "codebook_loss": 0.04032520949840546, "codebook_perplexity": 41.495357513427734, "codebook_active": 147.0, "codebook_commit": 0.16130083799362183} | |
| {"epoch": 24, "split": "val", "val_macro_f1": 0.33934124430884366, "val_accuracy": 0.6519122500485343} | |
| {"step": 9100, "epoch": 25, "loss": 0.2628982663154602, "task_loss": 0.21177442371845245, "partitioner_loss": 0.03941822797060013, "running_macro_f1": 0.6422745512491251, "running_accuracy": 0.893671875, "lr": 0.0002007054117127118, "codebook_loss": 0.046822439879179, "codebook_perplexity": 140.32794189453125, "codebook_active": 296.0, "codebook_commit": 0.187289759516716} | |
| {"step": 9150, "epoch": 25, "loss": 0.2953951954841614, "task_loss": 0.2463103085756302, "partitioner_loss": 0.039347898215055466, "running_macro_f1": 0.6199576409096342, "running_accuracy": 0.8920703125, "lr": 0.0002007054117127118, "codebook_loss": 0.038947977125644684, "codebook_perplexity": 187.08973693847656, "codebook_active": 336.0, "codebook_commit": 0.15579190850257874} | |
| {"step": 9200, "epoch": 25, "loss": 0.18890899419784546, "task_loss": 0.14102600514888763, "partitioner_loss": 0.03962147235870361, "running_macro_f1": 0.663237317955484, "running_accuracy": 0.90625, "lr": 0.0002007054117127118, "codebook_loss": 0.03304609656333923, "codebook_perplexity": 120.1235580444336, "codebook_active": 270.0, "codebook_commit": 0.13218438625335693} | |
| {"step": 9250, "epoch": 25, "loss": 0.228408545255661, "task_loss": 0.17905978858470917, "partitioner_loss": 0.03933732211589813, "running_macro_f1": 0.6811831108600779, "running_accuracy": 0.9074929533354212, "lr": 0.0002007054117127118, "codebook_loss": 0.040045760571956635, "codebook_perplexity": 144.04986572265625, "codebook_active": 289.0, "codebook_commit": 0.16018304228782654} | |
| {"step": 9300, "epoch": 25, "loss": 0.13454680144786835, "task_loss": 0.08643265813589096, "partitioner_loss": 0.039512552320957184, "running_macro_f1": 0.6399136658766719, "running_accuracy": 0.909140625, "lr": 0.0002007054117127118, "codebook_loss": 0.03440634161233902, "codebook_perplexity": 70.16456604003906, "codebook_active": 246.0, "codebook_commit": 0.13762536644935608} | |
| {"step": 9350, "epoch": 25, "loss": 0.2916821539402008, "task_loss": 0.23790696263313293, "partitioner_loss": 0.042451366782188416, "running_macro_f1": 0.6363035538071787, "running_accuracy": 0.90671875, "lr": 0.0002007054117127118, "codebook_loss": 0.04529538378119469, "codebook_perplexity": 136.60906982421875, "codebook_active": 249.0, "codebook_commit": 0.18118153512477875} | |
| {"step": 9400, "epoch": 25, "loss": 0.48656371235847473, "task_loss": 0.43039608001708984, "partitioner_loss": 0.04313091188669205, "running_macro_f1": 0.6608797454082789, "running_accuracy": 0.8977734375, "lr": 0.0002007054117127118, "codebook_loss": 0.05214685574173927, "codebook_perplexity": 103.46931457519531, "codebook_active": 254.0, "codebook_commit": 0.2085874229669571} | |
| {"step": 9450, "epoch": 25, "loss": 0.6646471619606018, "task_loss": 0.6088204383850098, "partitioner_loss": 0.044554635882377625, "running_macro_f1": 0.6236754524179778, "running_accuracy": 0.8775, "lr": 0.0002007054117127118, "codebook_loss": 0.04508824646472931, "codebook_perplexity": 145.2340850830078, "codebook_active": 265.0, "codebook_commit": 0.18035298585891724} | |
| {"epoch": 25, "split": "val", "val_macro_f1": 0.31462217922315944, "val_accuracy": 0.5965831877305378} | |
| {"step": 9500, "epoch": 26, "loss": 0.6661176085472107, "task_loss": 0.603554368019104, "partitioner_loss": 0.05094636231660843, "running_macro_f1": 0.6401489423329052, "running_accuracy": 0.894296875, "lr": 0.00019822941438208308, "codebook_loss": 0.046467531472444534, "codebook_perplexity": 129.00213623046875, "codebook_active": 262.0, "codebook_commit": 0.18587012588977814} | |
| {"step": 9550, "epoch": 26, "loss": 0.3352995216846466, "task_loss": 0.28009089827537537, "partitioner_loss": 0.045070625841617584, "running_macro_f1": 0.6593753878205791, "running_accuracy": 0.8964140306921391, "lr": 0.00019822941438208308, "codebook_loss": 0.040552057325839996, "codebook_perplexity": 175.88800048828125, "codebook_active": 323.0, "codebook_commit": 0.16220822930335999} | |
| {"step": 9600, "epoch": 26, "loss": 0.5359323024749756, "task_loss": 0.4755434989929199, "partitioner_loss": 0.04954604059457779, "running_macro_f1": 0.6531466595694597, "running_accuracy": 0.9094140625, "lr": 0.00019822941438208308, "codebook_loss": 0.04337090626358986, "codebook_perplexity": 155.3347930908203, "codebook_active": 335.0, "codebook_commit": 0.17348362505435944} | |
| {"step": 9650, "epoch": 26, "loss": 0.4411400556564331, "task_loss": 0.3894496560096741, "partitioner_loss": 0.043675947934389114, "running_macro_f1": 0.6093259805265702, "running_accuracy": 0.8452734375, "lr": 0.00019822941438208308, "codebook_loss": 0.03205777704715729, "codebook_perplexity": 175.00807189941406, "codebook_active": 346.0, "codebook_commit": 0.12823110818862915} | |
| {"step": 9700, "epoch": 26, "loss": 0.2504580318927765, "task_loss": 0.1972343474626541, "partitioner_loss": 0.04489611089229584, "running_macro_f1": 0.6314817306673713, "running_accuracy": 0.901796875, "lr": 0.00019822941438208308, "codebook_loss": 0.033310286700725555, "codebook_perplexity": 163.30250549316406, "codebook_active": 322.0, "codebook_commit": 0.13324114680290222} | |
| {"step": 9750, "epoch": 26, "loss": 0.31784898042678833, "task_loss": 0.26493707299232483, "partitioner_loss": 0.04357798770070076, "running_macro_f1": 0.6446437823546055, "running_accuracy": 0.9047265625, "lr": 0.00019822941438208308, "codebook_loss": 0.03733569011092186, "codebook_perplexity": 141.0244903564453, "codebook_active": 270.0, "codebook_commit": 0.14934276044368744} | |
| {"step": 9800, "epoch": 26, "loss": 0.7582568526268005, "task_loss": 0.6970428228378296, "partitioner_loss": 0.047729335725307465, "running_macro_f1": 0.6068869670100926, "running_accuracy": 0.8877734375, "lr": 0.00019822941438208308, "codebook_loss": 0.05393877997994423, "codebook_perplexity": 111.68528747558594, "codebook_active": 248.0, "codebook_commit": 0.21575511991977692} | |
| {"epoch": 26, "split": "val", "val_macro_f1": 0.3189477252576518, "val_accuracy": 0.6093962337410211} | |
| {"step": 9850, "epoch": 27, "loss": 0.14885017275810242, "task_loss": 0.09989341348409653, "partitioner_loss": 0.04030374437570572, "running_macro_f1": 0.6555250817925772, "running_accuracy": 0.9109375, "lr": 0.00019566961208622696, "codebook_loss": 0.03461206331849098, "codebook_perplexity": 182.2270050048828, "codebook_active": 338.0, "codebook_commit": 0.13844825327396393} | |
| {"step": 9900, "epoch": 27, "loss": 0.18550170958042145, "task_loss": 0.13323470950126648, "partitioner_loss": 0.04282233864068985, "running_macro_f1": 0.6187357669431229, "running_accuracy": 0.9133203125, "lr": 0.00019566961208622696, "codebook_loss": 0.037778668105602264, "codebook_perplexity": 133.1591796875, "codebook_active": 322.0, "codebook_commit": 0.15111467242240906} | |
| {"step": 9950, "epoch": 27, "loss": 0.22842039167881012, "task_loss": 0.1714704930782318, "partitioner_loss": 0.04856342077255249, "running_macro_f1": 0.6651804777082703, "running_accuracy": 0.91484375, "lr": 0.00019566961208622696, "codebook_loss": 0.03354589268565178, "codebook_perplexity": 152.58413696289062, "codebook_active": 361.0, "codebook_commit": 0.13418357074260712} | |
| {"step": 10000, "epoch": 27, "loss": 0.27099618315696716, "task_loss": 0.22232750058174133, "partitioner_loss": 0.03967013210058212, "running_macro_f1": 0.6744531598985634, "running_accuracy": 0.8923046875, "lr": 0.00019566961208622696, "codebook_loss": 0.03599415719509125, "codebook_perplexity": 219.77020263671875, "codebook_active": 361.0, "codebook_commit": 0.143976628780365} | |
| {"step": 10050, "epoch": 27, "loss": 0.28123918175697327, "task_loss": 0.2292572557926178, "partitioner_loss": 0.0417032316327095, "running_macro_f1": 0.6528554658693332, "running_accuracy": 0.9026953125, "lr": 0.00019566961208622696, "codebook_loss": 0.041114792227745056, "codebook_perplexity": 138.5384063720703, "codebook_active": 255.0, "codebook_commit": 0.16445916891098022} | |
| {"step": 10100, "epoch": 27, "loss": 0.2532089650630951, "task_loss": 0.2025899440050125, "partitioner_loss": 0.040918972343206406, "running_macro_f1": 0.6735158438082848, "running_accuracy": 0.91078125, "lr": 0.00019566961208622696, "codebook_loss": 0.038800161331892014, "codebook_perplexity": 130.49974060058594, "codebook_active": 317.0, "codebook_commit": 0.15520064532756805} | |
| {"step": 10150, "epoch": 27, "loss": 0.26721441745758057, "task_loss": 0.2165033370256424, "partitioner_loss": 0.04150255769491196, "running_macro_f1": 0.6251582358208725, "running_accuracy": 0.884921875, "lr": 0.00019566961208622696, "codebook_loss": 0.03683409094810486, "codebook_perplexity": 130.82522583007812, "codebook_active": 332.0, "codebook_commit": 0.14733636379241943} | |
| {"step": 10200, "epoch": 27, "loss": 0.3660259246826172, "task_loss": 0.30888810753822327, "partitioner_loss": 0.04816526919603348, "running_macro_f1": 0.6513568708789349, "running_accuracy": 0.8980191042906358, "lr": 0.00019566961208622696, "codebook_loss": 0.03589016944169998, "codebook_perplexity": 86.7441635131836, "codebook_active": 190.0, "codebook_commit": 0.14356067776679993} | |
| {"epoch": 27, "split": "val", "val_macro_f1": 0.3339257067835646, "val_accuracy": 0.6278392545136867} | |
| {"step": 10250, "epoch": 28, "loss": 0.47096994519233704, "task_loss": 0.4120713472366333, "partitioner_loss": 0.04973457381129265, "running_macro_f1": 0.63898302277378, "running_accuracy": 0.9046875, "lr": 0.0001930285823290702, "codebook_loss": 0.03665618598461151, "codebook_perplexity": 34.45134735107422, "codebook_active": 117.0, "codebook_commit": 0.14662474393844604} | |
| {"step": 10300, "epoch": 28, "loss": 0.45831426978111267, "task_loss": 0.3921460509300232, "partitioner_loss": 0.055781058967113495, "running_macro_f1": 0.6122943749251926, "running_accuracy": 0.86078125, "lr": 0.0001930285823290702, "codebook_loss": 0.04154863953590393, "codebook_perplexity": 145.15826416015625, "codebook_active": 332.0, "codebook_commit": 0.16619455814361572} | |
| {"step": 10350, "epoch": 28, "loss": 0.17072439193725586, "task_loss": 0.10821365565061569, "partitioner_loss": 0.05188998579978943, "running_macro_f1": 0.6445240272093365, "running_accuracy": 0.8962109375, "lr": 0.0001930285823290702, "codebook_loss": 0.04248298704624176, "codebook_perplexity": 167.37876892089844, "codebook_active": 336.0, "codebook_commit": 0.16993194818496704} | |
| {"step": 10400, "epoch": 28, "loss": 0.3169112801551819, "task_loss": 0.2560720443725586, "partitioner_loss": 0.049785397946834564, "running_macro_f1": 0.6308991266193149, "running_accuracy": 0.902265625, "lr": 0.0001930285823290702, "codebook_loss": 0.04421528801321983, "codebook_perplexity": 92.71112823486328, "codebook_active": 204.0, "codebook_commit": 0.17686115205287933} | |
| {"step": 10450, "epoch": 28, "loss": 0.17673610150814056, "task_loss": 0.12189410626888275, "partitioner_loss": 0.04446524754166603, "running_macro_f1": 0.6142679409836856, "running_accuracy": 0.88328125, "lr": 0.0001930285823290702, "codebook_loss": 0.041506994515657425, "codebook_perplexity": 154.10650634765625, "codebook_active": 289.0, "codebook_commit": 0.1660279780626297} | |
| {"step": 10500, "epoch": 28, "loss": 0.2121775895357132, "task_loss": 0.1599140614271164, "partitioner_loss": 0.042123183608055115, "running_macro_f1": 0.6076378280300735, "running_accuracy": 0.8659375, "lr": 0.0001930285823290702, "codebook_loss": 0.040561385452747345, "codebook_perplexity": 203.4247589111328, "codebook_active": 339.0, "codebook_commit": 0.16224554181098938} | |
| {"step": 10550, "epoch": 28, "loss": 0.23692961037158966, "task_loss": 0.17952729761600494, "partitioner_loss": 0.0484461709856987, "running_macro_f1": 0.6297515487337104, "running_accuracy": 0.8894848105230191, "lr": 0.0001930285823290702, "codebook_loss": 0.035824574530124664, "codebook_perplexity": 129.00921630859375, "codebook_active": 272.0, "codebook_commit": 0.14329829812049866} | |
| {"epoch": 28, "split": "val", "val_macro_f1": 0.3203136995713128, "val_accuracy": 0.6258008153756552} | |
| {"step": 10600, "epoch": 29, "loss": 0.23566585779190063, "task_loss": 0.18446867167949677, "partitioner_loss": 0.04163171350955963, "running_macro_f1": 0.6459012281389667, "running_accuracy": 0.8965625, "lr": 0.0001903089844037078, "codebook_loss": 0.03826192021369934, "codebook_perplexity": 86.83979797363281, "codebook_active": 265.0, "codebook_commit": 0.15304768085479736} | |
| {"step": 10650, "epoch": 29, "loss": 0.17586489021778107, "task_loss": 0.12497790902853012, "partitioner_loss": 0.041573017835617065, "running_macro_f1": 0.6910685529252651, "running_accuracy": 0.917265625, "lr": 0.0001903089844037078, "codebook_loss": 0.03725581243634224, "codebook_perplexity": 126.45333099365234, "codebook_active": 282.0, "codebook_commit": 0.14902324974536896} | |
| {"step": 10700, "epoch": 29, "loss": 0.2129688262939453, "task_loss": 0.15990926325321198, "partitioner_loss": 0.04408153146505356, "running_macro_f1": 0.6679648011318013, "running_accuracy": 0.912734375, "lr": 0.0001903089844037078, "codebook_loss": 0.035912178456783295, "codebook_perplexity": 212.03573608398438, "codebook_active": 366.0, "codebook_commit": 0.14364871382713318} | |
| {"step": 10750, "epoch": 29, "loss": 0.5234864354133606, "task_loss": 0.4744004011154175, "partitioner_loss": 0.040883082896471024, "running_macro_f1": 0.639565960646195, "running_accuracy": 0.8988412151581585, "lr": 0.0001903089844037078, "codebook_loss": 0.03281189873814583, "codebook_perplexity": 123.71549987792969, "codebook_active": 331.0, "codebook_commit": 0.1312475949525833} | |
| {"step": 10800, "epoch": 29, "loss": 0.46373113989830017, "task_loss": 0.41404488682746887, "partitioner_loss": 0.03732339292764664, "running_macro_f1": 0.6463094372482195, "running_accuracy": 0.89734375, "lr": 0.0001903089844037078, "codebook_loss": 0.049451444298028946, "codebook_perplexity": 177.427001953125, "codebook_active": 327.0, "codebook_commit": 0.19780577719211578} | |
| {"step": 10850, "epoch": 29, "loss": 4.233652591705322, "task_loss": 4.18189811706543, "partitioner_loss": 0.0416138619184494, "running_macro_f1": 0.6493444492708249, "running_accuracy": 0.8987890625, "lr": 0.0001903089844037078, "codebook_loss": 0.04056239873170853, "codebook_perplexity": 125.1941146850586, "codebook_active": 247.0, "codebook_commit": 0.1622495949268341} | |
| {"step": 10900, "epoch": 29, "loss": 0.39980602264404297, "task_loss": 0.3425460755825043, "partitioner_loss": 0.04748508334159851, "running_macro_f1": 0.6178322361752417, "running_accuracy": 0.883125, "lr": 0.0001903089844037078, "codebook_loss": 0.03909939527511597, "codebook_perplexity": 132.38792419433594, "codebook_active": 264.0, "codebook_commit": 0.15639758110046387} | |
| {"step": 10950, "epoch": 29, "loss": 0.26593178510665894, "task_loss": 0.21680957078933716, "partitioner_loss": 0.03993107005953789, "running_macro_f1": 0.6570149917981438, "running_accuracy": 0.9, "lr": 0.0001903089844037078, "codebook_loss": 0.03676462173461914, "codebook_perplexity": 122.83336639404297, "codebook_active": 269.0, "codebook_commit": 0.14705848693847656} | |
| {"epoch": 29, "split": "val", "val_macro_f1": 0.3567359512479699, "val_accuracy": 0.6407493690545525} | |
| {"step": 11000, "epoch": 30, "loss": 0.25240543484687805, "task_loss": 0.19730347394943237, "partitioner_loss": 0.04485108703374863, "running_macro_f1": 0.6781423572024586, "running_accuracy": 0.9154296875, "lr": 0.0001875135567147201, "codebook_loss": 0.04100347310304642, "codebook_perplexity": 155.70335388183594, "codebook_active": 336.0, "codebook_commit": 0.16401389241218567} | |
| {"step": 11050, "epoch": 30, "loss": 0.3076173961162567, "task_loss": 0.24996446073055267, "partitioner_loss": 0.046938396990299225, "running_macro_f1": 0.6983429213712443, "running_accuracy": 0.917734375, "lr": 0.0001875135567147201, "codebook_loss": 0.04285813122987747, "codebook_perplexity": 141.31341552734375, "codebook_active": 295.0, "codebook_commit": 0.1714325249195099} | |
| {"step": 11100, "epoch": 30, "loss": 0.2708531320095062, "task_loss": 0.21778208017349243, "partitioner_loss": 0.04262714087963104, "running_macro_f1": 0.685815013721463, "running_accuracy": 0.9094140625, "lr": 0.0001875135567147201, "codebook_loss": 0.04177554324269295, "codebook_perplexity": 183.25453186035156, "codebook_active": 319.0, "codebook_commit": 0.1671021729707718} | |
| {"step": 11150, "epoch": 30, "loss": 0.22718317806720734, "task_loss": 0.18005365133285522, "partitioner_loss": 0.036863282322883606, "running_macro_f1": 0.6492686794212504, "running_accuracy": 0.910078125, "lr": 0.0001875135567147201, "codebook_loss": 0.04106497764587402, "codebook_perplexity": 94.25077056884766, "codebook_active": 264.0, "codebook_commit": 0.1642599105834961} | |
| {"step": 11200, "epoch": 30, "loss": 0.4613158702850342, "task_loss": 0.4116898477077484, "partitioner_loss": 0.03850901499390602, "running_macro_f1": 0.6580695927979714, "running_accuracy": 0.9105859375, "lr": 0.0001875135567147201, "codebook_loss": 0.04446800798177719, "codebook_perplexity": 104.26944732666016, "codebook_active": 251.0, "codebook_commit": 0.17787203192710876} | |
| {"step": 11250, "epoch": 30, "loss": 0.3815222382545471, "task_loss": 0.3336469233036041, "partitioner_loss": 0.038137517869472504, "running_macro_f1": 0.6608992607038419, "running_accuracy": 0.898203125, "lr": 0.0001875135567147201, "codebook_loss": 0.038951098918914795, "codebook_perplexity": 139.51821899414062, "codebook_active": 270.0, "codebook_commit": 0.15580439567565918} | |
| {"step": 11300, "epoch": 30, "loss": 0.44492921233177185, "task_loss": 0.3875587284564972, "partitioner_loss": 0.047792620956897736, "running_macro_f1": 0.6618686123168361, "running_accuracy": 0.8981365487002818, "lr": 0.0001875135567147201, "codebook_loss": 0.03831150010228157, "codebook_perplexity": 204.9772186279297, "codebook_active": 374.0, "codebook_commit": 0.15324600040912628} | |
| {"epoch": 30, "split": "val", "val_macro_f1": 0.347160840664619, "val_accuracy": 0.6449233158609978} | |
| {"step": 11350, "epoch": 31, "loss": 0.24334914982318878, "task_loss": 0.19353704154491425, "partitioner_loss": 0.04051712900400162, "running_macro_f1": 0.6323004495828907, "running_accuracy": 0.90265625, "lr": 0.00018464511402083167, "codebook_loss": 0.03717987984418869, "codebook_perplexity": 116.7929458618164, "codebook_active": 308.0, "codebook_commit": 0.14871951937675476} | |
| {"step": 11400, "epoch": 31, "loss": 0.8913396000862122, "task_loss": 0.8379798531532288, "partitioner_loss": 0.0434543751180172, "running_macro_f1": 0.663704794364727, "running_accuracy": 0.897421875, "lr": 0.00018464511402083167, "codebook_loss": 0.03962162137031555, "codebook_perplexity": 106.66854858398438, "codebook_active": 282.0, "codebook_commit": 0.1584864854812622} | |
| {"step": 11450, "epoch": 31, "loss": 0.28404518961906433, "task_loss": 0.2368389219045639, "partitioner_loss": 0.038569800555706024, "running_macro_f1": 0.6704844362840793, "running_accuracy": 0.931796875, "lr": 0.00018464511402083167, "codebook_loss": 0.03454585373401642, "codebook_perplexity": 105.78779602050781, "codebook_active": 253.0, "codebook_commit": 0.13818341493606567} | |
| {"step": 11500, "epoch": 31, "loss": 0.8973236083984375, "task_loss": 0.8360131978988647, "partitioner_loss": 0.051190413534641266, "running_macro_f1": 0.6577796875412263, "running_accuracy": 0.903984375, "lr": 0.00018464511402083167, "codebook_loss": 0.04047992452979088, "codebook_perplexity": 30.105070114135742, "codebook_active": 114.0, "codebook_commit": 0.1619196981191635} | |
| {"step": 11550, "epoch": 31, "loss": 0.33698180317878723, "task_loss": 0.2806548476219177, "partitioner_loss": 0.04557500034570694, "running_macro_f1": 0.6969434336929472, "running_accuracy": 0.92484375, "lr": 0.00018464511402083167, "codebook_loss": 0.043007802218198776, "codebook_perplexity": 144.9444122314453, "codebook_active": 315.0, "codebook_commit": 0.1720312088727951} | |
| {"step": 11600, "epoch": 31, "loss": 0.2042885571718216, "task_loss": 0.1484750211238861, "partitioner_loss": 0.04565291479229927, "running_macro_f1": 0.6748080774383831, "running_accuracy": 0.9090197306608205, "lr": 0.00018464511402083167, "codebook_loss": 0.04064251482486725, "codebook_perplexity": 170.6951446533203, "codebook_active": 344.0, "codebook_commit": 0.162570059299469} | |
| {"step": 11650, "epoch": 31, "loss": 0.28560394048690796, "task_loss": 0.23370589315891266, "partitioner_loss": 0.04093247652053833, "running_macro_f1": 0.6961125854883217, "running_accuracy": 0.9154296875, "lr": 0.00018464511402083167, "codebook_loss": 0.04386232793331146, "codebook_perplexity": 125.85299682617188, "codebook_active": 269.0, "codebook_commit": 0.17544931173324585} | |
| {"step": 11700, "epoch": 31, "loss": 0.5685593485832214, "task_loss": 0.5021892786026001, "partitioner_loss": 0.05657443776726723, "running_macro_f1": 0.6639841849063038, "running_accuracy": 0.9090234375, "lr": 0.00018464511402083167, "codebook_loss": 0.0391823872923851, "codebook_perplexity": 52.19725799560547, "codebook_active": 164.0, "codebook_commit": 0.1567295491695404} | |
| {"epoch": 31, "split": "val", "val_macro_f1": 0.3542406644101978, "val_accuracy": 0.6304601048340128} | |
| {"step": 11750, "epoch": 32, "loss": 0.19477741420269012, "task_loss": 0.14480900764465332, "partitioner_loss": 0.042021606117486954, "running_macro_f1": 0.6849478121658593, "running_accuracy": 0.92625, "lr": 0.0001817065446006878, "codebook_loss": 0.03178722411394119, "codebook_perplexity": 102.24396514892578, "codebook_active": 306.0, "codebook_commit": 0.12714889645576477} | |
| {"step": 11800, "epoch": 32, "loss": 0.13673575222492218, "task_loss": 0.08397728949785233, "partitioner_loss": 0.04357755929231644, "running_macro_f1": 0.7028211338343725, "running_accuracy": 0.928359375, "lr": 0.0001817065446006878, "codebook_loss": 0.03672359883785248, "codebook_perplexity": 196.0618133544922, "codebook_active": 370.0, "codebook_commit": 0.1468943953514099} | |
| {"step": 11850, "epoch": 32, "loss": 0.35165584087371826, "task_loss": 0.30271127820014954, "partitioner_loss": 0.03954362869262695, "running_macro_f1": 0.677659731777183, "running_accuracy": 0.9239743188224241, "lr": 0.0001817065446006878, "codebook_loss": 0.03760369122028351, "codebook_perplexity": 118.77440643310547, "codebook_active": 289.0, "codebook_commit": 0.15041476488113403} | |
| {"step": 11900, "epoch": 32, "loss": 0.27728453278541565, "task_loss": 0.22396758198738098, "partitioner_loss": 0.04398173838853836, "running_macro_f1": 0.6558053005789766, "running_accuracy": 0.9007421875, "lr": 0.0001817065446006878, "codebook_loss": 0.037340931594371796, "codebook_perplexity": 215.48483276367188, "codebook_active": 374.0, "codebook_commit": 0.14936372637748718} | |
| {"step": 11950, "epoch": 32, "loss": 0.15223637223243713, "task_loss": 0.10334152728319168, "partitioner_loss": 0.040760282427072525, "running_macro_f1": 0.7104593105226406, "running_accuracy": 0.9392578125, "lr": 0.0001817065446006878, "codebook_loss": 0.03253825008869171, "codebook_perplexity": 100.90939331054688, "codebook_active": 254.0, "codebook_commit": 0.13015300035476685} | |
| {"step": 12000, "epoch": 32, "loss": 0.21387708187103271, "task_loss": 0.160630002617836, "partitioner_loss": 0.04440257325768471, "running_macro_f1": 0.6915289391399219, "running_accuracy": 0.922421875, "lr": 0.0001817065446006878, "codebook_loss": 0.03537806123495102, "codebook_perplexity": 191.24462890625, "codebook_active": 366.0, "codebook_commit": 0.14151224493980408} | |
| {"step": 12050, "epoch": 32, "loss": 0.1802167147397995, "task_loss": 0.12574434280395508, "partitioner_loss": 0.04454265162348747, "running_macro_f1": 0.7019287199108718, "running_accuracy": 0.926328125, "lr": 0.0001817065446006878, "codebook_loss": 0.0397188663482666, "codebook_perplexity": 135.64120483398438, "codebook_active": 312.0, "codebook_commit": 0.1588754653930664} | |
| {"epoch": 32, "split": "val", "val_macro_f1": 0.3603584478148149, "val_accuracy": 0.6624927198602213} | |
| {"step": 12100, "epoch": 33, "loss": 1.6315721273422241, "task_loss": 1.5738933086395264, "partitioner_loss": 0.04708658903837204, "running_macro_f1": 0.694005726986718, "running_accuracy": 0.922109375, "lr": 0.0001787008073446027, "codebook_loss": 0.04236902669072151, "codebook_perplexity": 107.35077667236328, "codebook_active": 292.0, "codebook_commit": 0.16947610676288605} | |
| {"step": 12150, "epoch": 33, "loss": 0.3029407560825348, "task_loss": 0.2459823042154312, "partitioner_loss": 0.047517530620098114, "running_macro_f1": 0.6895283876140064, "running_accuracy": 0.908828125, "lr": 0.0001787008073446027, "codebook_loss": 0.03776370733976364, "codebook_perplexity": 121.46073913574219, "codebook_active": 317.0, "codebook_commit": 0.15105482935905457} | |
| {"step": 12200, "epoch": 33, "loss": 0.13133712112903595, "task_loss": 0.0845286101102829, "partitioner_loss": 0.04009653627872467, "running_macro_f1": 0.6622002607804164, "running_accuracy": 0.9203125, "lr": 0.0001787008073446027, "codebook_loss": 0.026847904548048973, "codebook_perplexity": 171.5635528564453, "codebook_active": 348.0, "codebook_commit": 0.10739161819219589} | |
| {"step": 12250, "epoch": 33, "loss": 0.14236797392368317, "task_loss": 0.09119436889886856, "partitioner_loss": 0.03983921557664871, "running_macro_f1": 0.7076370012997171, "running_accuracy": 0.9337890625, "lr": 0.0001787008073446027, "codebook_loss": 0.04533753916621208, "codebook_perplexity": 62.35658264160156, "codebook_active": 199.0, "codebook_commit": 0.18135015666484833} | |
| {"step": 12300, "epoch": 33, "loss": 0.6700906157493591, "task_loss": 0.6117561459541321, "partitioner_loss": 0.04715238884091377, "running_macro_f1": 0.6935632197443661, "running_accuracy": 0.9209375, "lr": 0.0001787008073446027, "codebook_loss": 0.04472818970680237, "codebook_perplexity": 29.587154388427734, "codebook_active": 108.0, "codebook_commit": 0.17891275882720947} | |
| {"step": 12350, "epoch": 33, "loss": 0.2724934220314026, "task_loss": 0.2231650948524475, "partitioner_loss": 0.03788629174232483, "running_macro_f1": 0.6996631036876798, "running_accuracy": 0.9226041340432195, "lr": 0.0001787008073446027, "codebook_loss": 0.04576810821890831, "codebook_perplexity": 86.70838928222656, "codebook_active": 256.0, "codebook_commit": 0.18307243287563324} | |
| {"step": 12400, "epoch": 33, "loss": 0.7715110182762146, "task_loss": 0.7214614152908325, "partitioner_loss": 0.03994593769311905, "running_macro_f1": 0.7042926562384056, "running_accuracy": 0.924375, "lr": 0.0001787008073446027, "codebook_loss": 0.04041454941034317, "codebook_perplexity": 86.50360107421875, "codebook_active": 219.0, "codebook_commit": 0.16165819764137268} | |
| {"step": 12450, "epoch": 33, "loss": 0.3554190695285797, "task_loss": 0.2936719059944153, "partitioner_loss": 0.04643609747290611, "running_macro_f1": 0.6923182212167666, "running_accuracy": 0.929296875, "lr": 0.0001787008073446027, "codebook_loss": 0.061244264245033264, "codebook_perplexity": 17.460397720336914, "codebook_active": 91.0, "codebook_commit": 0.24497705698013306} | |
| {"epoch": 33, "split": "val", "val_macro_f1": 0.35030441211718055, "val_accuracy": 0.6471558920597942} | |
| {"step": 12500, "epoch": 34, "loss": 0.1500312238931656, "task_loss": 0.1063050851225853, "partitioner_loss": 0.038852326571941376, "running_macro_f1": 0.6792172183913305, "running_accuracy": 0.9098828125, "lr": 0.00017563092877520778, "codebook_loss": 0.01949525997042656, "codebook_perplexity": 151.2359619140625, "codebook_active": 289.0, "codebook_commit": 0.07798103988170624} | |
| {"step": 12550, "epoch": 34, "loss": 0.19401401281356812, "task_loss": 0.14548753201961517, "partitioner_loss": 0.03948141634464264, "running_macro_f1": 0.6744040538694138, "running_accuracy": 0.91890625, "lr": 0.00017563092877520778, "codebook_loss": 0.03618024289608002, "codebook_perplexity": 169.6021270751953, "codebook_active": 320.0, "codebook_commit": 0.14472097158432007} | |
| {"step": 12600, "epoch": 34, "loss": 0.22138415277004242, "task_loss": 0.17330233752727509, "partitioner_loss": 0.03952660411596298, "running_macro_f1": 0.7311124428879027, "running_accuracy": 0.9312109375, "lr": 0.00017563092877520778, "codebook_loss": 0.034220870584249496, "codebook_perplexity": 193.1698455810547, "codebook_active": 369.0, "codebook_commit": 0.13688348233699799} | |
| {"step": 12650, "epoch": 34, "loss": 0.2600245773792267, "task_loss": 0.21040719747543335, "partitioner_loss": 0.041147761046886444, "running_macro_f1": 0.7076374738779918, "running_accuracy": 0.9390625, "lr": 0.00017563092877520778, "codebook_loss": 0.03387841582298279, "codebook_perplexity": 169.57591247558594, "codebook_active": 315.0, "codebook_commit": 0.13551366329193115} | |
| {"step": 12700, "epoch": 34, "loss": 0.31561872363090515, "task_loss": 0.2599986493587494, "partitioner_loss": 0.0463583841919899, "running_macro_f1": 0.7045823675814757, "running_accuracy": 0.92109375, "lr": 0.00017563092877520778, "codebook_loss": 0.03704679012298584, "codebook_perplexity": 149.72203063964844, "codebook_active": 343.0, "codebook_commit": 0.14818716049194336} | |
| {"step": 12750, "epoch": 34, "loss": 0.22634297609329224, "task_loss": 0.17090648412704468, "partitioner_loss": 0.04496509209275246, "running_macro_f1": 0.6825937501966279, "running_accuracy": 0.929765625, "lr": 0.00017563092877520778, "codebook_loss": 0.04188559204339981, "codebook_perplexity": 190.8259735107422, "codebook_active": 372.0, "codebook_commit": 0.16754236817359924} | |
| {"step": 12800, "epoch": 34, "loss": 0.1519249826669693, "task_loss": 0.1020861268043518, "partitioner_loss": 0.039868660271167755, "running_macro_f1": 0.6604640187475195, "running_accuracy": 0.9054963983714375, "lr": 0.00017563092877520778, "codebook_loss": 0.03988078981637955, "codebook_perplexity": 143.45016479492188, "codebook_active": 306.0, "codebook_commit": 0.1595231592655182} | |
| {"step": 12850, "epoch": 34, "loss": 0.5334795117378235, "task_loss": 0.475689172744751, "partitioner_loss": 0.04680013656616211, "running_macro_f1": 0.6919863644121429, "running_accuracy": 0.9203125, "lr": 0.00017563092877520778, "codebook_loss": 0.043960846960544586, "codebook_perplexity": 142.41217041015625, "codebook_active": 320.0, "codebook_commit": 0.17584338784217834} | |
| {"epoch": 34, "split": "val", "val_macro_f1": 0.33434250281332417, "val_accuracy": 0.6294894195301883} | |
| {"step": 12900, "epoch": 35, "loss": 0.1315670907497406, "task_loss": 0.07672986388206482, "partitioner_loss": 0.04576035961508751, "running_macro_f1": 0.6723437410012882, "running_accuracy": 0.92375, "lr": 0.00017250000000000002, "codebook_loss": 0.03630742430686951, "codebook_perplexity": 166.45175170898438, "codebook_active": 335.0, "codebook_commit": 0.14522969722747803} | |
| {"step": 12950, "epoch": 35, "loss": 0.37664785981178284, "task_loss": 0.31965091824531555, "partitioner_loss": 0.04522762447595596, "running_macro_f1": 0.6739349795459614, "running_accuracy": 0.89640625, "lr": 0.00017250000000000002, "codebook_loss": 0.047077298164367676, "codebook_perplexity": 96.53036499023438, "codebook_active": 247.0, "codebook_commit": 0.1883091926574707} | |
| {"step": 13000, "epoch": 35, "loss": 0.24338045716285706, "task_loss": 0.19100697338581085, "partitioner_loss": 0.04269479215145111, "running_macro_f1": 0.6758608039192977, "running_accuracy": 0.9201378014406514, "lr": 0.00017250000000000002, "codebook_loss": 0.03871474042534828, "codebook_perplexity": 175.5468292236328, "codebook_active": 337.0, "codebook_commit": 0.15485896170139313} | |
| {"step": 13050, "epoch": 35, "loss": 0.20324623584747314, "task_loss": 0.15235336124897003, "partitioner_loss": 0.04020228981971741, "running_macro_f1": 0.677325087327966, "running_accuracy": 0.9215625, "lr": 0.00017250000000000002, "codebook_loss": 0.042762335389852524, "codebook_perplexity": 110.36083984375, "codebook_active": 275.0, "codebook_commit": 0.1710493415594101} | |
| {"step": 13100, "epoch": 35, "loss": 0.2001192271709442, "task_loss": 0.14974234998226166, "partitioner_loss": 0.03959687054157257, "running_macro_f1": 0.6874946225881867, "running_accuracy": 0.9293359375, "lr": 0.00017250000000000002, "codebook_loss": 0.043120019137859344, "codebook_perplexity": 144.81838989257812, "codebook_active": 321.0, "codebook_commit": 0.17248007655143738} | |
| {"step": 13150, "epoch": 35, "loss": 0.25307244062423706, "task_loss": 0.2041773945093155, "partitioner_loss": 0.03831230103969574, "running_macro_f1": 0.7027364304825308, "running_accuracy": 0.9158984375, "lr": 0.00017250000000000002, "codebook_loss": 0.042330943048000336, "codebook_perplexity": 211.0042266845703, "codebook_active": 365.0, "codebook_commit": 0.16932377219200134} | |
| {"step": 13200, "epoch": 35, "loss": 0.2004324346780777, "task_loss": 0.15103109180927277, "partitioner_loss": 0.04012763127684593, "running_macro_f1": 0.7031566743310061, "running_accuracy": 0.9275, "lr": 0.00017250000000000002, "codebook_loss": 0.037094853818416595, "codebook_perplexity": 176.66452026367188, "codebook_active": 336.0, "codebook_commit": 0.14837941527366638} | |
| {"epoch": 35, "split": "val", "val_macro_f1": 0.3360493963438306, "val_accuracy": 0.6610366919044846} | |
| {"step": 13250, "epoch": 36, "loss": 0.21243934333324432, "task_loss": 0.16151806712150574, "partitioner_loss": 0.041981782764196396, "running_macro_f1": 0.6706837515128274, "running_accuracy": 0.9178515625, "lr": 0.00016931117359885852, "codebook_loss": 0.03575795516371727, "codebook_perplexity": 156.16688537597656, "codebook_active": 306.0, "codebook_commit": 0.14303182065486908} | |
| {"step": 13300, "epoch": 36, "loss": 0.21233510971069336, "task_loss": 0.1632007509469986, "partitioner_loss": 0.03868487477302551, "running_macro_f1": 0.6903837298045714, "running_accuracy": 0.9216015625, "lr": 0.00016931117359885852, "codebook_loss": 0.04179796576499939, "codebook_perplexity": 202.56829833984375, "codebook_active": 358.0, "codebook_commit": 0.16719186305999756} | |
| {"step": 13350, "epoch": 36, "loss": 0.3084399402141571, "task_loss": 0.2584143280982971, "partitioner_loss": 0.04015881568193436, "running_macro_f1": 0.6867612487023349, "running_accuracy": 0.93171875, "lr": 0.00016931117359885852, "codebook_loss": 0.03946724534034729, "codebook_perplexity": 127.04254150390625, "codebook_active": 306.0, "codebook_commit": 0.15786898136138916} | |
| {"step": 13400, "epoch": 36, "loss": 0.2350986897945404, "task_loss": 0.18850906193256378, "partitioner_loss": 0.03934381157159805, "running_macro_f1": 0.6820051852663944, "running_accuracy": 0.9046875, "lr": 0.00016931117359885852, "codebook_loss": 0.028983231633901596, "codebook_perplexity": 173.73194885253906, "codebook_active": 349.0, "codebook_commit": 0.11593292653560638} | |
| {"step": 13450, "epoch": 36, "loss": 0.41721853613853455, "task_loss": 0.3669198751449585, "partitioner_loss": 0.04249238222837448, "running_macro_f1": 0.6493556815320969, "running_accuracy": 0.9046484375, "lr": 0.00016931117359885852, "codebook_loss": 0.03122512809932232, "codebook_perplexity": 206.4686737060547, "codebook_active": 369.0, "codebook_commit": 0.12490051239728928} | |
| {"step": 13500, "epoch": 36, "loss": 0.21813344955444336, "task_loss": 0.16602589190006256, "partitioner_loss": 0.04316192865371704, "running_macro_f1": 0.6540279328158735, "running_accuracy": 0.9192578125, "lr": 0.00016931117359885852, "codebook_loss": 0.035782523453235626, "codebook_perplexity": 160.3397979736328, "codebook_active": 347.0, "codebook_commit": 0.1431300938129425} | |
| {"step": 13550, "epoch": 36, "loss": 0.3861120641231537, "task_loss": 0.3334706127643585, "partitioner_loss": 0.044224463403224945, "running_macro_f1": 0.6642325437294032, "running_accuracy": 0.9150093955527717, "lr": 0.00016931117359885852, "codebook_loss": 0.03366793319582939, "codebook_perplexity": 64.1403579711914, "codebook_active": 165.0, "codebook_commit": 0.13467173278331757} | |
| {"step": 13600, "epoch": 36, "loss": 0.18192850053310394, "task_loss": 0.13066813349723816, "partitioner_loss": 0.04094556346535683, "running_macro_f1": 0.6911220676599555, "running_accuracy": 0.9253515625, "lr": 0.00016931117359885852, "codebook_loss": 0.04125920683145523, "codebook_perplexity": 168.78550720214844, "codebook_active": 353.0, "codebook_commit": 0.16503682732582092} | |
| {"epoch": 36, "split": "val", "val_macro_f1": 0.35681959183482764, "val_accuracy": 0.6451174529217628} | |
| {"step": 13650, "epoch": 37, "loss": 0.11985735595226288, "task_loss": 0.0718652606010437, "partitioner_loss": 0.03914792090654373, "running_macro_f1": 0.7175189028226922, "running_accuracy": 0.9378125, "lr": 0.00016606766044966403, "codebook_loss": 0.035376690328121185, "codebook_perplexity": 169.42478942871094, "codebook_active": 318.0, "codebook_commit": 0.14150676131248474} | |
| {"step": 13700, "epoch": 37, "loss": 0.3628884553909302, "task_loss": 0.3114592134952545, "partitioner_loss": 0.04151399806141853, "running_macro_f1": 0.7039552010864976, "running_accuracy": 0.933643908549953, "lr": 0.00016606766044966403, "codebook_loss": 0.03966096416115761, "codebook_perplexity": 178.55239868164062, "codebook_active": 356.0, "codebook_commit": 0.15864385664463043} | |
| {"step": 13750, "epoch": 37, "loss": 0.14090271294116974, "task_loss": 0.08708760142326355, "partitioner_loss": 0.04392269253730774, "running_macro_f1": 0.7264986859224977, "running_accuracy": 0.9394921875, "lr": 0.00016606766044966403, "codebook_loss": 0.0395696759223938, "codebook_perplexity": 136.79739379882812, "codebook_active": 307.0, "codebook_commit": 0.1582787036895752} | |
| {"step": 13800, "epoch": 37, "loss": 0.21944035589694977, "task_loss": 0.1691451370716095, "partitioner_loss": 0.038567449897527695, "running_macro_f1": 0.7043939118436436, "running_accuracy": 0.9321875, "lr": 0.00016606766044966403, "codebook_loss": 0.04691106081008911, "codebook_perplexity": 181.5219268798828, "codebook_active": 335.0, "codebook_commit": 0.18764424324035645} | |
| {"step": 13850, "epoch": 37, "loss": 0.23824870586395264, "task_loss": 0.18812638521194458, "partitioner_loss": 0.039738863706588745, "running_macro_f1": 0.701264291927677, "running_accuracy": 0.93296875, "lr": 0.00016606766044966403, "codebook_loss": 0.04153381288051605, "codebook_perplexity": 181.77735900878906, "codebook_active": 312.0, "codebook_commit": 0.1661352515220642} | |
| {"step": 13900, "epoch": 37, "loss": 0.1456597000360489, "task_loss": 0.08935161679983139, "partitioner_loss": 0.046316660940647125, "running_macro_f1": 0.6761421663359405, "running_accuracy": 0.9269140625, "lr": 0.00016606766044966403, "codebook_loss": 0.0399656742811203, "codebook_perplexity": 118.82466125488281, "codebook_active": 287.0, "codebook_commit": 0.1598626971244812} | |
| {"step": 13950, "epoch": 37, "loss": 0.1606443077325821, "task_loss": 0.1124747097492218, "partitioner_loss": 0.03829386830329895, "running_macro_f1": 0.6986572335577187, "running_accuracy": 0.915625, "lr": 0.00016606766044966403, "codebook_loss": 0.03950289636850357, "codebook_perplexity": 158.57913208007812, "codebook_active": 315.0, "codebook_commit": 0.15801158547401428} | |
| {"epoch": 37, "split": "val", "val_macro_f1": 0.33835915156955987, "val_accuracy": 0.6334692292758688} | |
| {"step": 14000, "epoch": 38, "loss": 0.18043489754199982, "task_loss": 0.12548679113388062, "partitioner_loss": 0.04608515650033951, "running_macro_f1": 0.6585413673429145, "running_accuracy": 0.910390625, "lr": 0.00016277272649521695, "codebook_loss": 0.03545180708169937, "codebook_perplexity": 66.9413833618164, "codebook_active": 194.0, "codebook_commit": 0.14180722832679749} | |
| {"step": 14050, "epoch": 38, "loss": 0.15136028826236725, "task_loss": 0.1061912551522255, "partitioner_loss": 0.03772181645035744, "running_macro_f1": 0.6884677952877023, "running_accuracy": 0.9251171875, "lr": 0.00016277272649521695, "codebook_loss": 0.02978883683681488, "codebook_perplexity": 228.48236083984375, "codebook_active": 402.0, "codebook_commit": 0.11915534734725952} | |
| {"step": 14100, "epoch": 38, "loss": 0.11270469427108765, "task_loss": 0.06804029643535614, "partitioner_loss": 0.037573814392089844, "running_macro_f1": 0.6838815450327348, "running_accuracy": 0.9403515625, "lr": 0.00016277272649521695, "codebook_loss": 0.028362328186631203, "codebook_perplexity": 124.00206756591797, "codebook_active": 290.0, "codebook_commit": 0.11344931274652481} | |
| {"step": 14150, "epoch": 38, "loss": 0.18359822034835815, "task_loss": 0.13148286938667297, "partitioner_loss": 0.041000351309776306, "running_macro_f1": 0.7289208314904114, "running_accuracy": 0.926875, "lr": 0.00016277272649521695, "codebook_loss": 0.044460002332925797, "codebook_perplexity": 129.37698364257812, "codebook_active": 284.0, "codebook_commit": 0.17784000933170319} | |
| {"step": 14200, "epoch": 38, "loss": 0.15405656397342682, "task_loss": 0.10951109230518341, "partitioner_loss": 0.03626953810453415, "running_macro_f1": 0.6564912337165915, "running_accuracy": 0.9140234375, "lr": 0.00016277272649521695, "codebook_loss": 0.03310377523303032, "codebook_perplexity": 144.5658721923828, "codebook_active": 297.0, "codebook_commit": 0.13241510093212128} | |
| {"step": 14250, "epoch": 38, "loss": 0.1705816239118576, "task_loss": 0.1220514103770256, "partitioner_loss": 0.03886880725622177, "running_macro_f1": 0.6973264891009948, "running_accuracy": 0.9144140625, "lr": 0.00016277272649521695, "codebook_loss": 0.03864561766386032, "codebook_perplexity": 87.39774322509766, "codebook_active": 258.0, "codebook_commit": 0.15458247065544128} | |
| {"step": 14300, "epoch": 38, "loss": 0.32249584794044495, "task_loss": 0.2737116813659668, "partitioner_loss": 0.03851710632443428, "running_macro_f1": 0.6991258105886448, "running_accuracy": 0.9205859375, "lr": 0.00016277272649521695, "codebook_loss": 0.04106816649436951, "codebook_perplexity": 185.15394592285156, "codebook_active": 336.0, "codebook_commit": 0.16427266597747803} | |
| {"step": 14350, "epoch": 38, "loss": 0.17880097031593323, "task_loss": 0.1255892962217331, "partitioner_loss": 0.042818933725357056, "running_macro_f1": 0.6617505306907853, "running_accuracy": 0.8984765625, "lr": 0.00016277272649521695, "codebook_loss": 0.04157097265124321, "codebook_perplexity": 172.2736358642578, "codebook_active": 340.0, "codebook_commit": 0.16628389060497284} | |
| {"epoch": 38, "split": "val", "val_macro_f1": 0.3441424563776817, "val_accuracy": 0.641914191419142} | |
| {"step": 14400, "epoch": 39, "loss": 0.33691757917404175, "task_loss": 0.2841484844684601, "partitioner_loss": 0.042356591671705246, "running_macro_f1": 0.6551642742357711, "running_accuracy": 0.9284372063889759, "lr": 0.0001594296894547098, "codebook_loss": 0.04165007919073105, "codebook_perplexity": 141.6969451904297, "codebook_active": 324.0, "codebook_commit": 0.1666003167629242} | |
| {"step": 14450, "epoch": 39, "loss": 0.3958417773246765, "task_loss": 0.3445701003074646, "partitioner_loss": 0.03941340371966362, "running_macro_f1": 0.6929525172777857, "running_accuracy": 0.923671875, "lr": 0.0001594296894547098, "codebook_loss": 0.04743319749832153, "codebook_perplexity": 46.153106689453125, "codebook_active": 208.0, "codebook_commit": 0.18973278999328613} | |
| {"step": 14500, "epoch": 39, "loss": 0.1636027842760086, "task_loss": 0.11354640871286392, "partitioner_loss": 0.04058096930384636, "running_macro_f1": 0.7058384287217052, "running_accuracy": 0.9292593172564986, "lr": 0.0001594296894547098, "codebook_loss": 0.03790166229009628, "codebook_perplexity": 158.59341430664062, "codebook_active": 264.0, "codebook_commit": 0.15160664916038513} | |
| {"step": 14550, "epoch": 39, "loss": 0.16149988770484924, "task_loss": 0.10193861275911331, "partitioner_loss": 0.051522575318813324, "running_macro_f1": 0.6498325383107455, "running_accuracy": 0.8998046875, "lr": 0.0001594296894547098, "codebook_loss": 0.03215479850769043, "codebook_perplexity": 183.9204559326172, "codebook_active": 355.0, "codebook_commit": 0.12861919403076172} | |
| {"step": 14600, "epoch": 39, "loss": 0.17984715104103088, "task_loss": 0.12654389441013336, "partitioner_loss": 0.04229176789522171, "running_macro_f1": 0.688538497277508, "running_accuracy": 0.9174609375, "lr": 0.0001594296894547098, "codebook_loss": 0.04404594376683235, "codebook_perplexity": 171.54824829101562, "codebook_active": 351.0, "codebook_commit": 0.1761837750673294} | |
| {"step": 14650, "epoch": 39, "loss": 0.12428939342498779, "task_loss": 0.0713844820857048, "partitioner_loss": 0.04291796311736107, "running_macro_f1": 0.67748714924341, "running_accuracy": 0.922578125, "lr": 0.0001594296894547098, "codebook_loss": 0.03994779288768768, "codebook_perplexity": 125.70394897460938, "codebook_active": 293.0, "codebook_commit": 0.15979117155075073} | |
| {"step": 14700, "epoch": 39, "loss": 0.35663479566574097, "task_loss": 0.2984083294868469, "partitioner_loss": 0.045897677540779114, "running_macro_f1": 0.6916831329984261, "running_accuracy": 0.9309765625, "lr": 0.0001594296894547098, "codebook_loss": 0.04931525141000748, "codebook_perplexity": 100.5774917602539, "codebook_active": 249.0, "codebook_commit": 0.1972610056400299} | |
| {"epoch": 39, "split": "val", "val_macro_f1": 0.36988703406488754, "val_accuracy": 0.6767617938264414} | |
| {"step": 14750, "epoch": 40, "loss": 0.14350832998752594, "task_loss": 0.09247124940156937, "partitioner_loss": 0.04169763997197151, "running_macro_f1": 0.7311359461719305, "running_accuracy": 0.9302734375, "lr": 0.00015604191548306527, "codebook_loss": 0.037357743829488754, "codebook_perplexity": 133.50270080566406, "codebook_active": 298.0, "codebook_commit": 0.14943097531795502} | |
| {"step": 14800, "epoch": 40, "loss": 0.18818356096744537, "task_loss": 0.13816896080970764, "partitioner_loss": 0.03940800204873085, "running_macro_f1": 0.7072512729159283, "running_accuracy": 0.937578125, "lr": 0.00015604191548306527, "codebook_loss": 0.042426418513059616, "codebook_perplexity": 163.4611358642578, "codebook_active": 271.0, "codebook_commit": 0.16970567405223846} | |
| {"step": 14850, "epoch": 40, "loss": 0.16081033647060394, "task_loss": 0.11095883697271347, "partitioner_loss": 0.040536973625421524, "running_macro_f1": 0.7250218302185101, "running_accuracy": 0.939140625, "lr": 0.00015604191548306527, "codebook_loss": 0.03725811466574669, "codebook_perplexity": 153.608642578125, "codebook_active": 338.0, "codebook_commit": 0.14903245866298676} | |
| {"step": 14900, "epoch": 40, "loss": 0.13918042182922363, "task_loss": 0.09448488056659698, "partitioner_loss": 0.035226285457611084, "running_macro_f1": 0.7181595386683798, "running_accuracy": 0.942139054181021, "lr": 0.00015604191548306527, "codebook_loss": 0.03787700831890106, "codebook_perplexity": 191.20997619628906, "codebook_active": 348.0, "codebook_commit": 0.15150803327560425} | |
| {"step": 14950, "epoch": 40, "loss": 0.2194570004940033, "task_loss": 0.16880853474140167, "partitioner_loss": 0.04302661120891571, "running_macro_f1": 0.7103350096930319, "running_accuracy": 0.9343359375, "lr": 0.00015604191548306527, "codebook_loss": 0.03048740141093731, "codebook_perplexity": 170.07394409179688, "codebook_active": 362.0, "codebook_commit": 0.12194960564374924} | |
| {"step": 15000, "epoch": 40, "loss": 0.3047591745853424, "task_loss": 0.2523867189884186, "partitioner_loss": 0.04291846975684166, "running_macro_f1": 0.6911691002549535, "running_accuracy": 0.9255078125, "lr": 0.00015604191548306527, "codebook_loss": 0.03781590983271599, "codebook_perplexity": 135.50454711914062, "codebook_active": 249.0, "codebook_commit": 0.15126363933086395} | |
| {"step": 15050, "epoch": 40, "loss": 0.38715222477912903, "task_loss": 0.3274209201335907, "partitioner_loss": 0.04600954428315163, "running_macro_f1": 0.7085813550858345, "running_accuracy": 0.936796875, "lr": 0.00015604191548306527, "codebook_loss": 0.05488709732890129, "codebook_perplexity": 155.6251220703125, "codebook_active": 261.0, "codebook_commit": 0.21954838931560516} | |
| {"step": 15100, "epoch": 40, "loss": 0.18689270317554474, "task_loss": 0.12324952334165573, "partitioner_loss": 0.047849949449300766, "running_macro_f1": 0.717323246895566, "running_accuracy": 0.914765625, "lr": 0.00015604191548306527, "codebook_loss": 0.06317295879125595, "codebook_perplexity": 26.979833602905273, "codebook_active": 90.0, "codebook_commit": 0.2526918351650238} | |
| {"epoch": 40, "split": "val", "val_macro_f1": 0.3638835696294927, "val_accuracy": 0.6661813240147544} | |
| {"step": 15150, "epoch": 41, "loss": 0.13617464900016785, "task_loss": 0.08255933970212936, "partitioner_loss": 0.04359957203269005, "running_macro_f1": 0.6820128560836094, "running_accuracy": 0.9155574694644535, "lr": 0.00015261281578150352, "codebook_loss": 0.040062956511974335, "codebook_perplexity": 171.517578125, "codebook_active": 333.0, "codebook_commit": 0.16025182604789734} | |
| {"step": 15200, "epoch": 41, "loss": 0.06551849842071533, "task_loss": 0.01847144402563572, "partitioner_loss": 0.038758471608161926, "running_macro_f1": 0.7215400482799598, "running_accuracy": 0.9478125, "lr": 0.00015261281578150352, "codebook_loss": 0.03315434232354164, "codebook_perplexity": 166.5094757080078, "codebook_active": 351.0, "codebook_commit": 0.13261736929416656} | |
| {"step": 15250, "epoch": 41, "loss": 0.13994377851486206, "task_loss": 0.09325281530618668, "partitioner_loss": 0.03810664266347885, "running_macro_f1": 0.7180606508125958, "running_accuracy": 0.9441015625, "lr": 0.00015261281578150352, "codebook_loss": 0.03433729708194733, "codebook_perplexity": 191.8798370361328, "codebook_active": 349.0, "codebook_commit": 0.1373491883277893} | |
| {"step": 15300, "epoch": 41, "loss": 0.2531636953353882, "task_loss": 0.2034292370080948, "partitioner_loss": 0.0408439040184021, "running_macro_f1": 0.714090788685953, "running_accuracy": 0.92484375, "lr": 0.00015261281578150352, "codebook_loss": 0.03556215763092041, "codebook_perplexity": 212.68247985839844, "codebook_active": 374.0, "codebook_commit": 0.14224863052368164} | |
| {"step": 15350, "epoch": 41, "loss": 0.24971015751361847, "task_loss": 0.19788408279418945, "partitioner_loss": 0.04177346080541611, "running_macro_f1": 0.7124409725741546, "running_accuracy": 0.9419140625, "lr": 0.00015261281578150352, "codebook_loss": 0.04021041840314865, "codebook_perplexity": 158.61740112304688, "codebook_active": 353.0, "codebook_commit": 0.1608416736125946} | |
| {"step": 15400, "epoch": 41, "loss": 0.14274878799915314, "task_loss": 0.09242210537195206, "partitioner_loss": 0.04114760458469391, "running_macro_f1": 0.7190673799766959, "running_accuracy": 0.9449609375, "lr": 0.00015261281578150352, "codebook_loss": 0.036716289818286896, "codebook_perplexity": 164.38949584960938, "codebook_active": 312.0, "codebook_commit": 0.14686515927314758} | |
| {"step": 15450, "epoch": 41, "loss": 0.20866011083126068, "task_loss": 0.15811344981193542, "partitioner_loss": 0.042125679552555084, "running_macro_f1": 0.7153601472113212, "running_accuracy": 0.9381640625, "lr": 0.00015261281578150352, "codebook_loss": 0.033683933317661285, "codebook_perplexity": 140.85728454589844, "codebook_active": 315.0, "codebook_commit": 0.13473573327064514} | |
| {"epoch": 41, "split": "val", "val_macro_f1": 0.3548284632540469, "val_accuracy": 0.6050281498738109} | |
| {"step": 15500, "epoch": 42, "loss": 0.17604121565818787, "task_loss": 0.1255422979593277, "partitioner_loss": 0.04127833992242813, "running_macro_f1": 0.6996791445759875, "running_accuracy": 0.9269140625, "lr": 0.00014914584316275164, "codebook_loss": 0.03688230738043785, "codebook_perplexity": 102.66704559326172, "codebook_active": 282.0, "codebook_commit": 0.1475292295217514} | |
| {"step": 15550, "epoch": 42, "loss": 0.25558775663375854, "task_loss": 0.200389102101326, "partitioner_loss": 0.04422701150178909, "running_macro_f1": 0.6792881405557172, "running_accuracy": 0.9218359375, "lr": 0.00014914584316275164, "codebook_loss": 0.043886490166187286, "codebook_perplexity": 156.4951934814453, "codebook_active": 320.0, "codebook_commit": 0.17554596066474915} | |
| {"step": 15600, "epoch": 42, "loss": 0.3813583552837372, "task_loss": 0.33302706480026245, "partitioner_loss": 0.03841330111026764, "running_macro_f1": 0.6894272850724515, "running_accuracy": 0.92953125, "lr": 0.00014914584316275164, "codebook_loss": 0.03967198729515076, "codebook_perplexity": 136.330810546875, "codebook_active": 324.0, "codebook_commit": 0.15868794918060303} | |
| {"step": 15650, "epoch": 42, "loss": 0.20003314316272736, "task_loss": 0.1484135240316391, "partitioner_loss": 0.04182960093021393, "running_macro_f1": 0.7254169643240781, "running_accuracy": 0.9368149076103978, "lr": 0.00014914584316275164, "codebook_loss": 0.03916005790233612, "codebook_perplexity": 155.4965057373047, "codebook_active": 352.0, "codebook_commit": 0.15664023160934448} | |
| {"step": 15700, "epoch": 42, "loss": 0.15007619559764862, "task_loss": 0.10229857265949249, "partitioner_loss": 0.03760991990566254, "running_macro_f1": 0.7218631057083017, "running_accuracy": 0.9450390625, "lr": 0.00014914584316275164, "codebook_loss": 0.040670834481716156, "codebook_perplexity": 167.1924285888672, "codebook_active": 357.0, "codebook_commit": 0.16268333792686462} | |
| {"step": 15750, "epoch": 42, "loss": 0.25401806831359863, "task_loss": 0.20623832941055298, "partitioner_loss": 0.03852167725563049, "running_macro_f1": 0.7307437882066541, "running_accuracy": 0.9355078125, "lr": 0.00014914584316275164, "codebook_loss": 0.03703225776553154, "codebook_perplexity": 118.4293212890625, "codebook_active": 253.0, "codebook_commit": 0.14812903106212616} | |
| {"step": 15800, "epoch": 42, "loss": 0.1407630741596222, "task_loss": 0.08564126491546631, "partitioner_loss": 0.04608301818370819, "running_macro_f1": 0.7182020721677456, "running_accuracy": 0.93609375, "lr": 0.00014914584316275164, "codebook_loss": 0.03615519404411316, "codebook_perplexity": 127.62159729003906, "codebook_active": 307.0, "codebook_commit": 0.14462077617645264} | |
| {"step": 15850, "epoch": 42, "loss": 0.15178067982196808, "task_loss": 0.09909224510192871, "partitioner_loss": 0.04248551279306412, "running_macro_f1": 0.7015503269372958, "running_accuracy": 0.9318359375, "lr": 0.00014914584316275164, "codebook_loss": 0.040811702609062195, "codebook_perplexity": 68.21977996826172, "codebook_active": 185.0, "codebook_commit": 0.16324681043624878} | |
| {"epoch": 42, "split": "val", "val_macro_f1": 0.3754406988487273, "val_accuracy": 0.6746262861580276} | |
| {"step": 15900, "epoch": 43, "loss": 0.5137487053871155, "task_loss": 0.46569275856018066, "partitioner_loss": 0.03956540673971176, "running_macro_f1": 0.7337710076545283, "running_accuracy": 0.9478125, "lr": 0.00014564448857435402, "codebook_loss": 0.033962152898311615, "codebook_perplexity": 97.08623504638672, "codebook_active": 287.0, "codebook_commit": 0.13584861159324646} | |
| {"step": 15950, "epoch": 43, "loss": 0.14665672183036804, "task_loss": 0.09913117438554764, "partitioner_loss": 0.03704650700092316, "running_macro_f1": 0.7118719317463018, "running_accuracy": 0.9487109375, "lr": 0.00014564448857435402, "codebook_loss": 0.041916124522686005, "codebook_perplexity": 172.5284881591797, "codebook_active": 332.0, "codebook_commit": 0.16766449809074402} | |
| {"step": 16000, "epoch": 43, "loss": 0.09126622974872589, "task_loss": 0.04656289890408516, "partitioner_loss": 0.03811631351709366, "running_macro_f1": 0.7400482318650028, "running_accuracy": 0.9434765625, "lr": 0.00014564448857435402, "codebook_loss": 0.026348063722252846, "codebook_perplexity": 228.3188934326172, "codebook_active": 364.0, "codebook_commit": 0.10539225488901138} | |
| {"step": 16050, "epoch": 43, "loss": 0.11018029600381851, "task_loss": 0.062067992985248566, "partitioner_loss": 0.038264200091362, "running_macro_f1": 0.7193834931778466, "running_accuracy": 0.9419921875, "lr": 0.00014564448857435402, "codebook_loss": 0.03939240425825119, "codebook_perplexity": 185.21258544921875, "codebook_active": 343.0, "codebook_commit": 0.15756961703300476} | |
| {"step": 16100, "epoch": 43, "loss": 0.17252378165721893, "task_loss": 0.12157146632671356, "partitioner_loss": 0.04138270020484924, "running_macro_f1": 0.7220890672359924, "running_accuracy": 0.9438615721891638, "lr": 0.00014564448857435402, "codebook_loss": 0.0382784865796566, "codebook_perplexity": 132.26766967773438, "codebook_active": 319.0, "codebook_commit": 0.1531139463186264} | |
| {"step": 16150, "epoch": 43, "loss": 0.10160203278064728, "task_loss": 0.05241847783327103, "partitioner_loss": 0.03741621598601341, "running_macro_f1": 0.7067332623113866, "running_accuracy": 0.930703125, "lr": 0.00014564448857435402, "codebook_loss": 0.04706937447190285, "codebook_perplexity": 181.44439697265625, "codebook_active": 338.0, "codebook_commit": 0.1882774978876114} | |
| {"step": 16200, "epoch": 43, "loss": 0.1897924840450287, "task_loss": 0.13719414174556732, "partitioner_loss": 0.044531963765621185, "running_macro_f1": 0.7086064311105834, "running_accuracy": 0.9391015625, "lr": 0.00014564448857435402, "codebook_loss": 0.032265521585941315, "codebook_perplexity": 96.81875610351562, "codebook_active": 308.0, "codebook_commit": 0.12906208634376526} | |
| {"step": 16250, "epoch": 43, "loss": 0.135585218667984, "task_loss": 0.0902782529592514, "partitioner_loss": 0.03677675127983093, "running_macro_f1": 0.7348793698087068, "running_accuracy": 0.9433984375, "lr": 0.00014564448857435402, "codebook_loss": 0.034120842814445496, "codebook_perplexity": 162.63623046875, "codebook_active": 362.0, "codebook_commit": 0.13648337125778198} | |
| {"epoch": 43, "split": "val", "val_macro_f1": 0.3735445502942657, "val_accuracy": 0.6606484177829548} | |
| {"step": 16300, "epoch": 44, "loss": 0.21041497588157654, "task_loss": 0.16105270385742188, "partitioner_loss": 0.03947458416223526, "running_macro_f1": 0.6890009340661196, "running_accuracy": 0.9269921875, "lr": 0.00014211227758358417, "codebook_loss": 0.03955080360174179, "codebook_perplexity": 135.371826171875, "codebook_active": 317.0, "codebook_commit": 0.15820321440696716} | |
| {"step": 16350, "epoch": 44, "loss": 0.23068773746490479, "task_loss": 0.17588995397090912, "partitioner_loss": 0.04330868273973465, "running_macro_f1": 0.7466920246383175, "running_accuracy": 0.9533984375, "lr": 0.00014211227758358417, "codebook_loss": 0.04595636948943138, "codebook_perplexity": 145.4564971923828, "codebook_active": 334.0, "codebook_commit": 0.18382547795772552} | |
| {"step": 16400, "epoch": 44, "loss": 0.15215156972408295, "task_loss": 0.1066107228398323, "partitioner_loss": 0.037052806466817856, "running_macro_f1": 0.7534521724043398, "running_accuracy": 0.9475390625, "lr": 0.00014211227758358417, "codebook_loss": 0.03395215421915054, "codebook_perplexity": 137.7335662841797, "codebook_active": 266.0, "codebook_commit": 0.13580861687660217} | |
| {"step": 16450, "epoch": 44, "loss": 0.15949948132038116, "task_loss": 0.11622737348079681, "partitioner_loss": 0.03321034088730812, "running_macro_f1": 0.7261293439993511, "running_accuracy": 0.939375, "lr": 0.00014211227758358417, "codebook_loss": 0.04024709388613701, "codebook_perplexity": 134.2923583984375, "codebook_active": 298.0, "codebook_commit": 0.16098837554454803} | |
| {"step": 16500, "epoch": 44, "loss": 0.14205174148082733, "task_loss": 0.09369362145662308, "partitioner_loss": 0.03980400413274765, "running_macro_f1": 0.7222063121450228, "running_accuracy": 0.945, "lr": 0.00014211227758358417, "codebook_loss": 0.034216463565826416, "codebook_perplexity": 157.39923095703125, "codebook_active": 345.0, "codebook_commit": 0.13686585426330566} | |
| {"step": 16550, "epoch": 44, "loss": 0.0882350355386734, "task_loss": 0.04175166040658951, "partitioner_loss": 0.03714539483189583, "running_macro_f1": 0.7305126466045444, "running_accuracy": 0.9325477607265894, "lr": 0.00014211227758358417, "codebook_loss": 0.03735189139842987, "codebook_perplexity": 175.37782287597656, "codebook_active": 333.0, "codebook_commit": 0.14940756559371948} | |
| {"step": 16600, "epoch": 44, "loss": 0.11969241499900818, "task_loss": 0.07012394070625305, "partitioner_loss": 0.04054819792509079, "running_macro_f1": 0.7186036308746804, "running_accuracy": 0.9471875, "lr": 0.00014211227758358417, "codebook_loss": 0.03608112037181854, "codebook_perplexity": 166.27572631835938, "codebook_active": 320.0, "codebook_commit": 0.14432448148727417} | |
| {"epoch": 44, "split": "val", "val_macro_f1": 0.3918586056581298, "val_accuracy": 0.6877305377596583} | |
| {"step": 16650, "epoch": 45, "loss": 0.31510770320892334, "task_loss": 0.261372834444046, "partitioner_loss": 0.04337412863969803, "running_macro_f1": 0.730783255962828, "running_accuracy": 0.9502734375, "lr": 0.00013855276682749694, "codebook_loss": 0.04144294559955597, "codebook_perplexity": 138.36227416992188, "codebook_active": 320.0, "codebook_commit": 0.16577178239822388} | |
| {"step": 16700, "epoch": 45, "loss": 0.12714579701423645, "task_loss": 0.07824630290269852, "partitioner_loss": 0.03956794738769531, "running_macro_f1": 0.7346258507148566, "running_accuracy": 0.9507124960851864, "lr": 0.00013855276682749694, "codebook_loss": 0.03732617571949959, "codebook_perplexity": 167.07432556152344, "codebook_active": 327.0, "codebook_commit": 0.14930470287799835} | |
| {"step": 16750, "epoch": 45, "loss": 0.10778853297233582, "task_loss": 0.05946960672736168, "partitioner_loss": 0.03838562220335007, "running_macro_f1": 0.7071224858729518, "running_accuracy": 0.9339453125, "lr": 0.00013855276682749694, "codebook_loss": 0.03973323106765747, "codebook_perplexity": 167.9474334716797, "codebook_active": 337.0, "codebook_commit": 0.15893292427062988} | |
| {"step": 16800, "epoch": 45, "loss": 0.14660590887069702, "task_loss": 0.10132669657468796, "partitioner_loss": 0.03703433275222778, "running_macro_f1": 0.7453384212195476, "running_accuracy": 0.9496875, "lr": 0.00013855276682749694, "codebook_loss": 0.032979514449834824, "codebook_perplexity": 190.7197265625, "codebook_active": 375.0, "codebook_commit": 0.1319180577993393} | |
| {"step": 16850, "epoch": 45, "loss": 0.1334516406059265, "task_loss": 0.08631525188684464, "partitioner_loss": 0.03645722568035126, "running_macro_f1": 0.7230752210079883, "running_accuracy": 0.9446484375, "lr": 0.00013855276682749694, "codebook_loss": 0.04271663725376129, "codebook_perplexity": 138.53656005859375, "codebook_active": 298.0, "codebook_commit": 0.17086654901504517} | |
| {"step": 16900, "epoch": 45, "loss": 0.18541783094406128, "task_loss": 0.1278076022863388, "partitioner_loss": 0.04659741371870041, "running_macro_f1": 0.7654785477677344, "running_accuracy": 0.945625, "lr": 0.00013855276682749694, "codebook_loss": 0.04405131936073303, "codebook_perplexity": 113.10173034667969, "codebook_active": 223.0, "codebook_commit": 0.17620527744293213} | |
| {"step": 16950, "epoch": 45, "loss": 0.09352406114339828, "task_loss": 0.04466034844517708, "partitioner_loss": 0.0419546477496624, "running_macro_f1": 0.7497776814205677, "running_accuracy": 0.9483984375, "lr": 0.00013855276682749694, "codebook_loss": 0.027636270970106125, "codebook_perplexity": 232.40701293945312, "codebook_active": 405.0, "codebook_commit": 0.1105450838804245} | |
| {"step": 17000, "epoch": 45, "loss": 0.38151121139526367, "task_loss": 0.323609322309494, "partitioner_loss": 0.044883713126182556, "running_macro_f1": 0.7340321102402039, "running_accuracy": 0.9518359375, "lr": 0.00013855276682749694, "codebook_loss": 0.05207281932234764, "codebook_perplexity": 128.7796630859375, "codebook_active": 256.0, "codebook_commit": 0.20829127728939056} | |
| {"epoch": 45, "split": "val", "val_macro_f1": 0.36937361246703976, "val_accuracy": 0.6589011842360707} | |
| {"step": 17050, "epoch": 46, "loss": 0.09666259586811066, "task_loss": 0.05498672276735306, "partitioner_loss": 0.03333240747451782, "running_macro_f1": 0.7228303493554177, "running_accuracy": 0.9451171875, "lr": 0.000134969540431697, "codebook_loss": 0.033373862504959106, "codebook_perplexity": 123.67292022705078, "codebook_active": 309.0, "codebook_commit": 0.13349545001983643} | |
| {"step": 17100, "epoch": 46, "loss": 0.17530304193496704, "task_loss": 0.12138044089078903, "partitioner_loss": 0.04383959621191025, "running_macro_f1": 0.776268509724122, "running_accuracy": 0.9519140625, "lr": 0.000134969540431697, "codebook_loss": 0.040332041680812836, "codebook_perplexity": 174.89437866210938, "codebook_active": 341.0, "codebook_commit": 0.16132816672325134} | |
| {"step": 17150, "epoch": 46, "loss": 0.1971057951450348, "task_loss": 0.14640255272388458, "partitioner_loss": 0.03917384147644043, "running_macro_f1": 0.7490788781869082, "running_accuracy": 0.9581640625, "lr": 0.000134969540431697, "codebook_loss": 0.046117592602968216, "codebook_perplexity": 176.00823974609375, "codebook_active": 359.0, "codebook_commit": 0.18447037041187286} | |
| {"step": 17200, "epoch": 46, "loss": 0.14130574464797974, "task_loss": 0.0958595797419548, "partitioner_loss": 0.03959306329488754, "running_macro_f1": 0.7395799735970134, "running_accuracy": 0.957265625, "lr": 0.000134969540431697, "codebook_loss": 0.023412378504872322, "codebook_perplexity": 201.56565856933594, "codebook_active": 342.0, "codebook_commit": 0.09364951401948929} | |
| {"step": 17250, "epoch": 46, "loss": 0.12340886145830154, "task_loss": 0.0813019797205925, "partitioner_loss": 0.03381120041012764, "running_macro_f1": 0.7234114475300167, "running_accuracy": 0.93546875, "lr": 0.000134969540431697, "codebook_loss": 0.033182717859745026, "codebook_perplexity": 158.63198852539062, "codebook_active": 314.0, "codebook_commit": 0.1327308714389801} | |
| {"step": 17300, "epoch": 46, "loss": 0.11295667290687561, "task_loss": 0.06397946178913116, "partitioner_loss": 0.040703848004341125, "running_macro_f1": 0.7295011186630549, "running_accuracy": 0.9446484375, "lr": 0.000134969540431697, "codebook_loss": 0.03309345245361328, "codebook_perplexity": 132.614501953125, "codebook_active": 318.0, "codebook_commit": 0.13237380981445312} | |
| {"step": 17350, "epoch": 46, "loss": 0.3052181005477905, "task_loss": 0.239396870136261, "partitioner_loss": 0.05430971458554268, "running_macro_f1": 0.6996255809479216, "running_accuracy": 0.9307421875, "lr": 0.000134969540431697, "codebook_loss": 0.04604598134756088, "codebook_perplexity": 39.02602005004883, "codebook_active": 136.0, "codebook_commit": 0.18418392539024353} | |
| {"epoch": 46, "split": "val", "val_macro_f1": 0.35820539885643066, "val_accuracy": 0.6407493690545525} | |
| {"step": 17400, "epoch": 47, "loss": 0.2872787415981293, "task_loss": 0.23712530732154846, "partitioner_loss": 0.03822316601872444, "running_macro_f1": 0.7399170148489725, "running_accuracy": 0.9321954274976512, "lr": 0.0001313662064014278, "codebook_loss": 0.047720976173877716, "codebook_perplexity": 96.4286880493164, "codebook_active": 271.0, "codebook_commit": 0.19088390469551086} | |
| {"step": 17450, "epoch": 47, "loss": 0.31464746594429016, "task_loss": 0.2667636573314667, "partitioner_loss": 0.039366766810417175, "running_macro_f1": 0.7358547725520987, "running_accuracy": 0.9445703125, "lr": 0.0001313662064014278, "codebook_loss": 0.034068260341882706, "codebook_perplexity": 158.90438842773438, "codebook_active": 334.0, "codebook_commit": 0.13627304136753082} | |
| {"step": 17500, "epoch": 47, "loss": 0.1393263339996338, "task_loss": 0.08869235217571259, "partitioner_loss": 0.040746260434389114, "running_macro_f1": 0.7216238015268804, "running_accuracy": 0.944765625, "lr": 0.0001313662064014278, "codebook_loss": 0.03955090045928955, "codebook_perplexity": 170.30084228515625, "codebook_active": 332.0, "codebook_commit": 0.1582036018371582} | |
| {"step": 17550, "epoch": 47, "loss": 0.132364884018898, "task_loss": 0.08607472479343414, "partitioner_loss": 0.0382666140794754, "running_macro_f1": 0.7163134431191331, "running_accuracy": 0.936328125, "lr": 0.0001313662064014278, "codebook_loss": 0.03209419548511505, "codebook_perplexity": 127.46432495117188, "codebook_active": 335.0, "codebook_commit": 0.1283767819404602} | |
| {"step": 17600, "epoch": 47, "loss": 0.1788744032382965, "task_loss": 0.13236546516418457, "partitioner_loss": 0.03715876117348671, "running_macro_f1": 0.7247579355402218, "running_accuracy": 0.9453492013780144, "lr": 0.0001313662064014278, "codebook_loss": 0.03740072250366211, "codebook_perplexity": 174.686767578125, "codebook_active": 344.0, "codebook_commit": 0.14960289001464844} | |
| {"step": 17650, "epoch": 47, "loss": 0.12714898586273193, "task_loss": 0.07843072712421417, "partitioner_loss": 0.03981509804725647, "running_macro_f1": 0.7536043149408332, "running_accuracy": 0.9479296875, "lr": 0.0001313662064014278, "codebook_loss": 0.03561263531446457, "codebook_perplexity": 174.43421936035156, "codebook_active": 363.0, "codebook_commit": 0.14245054125785828} | |
| {"step": 17700, "epoch": 47, "loss": 0.11796201765537262, "task_loss": 0.06608104705810547, "partitioner_loss": 0.04485698044300079, "running_macro_f1": 0.6877631592205423, "running_accuracy": 0.928828125, "lr": 0.0001313662064014278, "codebook_loss": 0.028095975518226624, "codebook_perplexity": 201.83245849609375, "codebook_active": 407.0, "codebook_commit": 0.1123839020729065} | |
| {"step": 17750, "epoch": 47, "loss": 0.2399396449327469, "task_loss": 0.179220050573349, "partitioner_loss": 0.05042829364538193, "running_macro_f1": 0.7426856230990405, "running_accuracy": 0.9491796875, "lr": 0.0001313662064014278, "codebook_loss": 0.04116516560316086, "codebook_perplexity": 80.9051284790039, "codebook_active": 202.0, "codebook_commit": 0.16466066241264343} | |
| {"epoch": 47, "split": "val", "val_macro_f1": 0.350985630247232, "val_accuracy": 0.6598718695398952} | |
| {"step": 17800, "epoch": 48, "loss": 0.14382827281951904, "task_loss": 0.09035272896289825, "partitioner_loss": 0.042389266192913055, "running_macro_f1": 0.712931358431319, "running_accuracy": 0.941953125, "lr": 0.00012774639298861626, "codebook_loss": 0.04434513673186302, "codebook_perplexity": 140.4407958984375, "codebook_active": 342.0, "codebook_commit": 0.1773805469274521} | |
| {"step": 17850, "epoch": 48, "loss": 0.09369350224733353, "task_loss": 0.04320292919874191, "partitioner_loss": 0.040332477539777756, "running_macro_f1": 0.7571127236395537, "running_accuracy": 0.9553515625, "lr": 0.00012774639298861626, "codebook_loss": 0.040632396936416626, "codebook_perplexity": 132.18972778320312, "codebook_active": 287.0, "codebook_commit": 0.1625295877456665} | |
| {"step": 17900, "epoch": 48, "loss": 0.13552790880203247, "task_loss": 0.09103899449110031, "partitioner_loss": 0.03557450324296951, "running_macro_f1": 0.7292262865827932, "running_accuracy": 0.9533984375, "lr": 0.00012774639298861626, "codebook_loss": 0.03565766662359238, "codebook_perplexity": 143.6328582763672, "codebook_active": 292.0, "codebook_commit": 0.1426306664943695} | |
| {"step": 17950, "epoch": 48, "loss": 0.10973664373159409, "task_loss": 0.0609198622405529, "partitioner_loss": 0.03981993719935417, "running_macro_f1": 0.7304519980431372, "running_accuracy": 0.9519921875, "lr": 0.00012774639298861626, "codebook_loss": 0.035987384617328644, "codebook_perplexity": 200.82559204101562, "codebook_active": 358.0, "codebook_commit": 0.14394953846931458} | |
| {"step": 18000, "epoch": 48, "loss": 0.1244315505027771, "task_loss": 0.07800032943487167, "partitioner_loss": 0.03624217212200165, "running_macro_f1": 0.7374543817809305, "running_accuracy": 0.9436328125, "lr": 0.00012774639298861626, "codebook_loss": 0.04075618088245392, "codebook_perplexity": 191.9354705810547, "codebook_active": 374.0, "codebook_commit": 0.16302472352981567} | |
| {"step": 18050, "epoch": 48, "loss": 0.10145249962806702, "task_loss": 0.0481589175760746, "partitioner_loss": 0.044413670897483826, "running_macro_f1": 0.7091324774004584, "running_accuracy": 0.93421875, "lr": 0.00012774639298861626, "codebook_loss": 0.03551965206861496, "codebook_perplexity": 181.74322509765625, "codebook_active": 355.0, "codebook_commit": 0.14207860827445984} | |
| {"step": 18100, "epoch": 48, "loss": 0.16177858412265778, "task_loss": 0.11346679925918579, "partitioner_loss": 0.039298150688409805, "running_macro_f1": 0.7202707431719343, "running_accuracy": 0.9446875, "lr": 0.00012774639298861626, "codebook_loss": 0.03605454042553902, "codebook_perplexity": 181.15028381347656, "codebook_active": 339.0, "codebook_commit": 0.14421816170215607} | |
| {"epoch": 48, "split": "val", "val_macro_f1": 0.35604497684080183, "val_accuracy": 0.6697728596389051} | |
| {"step": 18150, "epoch": 49, "loss": 0.1100500151515007, "task_loss": 0.06548579037189484, "partitioner_loss": 0.035538122057914734, "running_macro_f1": 0.7109064621412766, "running_accuracy": 0.9325869088631381, "lr": 0.00012411374503853068, "codebook_loss": 0.03610439971089363, "codebook_perplexity": 207.71737670898438, "codebook_active": 357.0, "codebook_commit": 0.14441759884357452} | |
| {"step": 18200, "epoch": 49, "loss": 0.10536691546440125, "task_loss": 0.045330725610256195, "partitioner_loss": 0.052581481635570526, "running_macro_f1": 0.7185431096691388, "running_accuracy": 0.9519140625, "lr": 0.00012411374503853068, "codebook_loss": 0.02981881983578205, "codebook_perplexity": 147.08387756347656, "codebook_active": 340.0, "codebook_commit": 0.1192752793431282} | |
| {"step": 18250, "epoch": 49, "loss": 0.11649996042251587, "task_loss": 0.0701451376080513, "partitioner_loss": 0.03776346519589424, "running_macro_f1": 0.7366435767833354, "running_accuracy": 0.9578515625, "lr": 0.00012411374503853068, "codebook_loss": 0.03436543047428131, "codebook_perplexity": 123.98101806640625, "codebook_active": 274.0, "codebook_commit": 0.13746172189712524} | |
| {"step": 18300, "epoch": 49, "loss": 0.22365714609622955, "task_loss": 0.17532803118228912, "partitioner_loss": 0.036584679037332535, "running_macro_f1": 0.7418412890577899, "running_accuracy": 0.9449609375, "lr": 0.00012411374503853068, "codebook_loss": 0.046977780759334564, "codebook_perplexity": 123.8685073852539, "codebook_active": 255.0, "codebook_commit": 0.18791112303733826} | |
| {"step": 18350, "epoch": 49, "loss": 0.18318630754947662, "task_loss": 0.13726641237735748, "partitioner_loss": 0.03731001541018486, "running_macro_f1": 0.735366942624641, "running_accuracy": 0.9459375, "lr": 0.00012411374503853068, "codebook_loss": 0.03443949669599533, "codebook_perplexity": 172.20201110839844, "codebook_active": 307.0, "codebook_commit": 0.13775798678398132} | |
| {"step": 18400, "epoch": 49, "loss": 0.0919194370508194, "task_loss": 0.048396799713373184, "partitioner_loss": 0.0351458303630352, "running_macro_f1": 0.740320460346015, "running_accuracy": 0.94375, "lr": 0.00012411374503853068, "codebook_loss": 0.03350722789764404, "codebook_perplexity": 129.468505859375, "codebook_active": 311.0, "codebook_commit": 0.13402891159057617} | |
| {"step": 18450, "epoch": 49, "loss": 0.15361112356185913, "task_loss": 0.1023641899228096, "partitioner_loss": 0.041365452110767365, "running_macro_f1": 0.7056146918894773, "running_accuracy": 0.922890625, "lr": 0.00012411374503853068, "codebook_loss": 0.03952590748667717, "codebook_perplexity": 154.65890502929688, "codebook_active": 321.0, "codebook_commit": 0.15810362994670868} | |
| {"step": 18500, "epoch": 49, "loss": 0.18025070428848267, "task_loss": 0.1232077032327652, "partitioner_loss": 0.044632233679294586, "running_macro_f1": 0.7381967587994586, "running_accuracy": 0.9473849044785468, "lr": 0.00012411374503853068, "codebook_loss": 0.04964301362633705, "codebook_perplexity": 111.06148529052734, "codebook_active": 247.0, "codebook_commit": 0.1985720545053482} | |
| {"epoch": 49, "split": "val", "val_macro_f1": 0.3644654182453258, "val_accuracy": 0.6631721995728984} | |
| {"step": 18550, "epoch": 50, "loss": 0.14424997568130493, "task_loss": 0.08103663474321365, "partitioner_loss": 0.0535120815038681, "running_macro_f1": 0.7046957160040317, "running_accuracy": 0.953125, "lr": 0.0001204719203197304, "codebook_loss": 0.038805022835731506, "codebook_perplexity": 84.66466522216797, "codebook_active": 192.0, "codebook_commit": 0.15522009134292603} | |
| {"step": 18600, "epoch": 50, "loss": 0.23132571578025818, "task_loss": 0.18469485640525818, "partitioner_loss": 0.036895230412483215, "running_macro_f1": 0.7583874083050257, "running_accuracy": 0.9596875, "lr": 0.0001204719203197304, "codebook_loss": 0.038942500948905945, "codebook_perplexity": 142.93997192382812, "codebook_active": 310.0, "codebook_commit": 0.15577000379562378} | |
| {"step": 18650, "epoch": 50, "loss": 0.16891855001449585, "task_loss": 0.11626125872135162, "partitioner_loss": 0.039070505648851395, "running_macro_f1": 0.7264741215847146, "running_accuracy": 0.9292593172564986, "lr": 0.0001204719203197304, "codebook_loss": 0.054347164928913116, "codebook_perplexity": 103.32154846191406, "codebook_active": 225.0, "codebook_commit": 0.21738865971565247} | |
| {"step": 18700, "epoch": 50, "loss": 0.0755847692489624, "task_loss": 0.027910316362977028, "partitioner_loss": 0.037785157561302185, "running_macro_f1": 0.738422509195977, "running_accuracy": 0.951015625, "lr": 0.0001204719203197304, "codebook_loss": 0.039557185024023056, "codebook_perplexity": 197.3379669189453, "codebook_active": 321.0, "codebook_commit": 0.15822874009609222} | |
| {"step": 18750, "epoch": 50, "loss": 0.1285550743341446, "task_loss": 0.07302260398864746, "partitioner_loss": 0.04229826480150223, "running_macro_f1": 0.7794277212806484, "running_accuracy": 0.958671875, "lr": 0.0001204719203197304, "codebook_loss": 0.052936844527721405, "codebook_perplexity": 63.01272964477539, "codebook_active": 209.0, "codebook_commit": 0.21174737811088562} | |
| {"step": 18800, "epoch": 50, "loss": 0.24420824646949768, "task_loss": 0.1977752149105072, "partitioner_loss": 0.03536960482597351, "running_macro_f1": 0.737379436180209, "running_accuracy": 0.9472265625, "lr": 0.0001204719203197304, "codebook_loss": 0.04425367712974548, "codebook_perplexity": 101.90719604492188, "codebook_active": 276.0, "codebook_commit": 0.17701470851898193} | |
| {"step": 18850, "epoch": 50, "loss": 0.13477855920791626, "task_loss": 0.07935486733913422, "partitioner_loss": 0.046158596873283386, "running_macro_f1": 0.7279905026956821, "running_accuracy": 0.9477734375, "lr": 0.0001204719203197304, "codebook_loss": 0.03706035390496254, "codebook_perplexity": 142.0189208984375, "codebook_active": 281.0, "codebook_commit": 0.14824141561985016} | |
| {"step": 18900, "epoch": 50, "loss": 0.1899479776620865, "task_loss": 0.12743909657001495, "partitioner_loss": 0.05223555117845535, "running_macro_f1": 0.7373342417896959, "running_accuracy": 0.9461328125, "lr": 0.0001204719203197304, "codebook_loss": 0.041093289852142334, "codebook_perplexity": 100.17362976074219, "codebook_active": 206.0, "codebook_commit": 0.16437315940856934} | |
| {"epoch": 50, "split": "val", "val_macro_f1": 0.36676529361621396, "val_accuracy": 0.6696757911085226} | |
| {"step": 18950, "epoch": 51, "loss": 0.16109558939933777, "task_loss": 0.1065756231546402, "partitioner_loss": 0.04561908543109894, "running_macro_f1": 0.7151949222408099, "running_accuracy": 0.9362890625, "lr": 0.00011682458584100292, "codebook_loss": 0.03560349717736244, "codebook_perplexity": 111.10089111328125, "codebook_active": 265.0, "codebook_commit": 0.14241398870944977} | |
| {"step": 19000, "epoch": 51, "loss": 0.19111011922359467, "task_loss": 0.1408814787864685, "partitioner_loss": 0.038624171167612076, "running_macro_f1": 0.7014236933964029, "running_accuracy": 0.94421875, "lr": 0.00011682458584100292, "codebook_loss": 0.04641791433095932, "codebook_perplexity": 113.34127807617188, "codebook_active": 263.0, "codebook_commit": 0.18567165732383728} | |
| {"step": 19050, "epoch": 51, "loss": 0.07682257890701294, "task_loss": 0.029151324182748795, "partitioner_loss": 0.03810008987784386, "running_macro_f1": 0.7390425144363537, "running_accuracy": 0.9562109375, "lr": 0.00011682458584100292, "codebook_loss": 0.03828466683626175, "codebook_perplexity": 181.13534545898438, "codebook_active": 330.0, "codebook_commit": 0.153138667345047} | |
| {"step": 19100, "epoch": 51, "loss": 0.2823629677295685, "task_loss": 0.23172323405742645, "partitioner_loss": 0.04027664288878441, "running_macro_f1": 0.7249473199547601, "running_accuracy": 0.9437890625, "lr": 0.00011682458584100292, "codebook_loss": 0.04145244508981705, "codebook_perplexity": 125.7380599975586, "codebook_active": 321.0, "codebook_commit": 0.1658097803592682} | |
| {"step": 19150, "epoch": 51, "loss": 0.1728896200656891, "task_loss": 0.1273229718208313, "partitioner_loss": 0.035364046692848206, "running_macro_f1": 0.7599977089702894, "running_accuracy": 0.9534765625, "lr": 0.00011682458584100292, "codebook_loss": 0.04081038013100624, "codebook_perplexity": 133.74143981933594, "codebook_active": 311.0, "codebook_commit": 0.16324152052402496} | |
| {"step": 19200, "epoch": 51, "loss": 0.11436154693365097, "task_loss": 0.0629560723900795, "partitioner_loss": 0.04313000664114952, "running_macro_f1": 0.7440238043572318, "running_accuracy": 0.94640625, "lr": 0.00011682458584100292, "codebook_loss": 0.033101886510849, "codebook_perplexity": 147.48898315429688, "codebook_active": 312.0, "codebook_commit": 0.132407546043396} | |
| {"step": 19250, "epoch": 51, "loss": 0.15645910799503326, "task_loss": 0.11004053056240082, "partitioner_loss": 0.036853112280368805, "running_macro_f1": 0.7142568993516374, "running_accuracy": 0.932860945818979, "lr": 0.00011682458584100292, "codebook_loss": 0.03826180472970009, "codebook_perplexity": 115.20230865478516, "codebook_active": 234.0, "codebook_commit": 0.15304721891880035} | |
| {"epoch": 51, "split": "val", "val_macro_f1": 0.35583847047543693, "val_accuracy": 0.6582217045233936} | |
| {"step": 19300, "epoch": 52, "loss": 0.20856383442878723, "task_loss": 0.15471938252449036, "partitioner_loss": 0.04330753535032272, "running_macro_f1": 0.7267830801288074, "running_accuracy": 0.9490234375, "lr": 0.00011317541415899708, "codebook_loss": 0.04214763641357422, "codebook_perplexity": 168.8962860107422, "codebook_active": 314.0, "codebook_commit": 0.16859054565429688} | |
| {"step": 19350, "epoch": 52, "loss": 0.1557018756866455, "task_loss": 0.10250300168991089, "partitioner_loss": 0.043520987033843994, "running_macro_f1": 0.7255892797532442, "running_accuracy": 0.9441796875, "lr": 0.00011317541415899708, "codebook_loss": 0.03871152549982071, "codebook_perplexity": 179.96568298339844, "codebook_active": 362.0, "codebook_commit": 0.15484610199928284} | |
| {"step": 19400, "epoch": 52, "loss": 0.22633227705955505, "task_loss": 0.1761096566915512, "partitioner_loss": 0.04065399244427681, "running_macro_f1": 0.7342296958355266, "running_accuracy": 0.9584375, "lr": 0.00011317541415899708, "codebook_loss": 0.038274526596069336, "codebook_perplexity": 126.93675994873047, "codebook_active": 318.0, "codebook_commit": 0.15309810638427734} | |
| {"step": 19450, "epoch": 52, "loss": 0.20705939829349518, "task_loss": 0.14114725589752197, "partitioner_loss": 0.05696175992488861, "running_macro_f1": 0.7565874921463245, "running_accuracy": 0.94234375, "lr": 0.00011317541415899708, "codebook_loss": 0.035801537334918976, "codebook_perplexity": 114.92523956298828, "codebook_active": 298.0, "codebook_commit": 0.1432061493396759} | |
| {"step": 19500, "epoch": 52, "loss": 0.14424854516983032, "task_loss": 0.09510163217782974, "partitioner_loss": 0.03944556042551994, "running_macro_f1": 0.7228249362354315, "running_accuracy": 0.9283197619793297, "lr": 0.00011317541415899708, "codebook_loss": 0.03880542516708374, "codebook_perplexity": 178.13536071777344, "codebook_active": 349.0, "codebook_commit": 0.15522170066833496} | |
| {"step": 19550, "epoch": 52, "loss": 0.11481156200170517, "task_loss": 0.06894703209400177, "partitioner_loss": 0.03622140735387802, "running_macro_f1": 0.710602101975042, "running_accuracy": 0.9380078125, "lr": 0.00011317541415899708, "codebook_loss": 0.03857247903943062, "codebook_perplexity": 181.97544860839844, "codebook_active": 347.0, "codebook_commit": 0.15428991615772247} | |
| {"step": 19600, "epoch": 52, "loss": 0.11579262465238571, "task_loss": 0.07114671170711517, "partitioner_loss": 0.03445944935083389, "running_macro_f1": 0.731488608411355, "running_accuracy": 0.9510546875, "lr": 0.00011317541415899708, "codebook_loss": 0.04074586555361748, "codebook_perplexity": 169.32408142089844, "codebook_active": 334.0, "codebook_commit": 0.1629834622144699} | |
| {"step": 19650, "epoch": 52, "loss": 0.15495352447032928, "task_loss": 0.10431241244077682, "partitioner_loss": 0.03754109889268875, "running_macro_f1": 0.7439621257271403, "running_accuracy": 0.9462109375, "lr": 0.00011317541415899708, "codebook_loss": 0.05240005627274513, "codebook_perplexity": 110.11672973632812, "codebook_active": 242.0, "codebook_commit": 0.20960022509098053} | |
| {"epoch": 52, "split": "val", "val_macro_f1": 0.37338355758809155, "val_accuracy": 0.6778295476606484} | |
| {"step": 19700, "epoch": 53, "loss": 0.15772786736488342, "task_loss": 0.11014118790626526, "partitioner_loss": 0.03749418631196022, "running_macro_f1": 0.7528142675043842, "running_accuracy": 0.94984375, "lr": 0.00010952807968026964, "codebook_loss": 0.04036998376250267, "codebook_perplexity": 167.02223205566406, "codebook_active": 311.0, "codebook_commit": 0.16147993505001068} | |
| {"step": 19750, "epoch": 53, "loss": 0.13574755191802979, "task_loss": 0.08628953248262405, "partitioner_loss": 0.03970085829496384, "running_macro_f1": 0.7499592037523992, "running_accuracy": 0.9580078125, "lr": 0.00010952807968026964, "codebook_loss": 0.03902862221002579, "codebook_perplexity": 198.07850646972656, "codebook_active": 382.0, "codebook_commit": 0.15611448884010315} | |
| {"step": 19800, "epoch": 53, "loss": 0.15147265791893005, "task_loss": 0.10469093918800354, "partitioner_loss": 0.037667687982320786, "running_macro_f1": 0.7621450542319603, "running_accuracy": 0.9616348261822737, "lr": 0.00010952807968026964, "codebook_loss": 0.03645610809326172, "codebook_perplexity": 175.45953369140625, "codebook_active": 314.0, "codebook_commit": 0.14582443237304688} | |
| {"step": 19850, "epoch": 53, "loss": 0.09239858388900757, "task_loss": 0.04955177754163742, "partitioner_loss": 0.033862970769405365, "running_macro_f1": 0.7716187819121717, "running_accuracy": 0.95828125, "lr": 0.00010952807968026964, "codebook_loss": 0.03593534231185913, "codebook_perplexity": 179.76687622070312, "codebook_active": 337.0, "codebook_commit": 0.14374136924743652} | |
| {"step": 19900, "epoch": 53, "loss": 0.1679048240184784, "task_loss": 0.11700446903705597, "partitioner_loss": 0.04082983732223511, "running_macro_f1": 0.7621017047280393, "running_accuracy": 0.950078125, "lr": 0.00010952807968026964, "codebook_loss": 0.04028207063674927, "codebook_perplexity": 126.80390167236328, "codebook_active": 253.0, "codebook_commit": 0.16112828254699707} | |
| {"step": 19950, "epoch": 53, "loss": 0.27882274985313416, "task_loss": 0.22788693010807037, "partitioner_loss": 0.04062110185623169, "running_macro_f1": 0.7738047799950883, "running_accuracy": 0.9590625, "lr": 0.00010952807968026964, "codebook_loss": 0.041258953511714935, "codebook_perplexity": 183.4081268310547, "codebook_active": 326.0, "codebook_commit": 0.16503581404685974} | |
| {"step": 20000, "epoch": 53, "loss": 0.2839062809944153, "task_loss": 0.2306365966796875, "partitioner_loss": 0.04282056540250778, "running_macro_f1": 0.708158805538232, "running_accuracy": 0.94109375, "lr": 0.00010952807968026964, "codebook_loss": 0.04179646074771881, "codebook_perplexity": 183.50933837890625, "codebook_active": 373.0, "codebook_commit": 0.16718584299087524} | |
| {"epoch": 53, "split": "val", "val_macro_f1": 0.36045404914041346, "val_accuracy": 0.706658901184236} | |
| {"step": 20050, "epoch": 54, "loss": 0.12697847187519073, "task_loss": 0.08302073925733566, "partitioner_loss": 0.0355108268558979, "running_macro_f1": 0.7022892243583463, "running_accuracy": 0.91578125, "lr": 0.00010588625496146932, "codebook_loss": 0.03378758952021599, "codebook_perplexity": 143.23341369628906, "codebook_active": 359.0, "codebook_commit": 0.13515035808086395} | |
| {"step": 20100, "epoch": 54, "loss": 0.1486842781305313, "task_loss": 0.10034401714801788, "partitioner_loss": 0.038108982145786285, "running_macro_f1": 0.7186042617980128, "running_accuracy": 0.9490234375, "lr": 0.00010588625496146932, "codebook_loss": 0.04092505946755409, "codebook_perplexity": 177.94654846191406, "codebook_active": 367.0, "codebook_commit": 0.16370023787021637} | |
| {"step": 20150, "epoch": 54, "loss": 0.07288215309381485, "task_loss": 0.028930598869919777, "partitioner_loss": 0.035013891756534576, "running_macro_f1": 0.770988117063895, "running_accuracy": 0.950078125, "lr": 0.00010588625496146932, "codebook_loss": 0.03575066849589348, "codebook_perplexity": 170.502197265625, "codebook_active": 336.0, "codebook_commit": 0.1430026739835739} | |
| {"step": 20200, "epoch": 54, "loss": 0.16073358058929443, "task_loss": 0.11332175880670547, "partitioner_loss": 0.037102509289979935, "running_macro_f1": 0.7302671409024234, "running_accuracy": 0.955625, "lr": 0.00010588625496146932, "codebook_loss": 0.04123720899224281, "codebook_perplexity": 123.16315460205078, "codebook_active": 294.0, "codebook_commit": 0.16494883596897125} | |
| {"step": 20250, "epoch": 54, "loss": 0.10873287916183472, "task_loss": 0.06185780093073845, "partitioner_loss": 0.037628743797540665, "running_macro_f1": 0.7180608275781428, "running_accuracy": 0.94796875, "lr": 0.00010588625496146932, "codebook_loss": 0.03698534518480301, "codebook_perplexity": 179.46351623535156, "codebook_active": 360.0, "codebook_commit": 0.14794138073921204} | |
| {"step": 20300, "epoch": 54, "loss": 0.1018250361084938, "task_loss": 0.05658061057329178, "partitioner_loss": 0.03588064759969711, "running_macro_f1": 0.7521441799418636, "running_accuracy": 0.9519140625, "lr": 0.00010588625496146932, "codebook_loss": 0.03745511174201965, "codebook_perplexity": 156.08506774902344, "codebook_active": 344.0, "codebook_commit": 0.1498204469680786} | |
| {"step": 20350, "epoch": 54, "loss": 0.3528226613998413, "task_loss": 0.3070242404937744, "partitioner_loss": 0.03689572215080261, "running_macro_f1": 0.7469940189998452, "running_accuracy": 0.9502818665831506, "lr": 0.00010588625496146932, "codebook_loss": 0.035610854625701904, "codebook_perplexity": 172.171630859375, "codebook_active": 314.0, "codebook_commit": 0.14244341850280762} | |
| {"step": 20400, "epoch": 54, "loss": 0.4325760304927826, "task_loss": 0.38487789034843445, "partitioner_loss": 0.03730902820825577, "running_macro_f1": 0.7550831533663616, "running_accuracy": 0.951640625, "lr": 0.00010588625496146932, "codebook_loss": 0.0415564700961113, "codebook_perplexity": 164.63441467285156, "codebook_active": 298.0, "codebook_commit": 0.1662258803844452} | |
| {"epoch": 54, "split": "val", "val_macro_f1": 0.36010336499741064, "val_accuracy": 0.6716171617161716} | |
| {"step": 20450, "epoch": 55, "loss": 0.18503233790397644, "task_loss": 0.13514280319213867, "partitioner_loss": 0.0395011343061924, "running_macro_f1": 0.7248572436385482, "running_accuracy": 0.946328125, "lr": 0.00010225360701138374, "codebook_loss": 0.04155363887548447, "codebook_perplexity": 78.34380340576172, "codebook_active": 211.0, "codebook_commit": 0.16621455550193787} | |
| {"step": 20500, "epoch": 55, "loss": 0.15450751781463623, "task_loss": 0.10797388851642609, "partitioner_loss": 0.036609672009944916, "running_macro_f1": 0.7678701671336903, "running_accuracy": 0.95515625, "lr": 0.00010225360701138374, "codebook_loss": 0.0396958664059639, "codebook_perplexity": 126.34195709228516, "codebook_active": 306.0, "codebook_commit": 0.1587834656238556} | |
| {"step": 20550, "epoch": 55, "loss": 0.10000622272491455, "task_loss": 0.057626280933618546, "partitioner_loss": 0.03363469988107681, "running_macro_f1": 0.7706753549504778, "running_accuracy": 0.9528515625, "lr": 0.00010225360701138374, "codebook_loss": 0.03498093783855438, "codebook_perplexity": 140.79119873046875, "codebook_active": 331.0, "codebook_commit": 0.13992375135421753} | |
| {"step": 20600, "epoch": 55, "loss": 0.16520388424396515, "task_loss": 0.11630383878946304, "partitioner_loss": 0.038624465465545654, "running_macro_f1": 0.7505627901808413, "running_accuracy": 0.950390625, "lr": 0.00010225360701138374, "codebook_loss": 0.041102342307567596, "codebook_perplexity": 72.43136596679688, "codebook_active": 161.0, "codebook_commit": 0.16440936923027039} | |
| {"step": 20650, "epoch": 55, "loss": 0.16799792647361755, "task_loss": 0.11414836347103119, "partitioner_loss": 0.041409220546483994, "running_macro_f1": 0.7346829357803882, "running_accuracy": 0.9469140625, "lr": 0.00010225360701138374, "codebook_loss": 0.04976136237382889, "codebook_perplexity": 145.90614318847656, "codebook_active": 313.0, "codebook_commit": 0.19904544949531555} | |
| {"step": 20700, "epoch": 55, "loss": 0.1653803586959839, "task_loss": 0.11559803783893585, "partitioner_loss": 0.039017658680677414, "running_macro_f1": 0.7270147200124429, "running_accuracy": 0.9606952709051049, "lr": 0.00010225360701138374, "codebook_loss": 0.04305863380432129, "codebook_perplexity": 169.79010009765625, "codebook_active": 301.0, "codebook_commit": 0.17223453521728516} | |
| {"step": 20750, "epoch": 55, "loss": 0.11330126225948334, "task_loss": 0.06681865453720093, "partitioner_loss": 0.037397630512714386, "running_macro_f1": 0.7594465919077383, "running_accuracy": 0.9578515625, "lr": 0.00010225360701138374, "codebook_loss": 0.036339908838272095, "codebook_perplexity": 156.92739868164062, "codebook_active": 335.0, "codebook_commit": 0.14535963535308838} | |
| {"epoch": 55, "split": "val", "val_macro_f1": 0.38517734604097525, "val_accuracy": 0.7039409823335274} | |
| {"step": 20800, "epoch": 56, "loss": 0.10301034897565842, "task_loss": 0.055486489087343216, "partitioner_loss": 0.03727719187736511, "running_macro_f1": 0.7059703716928551, "running_accuracy": 0.9371875, "lr": 9.863379359857222e-05, "codebook_loss": 0.04098667949438095, "codebook_perplexity": 175.38943481445312, "codebook_active": 335.0, "codebook_commit": 0.1639467179775238} | |
| {"step": 20850, "epoch": 56, "loss": 0.06539800018072128, "task_loss": 0.02202063426375389, "partitioner_loss": 0.034604378044605255, "running_macro_f1": 0.7700242301992295, "running_accuracy": 0.961484375, "lr": 9.863379359857222e-05, "codebook_loss": 0.03509194031357765, "codebook_perplexity": 190.3159942626953, "codebook_active": 368.0, "codebook_commit": 0.1403677612543106} | |
| {"step": 20900, "epoch": 56, "loss": 0.14143887162208557, "task_loss": 0.09655477851629257, "partitioner_loss": 0.03443502262234688, "running_macro_f1": 0.7411898510315935, "running_accuracy": 0.935859375, "lr": 9.863379359857222e-05, "codebook_loss": 0.04179628565907478, "codebook_perplexity": 152.15475463867188, "codebook_active": 310.0, "codebook_commit": 0.16718514263629913} | |
| {"step": 20950, "epoch": 56, "loss": 0.1162368655204773, "task_loss": 0.07080923765897751, "partitioner_loss": 0.03574443235993385, "running_macro_f1": 0.7527650894453849, "running_accuracy": 0.9610546875, "lr": 9.863379359857222e-05, "codebook_loss": 0.03873276337981224, "codebook_perplexity": 165.8618927001953, "codebook_active": 310.0, "codebook_commit": 0.15493105351924896} | |
| {"step": 21000, "epoch": 56, "loss": 0.37294161319732666, "task_loss": 0.3153858780860901, "partitioner_loss": 0.05030263215303421, "running_macro_f1": 0.7516170232024214, "running_accuracy": 0.9526171875, "lr": 9.863379359857222e-05, "codebook_loss": 0.029012475162744522, "codebook_perplexity": 87.86323547363281, "codebook_active": 203.0, "codebook_commit": 0.11604990065097809} | |
| {"step": 21050, "epoch": 56, "loss": 0.11031041294336319, "task_loss": 0.061843037605285645, "partitioner_loss": 0.03957674279808998, "running_macro_f1": 0.7672664843786339, "running_accuracy": 0.9599906044472283, "lr": 9.863379359857222e-05, "codebook_loss": 0.03556254506111145, "codebook_perplexity": 158.63304138183594, "codebook_active": 359.0, "codebook_commit": 0.1422501802444458} | |
| {"step": 21100, "epoch": 56, "loss": 0.12317319959402084, "task_loss": 0.07494337111711502, "partitioner_loss": 0.03620399534702301, "running_macro_f1": 0.7659762838295986, "running_accuracy": 0.950703125, "lr": 9.863379359857222e-05, "codebook_loss": 0.04810333624482155, "codebook_perplexity": 172.62147521972656, "codebook_active": 323.0, "codebook_commit": 0.1924133449792862} | |
| {"step": 21150, "epoch": 56, "loss": 0.1216539517045021, "task_loss": 0.07480020821094513, "partitioner_loss": 0.03530197590589523, "running_macro_f1": 0.7585469260733412, "running_accuracy": 0.961796875, "lr": 9.863379359857222e-05, "codebook_loss": 0.04620707035064697, "codebook_perplexity": 171.58580017089844, "codebook_active": 369.0, "codebook_commit": 0.1848282814025879} | |
| {"epoch": 56, "split": "val", "val_macro_f1": 0.36226185378608544, "val_accuracy": 0.6826829741797709} | |
| {"step": 21200, "epoch": 57, "loss": 0.07275177538394928, "task_loss": 0.02787606418132782, "partitioner_loss": 0.03530653566122055, "running_macro_f1": 0.7702785006691232, "running_accuracy": 0.96625, "lr": 9.503045956830301e-05, "codebook_loss": 0.038276709616184235, "codebook_perplexity": 194.94203186035156, "codebook_active": 340.0, "codebook_commit": 0.15310683846473694} | |
| {"step": 21250, "epoch": 57, "loss": 0.09944920986890793, "task_loss": 0.05514444410800934, "partitioner_loss": 0.03286932036280632, "running_macro_f1": 0.7607404957195517, "running_accuracy": 0.9615234375, "lr": 9.503045956830301e-05, "codebook_loss": 0.045741770416498184, "codebook_perplexity": 111.50244140625, "codebook_active": 276.0, "codebook_commit": 0.18296708166599274} | |
| {"step": 21300, "epoch": 57, "loss": 0.11954944580793381, "task_loss": 0.07629088312387466, "partitioner_loss": 0.03203499689698219, "running_macro_f1": 0.7818422216159696, "running_accuracy": 0.9601171875, "lr": 9.503045956830301e-05, "codebook_loss": 0.044894251972436905, "codebook_perplexity": 109.29126739501953, "codebook_active": 278.0, "codebook_commit": 0.17957700788974762} | |
| {"step": 21350, "epoch": 57, "loss": 0.1638507843017578, "task_loss": 0.11846235394477844, "partitioner_loss": 0.036411769688129425, "running_macro_f1": 0.7477093555868453, "running_accuracy": 0.9514453125, "lr": 9.503045956830301e-05, "codebook_loss": 0.03590668365359306, "codebook_perplexity": 172.12550354003906, "codebook_active": 339.0, "codebook_commit": 0.14362673461437225} | |
| {"step": 21400, "epoch": 57, "loss": 0.2191341072320938, "task_loss": 0.1736009269952774, "partitioner_loss": 0.03516042232513428, "running_macro_f1": 0.7354148142623044, "running_accuracy": 0.959609375, "lr": 9.503045956830301e-05, "codebook_loss": 0.041491005569696426, "codebook_perplexity": 183.68118286132812, "codebook_active": 335.0, "codebook_commit": 0.1659640222787857} | |
| {"step": 21450, "epoch": 57, "loss": 0.08940431475639343, "task_loss": 0.04635598883032799, "partitioner_loss": 0.034435294568538666, "running_macro_f1": 0.7716439479045543, "running_accuracy": 0.9507421875, "lr": 9.503045956830301e-05, "codebook_loss": 0.034452155232429504, "codebook_perplexity": 135.8141326904297, "codebook_active": 309.0, "codebook_commit": 0.13780862092971802} | |
| {"step": 21500, "epoch": 57, "loss": 0.10226347297430038, "task_loss": 0.057691872119903564, "partitioner_loss": 0.03525304049253464, "running_macro_f1": 0.7513570479654292, "running_accuracy": 0.9473046875, "lr": 9.503045956830301e-05, "codebook_loss": 0.03727424144744873, "codebook_perplexity": 150.1253662109375, "codebook_active": 294.0, "codebook_commit": 0.14909696578979492} | |
| {"epoch": 57, "split": "val", "val_macro_f1": 0.3709061456204907, "val_accuracy": 0.6697728596389051} | |
| {"step": 21550, "epoch": 58, "loss": 0.10108629614114761, "task_loss": 0.05933074280619621, "partitioner_loss": 0.033060237765312195, "running_macro_f1": 0.7575560402810559, "running_accuracy": 0.9566630128405887, "lr": 9.14472331725031e-05, "codebook_loss": 0.03478123992681503, "codebook_perplexity": 141.64613342285156, "codebook_active": 323.0, "codebook_commit": 0.13912495970726013} | |
| {"step": 21600, "epoch": 58, "loss": 0.11170317232608795, "task_loss": 0.06244500353932381, "partitioner_loss": 0.03901709243655205, "running_macro_f1": 0.7800795373596745, "running_accuracy": 0.9670703125, "lr": 9.14472331725031e-05, "codebook_loss": 0.04096430540084839, "codebook_perplexity": 135.71560668945312, "codebook_active": 283.0, "codebook_commit": 0.16385722160339355} | |
| {"step": 21650, "epoch": 58, "loss": 0.06435645371675491, "task_loss": 0.02503049001097679, "partitioner_loss": 0.03154432401061058, "running_macro_f1": 0.7760822848391046, "running_accuracy": 0.9636328125, "lr": 9.14472331725031e-05, "codebook_loss": 0.031126566231250763, "codebook_perplexity": 115.85891723632812, "codebook_active": 292.0, "codebook_commit": 0.12450626492500305} | |
| {"step": 21700, "epoch": 58, "loss": 0.09727141261100769, "task_loss": 0.05024402588605881, "partitioner_loss": 0.036865174770355225, "running_macro_f1": 0.7782809443102187, "running_accuracy": 0.963046875, "lr": 9.14472331725031e-05, "codebook_loss": 0.040648847818374634, "codebook_perplexity": 157.76229858398438, "codebook_active": 334.0, "codebook_commit": 0.16259539127349854} | |
| {"step": 21750, "epoch": 58, "loss": 0.1279679834842682, "task_loss": 0.08609537780284882, "partitioner_loss": 0.032485902309417725, "running_macro_f1": 0.7742056783860303, "running_accuracy": 0.963359375, "lr": 9.14472331725031e-05, "codebook_loss": 0.0375467985868454, "codebook_perplexity": 171.24594116210938, "codebook_active": 353.0, "codebook_commit": 0.1501871943473816} | |
| {"step": 21800, "epoch": 58, "loss": 0.11691877245903015, "task_loss": 0.06972034275531769, "partitioner_loss": 0.03730306029319763, "running_macro_f1": 0.7807637246756398, "running_accuracy": 0.96078125, "lr": 9.14472331725031e-05, "codebook_loss": 0.03958147019147873, "codebook_perplexity": 159.2564239501953, "codebook_active": 327.0, "codebook_commit": 0.15832588076591492} | |
| {"step": 21850, "epoch": 58, "loss": 0.09592970460653305, "task_loss": 0.049220386892557144, "partitioner_loss": 0.03663851320743561, "running_macro_f1": 0.7684909531113211, "running_accuracy": 0.9509865330410272, "lr": 9.14472331725031e-05, "codebook_loss": 0.040283240377902985, "codebook_perplexity": 165.6975555419922, "codebook_active": 306.0, "codebook_commit": 0.16113296151161194} | |
| {"step": 21900, "epoch": 58, "loss": 0.08435449749231339, "task_loss": 0.03978992998600006, "partitioner_loss": 0.03413482755422592, "running_macro_f1": 0.754914569092056, "running_accuracy": 0.947109375, "lr": 9.14472331725031e-05, "codebook_loss": 0.041718948632478714, "codebook_perplexity": 175.51734924316406, "codebook_active": 359.0, "codebook_commit": 0.16687579452991486} | |
| {"epoch": 58, "split": "val", "val_macro_f1": 0.3824042414126252, "val_accuracy": 0.6833624538924481} | |
| {"step": 21950, "epoch": 59, "loss": 0.11710119247436523, "task_loss": 0.07565048336982727, "partitioner_loss": 0.03257632628083229, "running_macro_f1": 0.7292753352407477, "running_accuracy": 0.9622265625, "lr": 8.788772241641585e-05, "codebook_loss": 0.035497549921274185, "codebook_perplexity": 127.72936248779297, "codebook_active": 347.0, "codebook_commit": 0.14199019968509674} | |
| {"step": 22000, "epoch": 59, "loss": 0.07859709858894348, "task_loss": 0.040230948477983475, "partitioner_loss": 0.030453834682703018, "running_macro_f1": 0.7776697702040696, "running_accuracy": 0.9512890625, "lr": 8.788772241641585e-05, "codebook_loss": 0.031649261713027954, "codebook_perplexity": 116.29035949707031, "codebook_active": 323.0, "codebook_commit": 0.12659704685211182} | |
| {"step": 22050, "epoch": 59, "loss": 0.06486968696117401, "task_loss": 0.016813090071082115, "partitioner_loss": 0.03720550611615181, "running_macro_f1": 0.7835655000707902, "running_accuracy": 0.9619480112746633, "lr": 8.788772241641585e-05, "codebook_loss": 0.04340437054634094, "codebook_perplexity": 166.22657775878906, "codebook_active": 296.0, "codebook_commit": 0.17361748218536377} | |
| {"step": 22100, "epoch": 59, "loss": 0.08819384127855301, "task_loss": 0.042258210480213165, "partitioner_loss": 0.03667982667684555, "running_macro_f1": 0.7844726911845445, "running_accuracy": 0.95828125, "lr": 8.788772241641585e-05, "codebook_loss": 0.03702322393655777, "codebook_perplexity": 153.12020874023438, "codebook_active": 307.0, "codebook_commit": 0.14809289574623108} | |
| {"step": 22150, "epoch": 59, "loss": 0.0905296579003334, "task_loss": 0.04549265652894974, "partitioner_loss": 0.035312455147504807, "running_macro_f1": 0.7603787700177459, "running_accuracy": 0.9611328125, "lr": 8.788772241641585e-05, "codebook_loss": 0.03889819607138634, "codebook_perplexity": 179.59312438964844, "codebook_active": 323.0, "codebook_commit": 0.15559278428554535} | |
| {"step": 22200, "epoch": 59, "loss": 0.06346558779478073, "task_loss": 0.023795010522007942, "partitioner_loss": 0.0326458141207695, "running_macro_f1": 0.7810616245724968, "running_accuracy": 0.967890625, "lr": 8.788772241641585e-05, "codebook_loss": 0.028099050745368004, "codebook_perplexity": 190.9895477294922, "codebook_active": 391.0, "codebook_commit": 0.11239620298147202} | |
| {"step": 22250, "epoch": 59, "loss": 0.0966208428144455, "task_loss": 0.054603494703769684, "partitioner_loss": 0.03141236677765846, "running_macro_f1": 0.7606945042036531, "running_accuracy": 0.96, "lr": 8.788772241641585e-05, "codebook_loss": 0.0424199178814888, "codebook_perplexity": 168.52334594726562, "codebook_active": 327.0, "codebook_commit": 0.1696796715259552} | |
| {"step": 22300, "epoch": 59, "loss": 0.1133042573928833, "task_loss": 0.06550448387861252, "partitioner_loss": 0.03854769468307495, "running_macro_f1": 0.7823364600337243, "running_accuracy": 0.95984375, "lr": 8.788772241641585e-05, "codebook_loss": 0.03700830042362213, "codebook_perplexity": 151.3842315673828, "codebook_active": 311.0, "codebook_commit": 0.14803320169448853} | |
| {"epoch": 59, "split": "val", "val_macro_f1": 0.37733747799315276, "val_accuracy": 0.6872451951077461} | |
| {"step": 22350, "epoch": 60, "loss": 0.14258481562137604, "task_loss": 0.09067340195178986, "partitioner_loss": 0.04049466550350189, "running_macro_f1": 0.7568516532919137, "running_accuracy": 0.965, "lr": 8.435551142564599e-05, "codebook_loss": 0.04566701501607895, "codebook_perplexity": 163.7737579345703, "codebook_active": 336.0, "codebook_commit": 0.1826680600643158} | |
| {"step": 22400, "epoch": 60, "loss": 0.07840441912412643, "task_loss": 0.03674003854393959, "partitioner_loss": 0.032312169671058655, "running_macro_f1": 0.7266221976909972, "running_accuracy": 0.95734375, "lr": 8.435551142564599e-05, "codebook_loss": 0.037408847361803055, "codebook_perplexity": 74.56891632080078, "codebook_active": 264.0, "codebook_commit": 0.14963538944721222} | |
| {"step": 22450, "epoch": 60, "loss": 0.12090107798576355, "task_loss": 0.07443153858184814, "partitioner_loss": 0.03780809044837952, "running_macro_f1": 0.7560992175877198, "running_accuracy": 0.9614390854995303, "lr": 8.435551142564599e-05, "codebook_loss": 0.03464581072330475, "codebook_perplexity": 175.2766571044922, "codebook_active": 318.0, "codebook_commit": 0.138583242893219} | |
| {"step": 22500, "epoch": 60, "loss": 0.18430879712104797, "task_loss": 0.12793245911598206, "partitioner_loss": 0.04759053885936737, "running_macro_f1": 0.7440768392777918, "running_accuracy": 0.967578125, "lr": 8.435551142564599e-05, "codebook_loss": 0.03514321893453598, "codebook_perplexity": 74.27210235595703, "codebook_active": 205.0, "codebook_commit": 0.14057287573814392} | |
| {"step": 22550, "epoch": 60, "loss": 0.29116174578666687, "task_loss": 0.22871118783950806, "partitioner_loss": 0.04967781901359558, "running_macro_f1": 0.7528594519067432, "running_accuracy": 0.9425390625, "lr": 8.435551142564599e-05, "codebook_loss": 0.051090918481349945, "codebook_perplexity": 46.288089752197266, "codebook_active": 123.0, "codebook_commit": 0.20436367392539978} | |
| {"step": 22600, "epoch": 60, "loss": 0.2068222463130951, "task_loss": 0.16003772616386414, "partitioner_loss": 0.03641970455646515, "running_macro_f1": 0.7667649818085509, "running_accuracy": 0.957421875, "lr": 8.435551142564599e-05, "codebook_loss": 0.04145926982164383, "codebook_perplexity": 136.22930908203125, "codebook_active": 309.0, "codebook_commit": 0.16583707928657532} | |
| {"step": 22650, "epoch": 60, "loss": 0.08803100883960724, "task_loss": 0.04144936054944992, "partitioner_loss": 0.037203267216682434, "running_macro_f1": 0.7705730724117053, "running_accuracy": 0.96234375, "lr": 8.435551142564599e-05, "codebook_loss": 0.03751353546977043, "codebook_perplexity": 118.0528564453125, "codebook_active": 235.0, "codebook_commit": 0.15005414187908173} | |
| {"epoch": 60, "split": "val", "val_macro_f1": 0.3550044302896598, "val_accuracy": 0.6469617549990293} | |
| {"step": 22700, "epoch": 61, "loss": 0.12191514670848846, "task_loss": 0.07786274701356888, "partitioner_loss": 0.03417132422327995, "running_macro_f1": 0.7651644366227703, "running_accuracy": 0.961171875, "lr": 8.085415683724842e-05, "codebook_loss": 0.03952430188655853, "codebook_perplexity": 224.0574493408203, "codebook_active": 373.0, "codebook_commit": 0.15809720754623413} | |
| {"step": 22750, "epoch": 61, "loss": 0.10041041672229767, "task_loss": 0.05644961819052696, "partitioner_loss": 0.03500118851661682, "running_macro_f1": 0.7634897413832431, "running_accuracy": 0.96640625, "lr": 8.085415683724842e-05, "codebook_loss": 0.03583841025829315, "codebook_perplexity": 134.57786560058594, "codebook_active": 280.0, "codebook_commit": 0.1433536410331726} | |
| {"step": 22800, "epoch": 61, "loss": 0.10142002254724503, "task_loss": 0.055089034140110016, "partitioner_loss": 0.036179736256599426, "running_macro_f1": 0.773018381389966, "running_accuracy": 0.9653538991544003, "lr": 8.085415683724842e-05, "codebook_loss": 0.040605008602142334, "codebook_perplexity": 175.7215118408203, "codebook_active": 335.0, "codebook_commit": 0.16242003440856934} | |
| {"step": 22850, "epoch": 61, "loss": 0.3281553387641907, "task_loss": 0.2760111391544342, "partitioner_loss": 0.0405290350317955, "running_macro_f1": 0.7589193367739401, "running_accuracy": 0.9448046875, "lr": 8.085415683724842e-05, "codebook_loss": 0.046460606157779694, "codebook_perplexity": 175.93740844726562, "codebook_active": 370.0, "codebook_commit": 0.18584242463111877} | |
| {"step": 22900, "epoch": 61, "loss": 0.0973886027932167, "task_loss": 0.04744499549269676, "partitioner_loss": 0.03814311325550079, "running_macro_f1": 0.7641697495987986, "running_accuracy": 0.9530859375, "lr": 8.085415683724842e-05, "codebook_loss": 0.047201961278915405, "codebook_perplexity": 178.11276245117188, "codebook_active": 370.0, "codebook_commit": 0.18880784511566162} | |
| {"step": 22950, "epoch": 61, "loss": 0.11000049859285355, "task_loss": 0.06794679909944534, "partitioner_loss": 0.03255530819296837, "running_macro_f1": 0.7660597361538797, "running_accuracy": 0.9625, "lr": 8.085415683724842e-05, "codebook_loss": 0.03799358755350113, "codebook_perplexity": 139.53045654296875, "codebook_active": 322.0, "codebook_commit": 0.15197435021400452} | |
| {"step": 23000, "epoch": 61, "loss": 0.07333365827798843, "task_loss": 0.03066982515156269, "partitioner_loss": 0.03253614902496338, "running_macro_f1": 0.780155586681166, "running_accuracy": 0.953203125, "lr": 8.085415683724842e-05, "codebook_loss": 0.040510743856430054, "codebook_perplexity": 135.4922637939453, "codebook_active": 327.0, "codebook_commit": 0.16204297542572021} | |
| {"step": 23050, "epoch": 61, "loss": 0.08824124932289124, "task_loss": 0.04386717826128006, "partitioner_loss": 0.03465420752763748, "running_macro_f1": 0.777038058626626, "running_accuracy": 0.965703125, "lr": 8.085415683724842e-05, "codebook_loss": 0.03887946158647537, "codebook_perplexity": 179.5272674560547, "codebook_active": 328.0, "codebook_commit": 0.1555178463459015} | |
| {"epoch": 61, "split": "val", "val_macro_f1": 0.3834712583347801, "val_accuracy": 0.6720054358377014} | |
| {"step": 23100, "epoch": 62, "loss": 0.07653512060642242, "task_loss": 0.028613422065973282, "partitioner_loss": 0.03995482623577118, "running_macro_f1": 0.7834963049284941, "running_accuracy": 0.964609375, "lr": 7.738718421849652e-05, "codebook_loss": 0.03186751529574394, "codebook_perplexity": 153.14794921875, "codebook_active": 356.0, "codebook_commit": 0.12747006118297577} | |
| {"step": 23150, "epoch": 62, "loss": 0.10067110508680344, "task_loss": 0.056300897151231766, "partitioner_loss": 0.034216634929180145, "running_macro_f1": 0.7232923520820013, "running_accuracy": 0.9621875, "lr": 7.738718421849652e-05, "codebook_loss": 0.04061427339911461, "codebook_perplexity": 153.0540008544922, "codebook_active": 300.0, "codebook_commit": 0.16245709359645844} | |
| {"step": 23200, "epoch": 62, "loss": 0.12399856746196747, "task_loss": 0.08103024214506149, "partitioner_loss": 0.033015694469213486, "running_macro_f1": 0.7586776541246976, "running_accuracy": 0.949375, "lr": 7.738718421849652e-05, "codebook_loss": 0.039810530841350555, "codebook_perplexity": 156.04920959472656, "codebook_active": 351.0, "codebook_commit": 0.15924212336540222} | |
| {"step": 23250, "epoch": 62, "loss": 0.06156370788812637, "task_loss": 0.025085190311074257, "partitioner_loss": 0.03123786300420761, "running_macro_f1": 0.7852058550460231, "running_accuracy": 0.9630078125, "lr": 7.738718421849652e-05, "codebook_loss": 0.02096262387931347, "codebook_perplexity": 174.47813415527344, "codebook_active": 376.0, "codebook_commit": 0.08385049551725388} | |
| {"step": 23300, "epoch": 62, "loss": 0.11977662891149521, "task_loss": 0.07336005568504333, "partitioner_loss": 0.03658303990960121, "running_macro_f1": 0.7614145492629155, "running_accuracy": 0.9576171875, "lr": 7.738718421849652e-05, "codebook_loss": 0.03933414816856384, "codebook_perplexity": 174.26345825195312, "codebook_active": 307.0, "codebook_commit": 0.15733659267425537} | |
| {"step": 23350, "epoch": 62, "loss": 0.091265469789505, "task_loss": 0.04614365100860596, "partitioner_loss": 0.03556499257683754, "running_macro_f1": 0.7822378794152156, "running_accuracy": 0.963359375, "lr": 7.738718421849652e-05, "codebook_loss": 0.03822733461856842, "codebook_perplexity": 199.3851776123047, "codebook_active": 352.0, "codebook_commit": 0.15290933847427368} | |
| {"step": 23400, "epoch": 62, "loss": 0.1252463161945343, "task_loss": 0.0759812742471695, "partitioner_loss": 0.03833833336830139, "running_macro_f1": 0.7723397229491744, "running_accuracy": 0.9622611963670529, "lr": 7.738718421849652e-05, "codebook_loss": 0.04370681196451187, "codebook_perplexity": 184.98822021484375, "codebook_active": 360.0, "codebook_commit": 0.17482724785804749} | |
| {"epoch": 62, "split": "val", "val_macro_f1": 0.38508100391674416, "val_accuracy": 0.693263443991458} | |
| {"step": 23450, "epoch": 63, "loss": 0.10490594059228897, "task_loss": 0.05980980023741722, "partitioner_loss": 0.034549493342638016, "running_macro_f1": 0.7933398425284315, "running_accuracy": 0.9665234375, "lr": 7.395808451693475e-05, "codebook_loss": 0.04218659549951553, "codebook_perplexity": 156.2735595703125, "codebook_active": 342.0, "codebook_commit": 0.16874638199806213} | |
| {"step": 23500, "epoch": 63, "loss": 0.11310004442930222, "task_loss": 0.06376385688781738, "partitioner_loss": 0.038823533803224564, "running_macro_f1": 0.7693730603199043, "running_accuracy": 0.96609375, "lr": 7.395808451693475e-05, "codebook_loss": 0.042050622403621674, "codebook_perplexity": 79.56828308105469, "codebook_active": 199.0, "codebook_commit": 0.1682024896144867} | |
| {"step": 23550, "epoch": 63, "loss": 0.08362574875354767, "task_loss": 0.038212813436985016, "partitioner_loss": 0.036365702748298645, "running_macro_f1": 0.7618920217609918, "running_accuracy": 0.96640625, "lr": 7.395808451693475e-05, "codebook_loss": 0.03618893399834633, "codebook_perplexity": 187.78965759277344, "codebook_active": 338.0, "codebook_commit": 0.14475573599338531} | |
| {"step": 23600, "epoch": 63, "loss": 0.09963888674974442, "task_loss": 0.05680641531944275, "partitioner_loss": 0.03291139006614685, "running_macro_f1": 0.7540781444438157, "running_accuracy": 0.9562890625, "lr": 7.395808451693475e-05, "codebook_loss": 0.03968432918190956, "codebook_perplexity": 165.7385711669922, "codebook_active": 342.0, "codebook_commit": 0.15873731672763824} | |
| {"step": 23650, "epoch": 63, "loss": 0.10935478657484055, "task_loss": 0.06150276958942413, "partitioner_loss": 0.03661521524190903, "running_macro_f1": 0.7641895821157174, "running_accuracy": 0.954375, "lr": 7.395808451693475e-05, "codebook_loss": 0.04494721069931984, "codebook_perplexity": 119.85350036621094, "codebook_active": 329.0, "codebook_commit": 0.17978884279727936} | |
| {"step": 23700, "epoch": 63, "loss": 0.07800967246294022, "task_loss": 0.0379897803068161, "partitioner_loss": 0.03156929463148117, "running_macro_f1": 0.7890720643555658, "running_accuracy": 0.9670703125, "lr": 7.395808451693475e-05, "codebook_loss": 0.033802393823862076, "codebook_perplexity": 185.8438720703125, "codebook_active": 352.0, "codebook_commit": 0.1352095752954483} | |
| {"step": 23750, "epoch": 63, "loss": 0.1417912095785141, "task_loss": 0.09647610783576965, "partitioner_loss": 0.03653042018413544, "running_macro_f1": 0.7713193034483969, "running_accuracy": 0.95328125, "lr": 7.395808451693475e-05, "codebook_loss": 0.03513874113559723, "codebook_perplexity": 178.2753143310547, "codebook_active": 331.0, "codebook_commit": 0.14055496454238892} | |
| {"step": 23800, "epoch": 63, "loss": 0.12426386773586273, "task_loss": 0.07664185762405396, "partitioner_loss": 0.03619839996099472, "running_macro_f1": 0.8084303525503801, "running_accuracy": 0.9632398997807704, "lr": 7.395808451693475e-05, "codebook_loss": 0.045694440603256226, "codebook_perplexity": 134.86058044433594, "codebook_active": 300.0, "codebook_commit": 0.1827777624130249} | |
| {"epoch": 63, "split": "val", "val_macro_f1": 0.3775272433573375, "val_accuracy": 0.6765676567656765} | |
| {"step": 23850, "epoch": 64, "loss": 0.07406920939683914, "task_loss": 0.030856190249323845, "partitioner_loss": 0.03242340683937073, "running_macro_f1": 0.7639894265445452, "running_accuracy": 0.9602734375, "lr": 7.05703105452902e-05, "codebook_loss": 0.04315844178199768, "codebook_perplexity": 205.24050903320312, "codebook_active": 378.0, "codebook_commit": 0.17263376712799072} | |
| {"step": 23900, "epoch": 64, "loss": 0.11774537712335587, "task_loss": 0.06424223631620407, "partitioner_loss": 0.03989220783114433, "running_macro_f1": 0.7701528527013474, "running_accuracy": 0.955234375, "lr": 7.05703105452902e-05, "codebook_loss": 0.05444375425577164, "codebook_perplexity": 158.30850219726562, "codebook_active": 273.0, "codebook_commit": 0.21777501702308655} | |
| {"step": 23950, "epoch": 64, "loss": 0.07076801359653473, "task_loss": 0.0280593391507864, "partitioner_loss": 0.032843977212905884, "running_macro_f1": 0.78383994620016, "running_accuracy": 0.9634375, "lr": 7.05703105452902e-05, "codebook_loss": 0.03945878520607948, "codebook_perplexity": 184.4818878173828, "codebook_active": 309.0, "codebook_commit": 0.15783514082431793} | |
| {"step": 24000, "epoch": 64, "loss": 0.12100405991077423, "task_loss": 0.07618314027786255, "partitioner_loss": 0.03363632783293724, "running_macro_f1": 0.7591485707967024, "running_accuracy": 0.967265625, "lr": 7.05703105452902e-05, "codebook_loss": 0.04473835229873657, "codebook_perplexity": 165.2830352783203, "codebook_active": 309.0, "codebook_commit": 0.1789534091949463} | |
| {"step": 24050, "epoch": 64, "loss": 0.1603393703699112, "task_loss": 0.11848808825016022, "partitioner_loss": 0.033038899302482605, "running_macro_f1": 0.770221656123502, "running_accuracy": 0.963828125, "lr": 7.05703105452902e-05, "codebook_loss": 0.035249531269073486, "codebook_perplexity": 146.4060516357422, "codebook_active": 312.0, "codebook_commit": 0.14099812507629395} | |
| {"step": 24100, "epoch": 64, "loss": 0.10943230241537094, "task_loss": 0.06323955953121185, "partitioner_loss": 0.03476192057132721, "running_macro_f1": 0.7792861110907635, "running_accuracy": 0.9664453125, "lr": 7.05703105452902e-05, "codebook_loss": 0.04572328180074692, "codebook_perplexity": 103.95291900634766, "codebook_active": 265.0, "codebook_commit": 0.18289312720298767} | |
| {"step": 24150, "epoch": 64, "loss": 0.060986921191215515, "task_loss": 0.019165076315402985, "partitioner_loss": 0.03301700949668884, "running_macro_f1": 0.772939898153737, "running_accuracy": 0.96984375, "lr": 7.05703105452902e-05, "codebook_loss": 0.03521934896707535, "codebook_perplexity": 176.85853576660156, "codebook_active": 355.0, "codebook_commit": 0.1408773958683014} | |
| {"epoch": 64, "split": "val", "val_macro_f1": 0.38037652794429655, "val_accuracy": 0.6839448650747427} | |
| {"step": 24200, "epoch": 65, "loss": 0.0886639803647995, "task_loss": 0.04233305901288986, "partitioner_loss": 0.034761205315589905, "running_macro_f1": 0.7619586971039842, "running_accuracy": 0.9588944566238647, "lr": 6.722727350478307e-05, "codebook_loss": 0.04627884924411774, "codebook_perplexity": 103.92581176757812, "codebook_active": 222.0, "codebook_commit": 0.18511539697647095} | |
| {"step": 24250, "epoch": 65, "loss": 0.12560302019119263, "task_loss": 0.0674508810043335, "partitioner_loss": 0.04805523529648781, "running_macro_f1": 0.8065347118262183, "running_accuracy": 0.969140625, "lr": 6.722727350478307e-05, "codebook_loss": 0.04038764536380768, "codebook_perplexity": 126.14925384521484, "codebook_active": 232.0, "codebook_commit": 0.1615505814552307} | |
| {"step": 24300, "epoch": 65, "loss": 0.09322845935821533, "task_loss": 0.045595649629831314, "partitioner_loss": 0.03746134042739868, "running_macro_f1": 0.7435008334674286, "running_accuracy": 0.966484375, "lr": 6.722727350478307e-05, "codebook_loss": 0.04068589210510254, "codebook_perplexity": 184.0206298828125, "codebook_active": 338.0, "codebook_commit": 0.16274356842041016} | |
| {"step": 24350, "epoch": 65, "loss": 0.08184419572353363, "task_loss": 0.040173787623643875, "partitioner_loss": 0.03387995809316635, "running_macro_f1": 0.7505297763348954, "running_accuracy": 0.9609375, "lr": 6.722727350478307e-05, "codebook_loss": 0.031161775812506676, "codebook_perplexity": 239.427001953125, "codebook_active": 390.0, "codebook_commit": 0.1246471032500267} | |
| {"step": 24400, "epoch": 65, "loss": 0.11741133034229279, "task_loss": 0.07328370213508606, "partitioner_loss": 0.03286866471171379, "running_macro_f1": 0.7785287835567914, "running_accuracy": 0.9577734375, "lr": 6.722727350478307e-05, "codebook_loss": 0.04503583908081055, "codebook_perplexity": 118.82420349121094, "codebook_active": 269.0, "codebook_commit": 0.1801433563232422} | |
| {"step": 24450, "epoch": 65, "loss": 0.12117691338062286, "task_loss": 0.07996666431427002, "partitioner_loss": 0.031966432929039, "running_macro_f1": 0.775996650033764, "running_accuracy": 0.9638662699655497, "lr": 6.722727350478307e-05, "codebook_loss": 0.03697524964809418, "codebook_perplexity": 160.78233337402344, "codebook_active": 304.0, "codebook_commit": 0.1479009985923767} | |
| {"step": 24500, "epoch": 65, "loss": 0.09105657041072845, "task_loss": 0.04828758165240288, "partitioner_loss": 0.03366142138838768, "running_macro_f1": 0.7590201509577319, "running_accuracy": 0.9662109375, "lr": 6.722727350478307e-05, "codebook_loss": 0.03643025457859039, "codebook_perplexity": 120.98905944824219, "codebook_active": 302.0, "codebook_commit": 0.14572101831436157} | |
| {"step": 24550, "epoch": 65, "loss": 0.22193643450737, "task_loss": 0.1567244678735733, "partitioner_loss": 0.05423760041594505, "running_macro_f1": 0.7230953419643494, "running_accuracy": 0.94296875, "lr": 6.722727350478307e-05, "codebook_loss": 0.043897464871406555, "codebook_perplexity": 73.84403991699219, "codebook_active": 165.0, "codebook_commit": 0.17558985948562622} | |
| {"epoch": 65, "split": "val", "val_macro_f1": 0.3646066897228374, "val_accuracy": 0.6697728596389051} | |
| {"step": 24600, "epoch": 66, "loss": 0.08195092529058456, "task_loss": 0.03882461041212082, "partitioner_loss": 0.032866448163986206, "running_macro_f1": 0.7876507743700134, "running_accuracy": 0.9607421875, "lr": 6.393233955033597e-05, "codebook_loss": 0.04103945568203926, "codebook_perplexity": 220.960205078125, "codebook_active": 371.0, "codebook_commit": 0.16415782272815704} | |
| {"step": 24650, "epoch": 66, "loss": 0.10002338886260986, "task_loss": 0.05449476093053818, "partitioner_loss": 0.033746056258678436, "running_macro_f1": 0.7675413595469374, "running_accuracy": 0.9577200125274037, "lr": 6.393233955033597e-05, "codebook_loss": 0.0471302792429924, "codebook_perplexity": 172.7020721435547, "codebook_active": 362.0, "codebook_commit": 0.1885211169719696} | |
| {"step": 24700, "epoch": 66, "loss": 0.12299026548862457, "task_loss": 0.07798498868942261, "partitioner_loss": 0.034828413277864456, "running_macro_f1": 0.7769587559160533, "running_accuracy": 0.9495703125, "lr": 6.393233955033597e-05, "codebook_loss": 0.040707483887672424, "codebook_perplexity": 109.3186264038086, "codebook_active": 291.0, "codebook_commit": 0.1628299355506897} | |
| {"step": 24750, "epoch": 66, "loss": 0.09258948266506195, "task_loss": 0.04698150232434273, "partitioner_loss": 0.034456297755241394, "running_macro_f1": 0.7785864556840619, "running_accuracy": 0.9655078125, "lr": 6.393233955033597e-05, "codebook_loss": 0.04460674524307251, "codebook_perplexity": 170.0113525390625, "codebook_active": 332.0, "codebook_commit": 0.17842698097229004} | |
| {"step": 24800, "epoch": 66, "loss": 0.08779704570770264, "task_loss": 0.04318030923604965, "partitioner_loss": 0.03452511131763458, "running_macro_f1": 0.798202148831113, "running_accuracy": 0.964140625, "lr": 6.393233955033597e-05, "codebook_loss": 0.04036650061607361, "codebook_perplexity": 142.02650451660156, "codebook_active": 316.0, "codebook_commit": 0.16146600246429443} | |
| {"step": 24850, "epoch": 66, "loss": 0.08353911340236664, "task_loss": 0.03915061801671982, "partitioner_loss": 0.033937886357307434, "running_macro_f1": 0.7760811166709497, "running_accuracy": 0.968671875, "lr": 6.393233955033597e-05, "codebook_loss": 0.04180244356393814, "codebook_perplexity": 187.43191528320312, "codebook_active": 337.0, "codebook_commit": 0.16720977425575256} | |
| {"step": 24900, "epoch": 66, "loss": 0.11045366525650024, "task_loss": 0.06595481932163239, "partitioner_loss": 0.03391692787408829, "running_macro_f1": 0.7496689893237478, "running_accuracy": 0.961953125, "lr": 6.393233955033597e-05, "codebook_loss": 0.04232767969369888, "codebook_perplexity": 202.56097412109375, "codebook_active": 376.0, "codebook_commit": 0.16931071877479553} | |
| {"epoch": 66, "split": "val", "val_macro_f1": 0.38591372559316267, "val_accuracy": 0.6799650553290624} | |
| {"step": 24950, "epoch": 67, "loss": 0.07356773316860199, "task_loss": 0.028977202251553535, "partitioner_loss": 0.0351758748292923, "running_macro_f1": 0.7774444448710083, "running_accuracy": 0.9678515625, "lr": 6.06888264011415e-05, "codebook_loss": 0.03765864297747612, "codebook_perplexity": 181.5568084716797, "codebook_active": 353.0, "codebook_commit": 0.15063457190990448} | |
| {"step": 25000, "epoch": 67, "loss": 0.08449152857065201, "task_loss": 0.04222358763217926, "partitioner_loss": 0.03112688660621643, "running_macro_f1": 0.79632342129726, "running_accuracy": 0.97, "lr": 6.06888264011415e-05, "codebook_loss": 0.044564228504896164, "codebook_perplexity": 95.44110870361328, "codebook_active": 269.0, "codebook_commit": 0.17825691401958466} | |
| {"step": 25050, "epoch": 67, "loss": 0.11862652003765106, "task_loss": 0.07499004900455475, "partitioner_loss": 0.03157646209001541, "running_macro_f1": 0.7704307892657373, "running_accuracy": 0.9527734375, "lr": 6.06888264011415e-05, "codebook_loss": 0.04824002832174301, "codebook_perplexity": 93.26168823242188, "codebook_active": 214.0, "codebook_commit": 0.19296011328697205} | |
| {"step": 25100, "epoch": 67, "loss": 0.06575988233089447, "task_loss": 0.025713084265589714, "partitioner_loss": 0.03180452436208725, "running_macro_f1": 0.7780081077398266, "running_accuracy": 0.9525, "lr": 6.06888264011415e-05, "codebook_loss": 0.032969072461128235, "codebook_perplexity": 212.38595581054688, "codebook_active": 384.0, "codebook_commit": 0.13187628984451294} | |
| {"step": 25150, "epoch": 67, "loss": 0.08316457271575928, "task_loss": 0.03386227786540985, "partitioner_loss": 0.04113203287124634, "running_macro_f1": 0.7883995019234707, "running_accuracy": 0.9666457876605073, "lr": 6.06888264011415e-05, "codebook_loss": 0.03268106281757355, "codebook_perplexity": 66.06858825683594, "codebook_active": 171.0, "codebook_commit": 0.1307242512702942} | |
| {"step": 25200, "epoch": 67, "loss": 0.12992063164710999, "task_loss": 0.08073435723781586, "partitioner_loss": 0.03876735270023346, "running_macro_f1": 0.7818357195564838, "running_accuracy": 0.96984375, "lr": 6.06888264011415e-05, "codebook_loss": 0.041675686836242676, "codebook_perplexity": 141.32432556152344, "codebook_active": 253.0, "codebook_commit": 0.1667027473449707} | |
| {"step": 25250, "epoch": 67, "loss": 0.1035432517528534, "task_loss": 0.05995716154575348, "partitioner_loss": 0.03259408101439476, "running_macro_f1": 0.7888576107012516, "running_accuracy": 0.9719140625, "lr": 6.06888264011415e-05, "codebook_loss": 0.04396800696849823, "codebook_perplexity": 188.52734375, "codebook_active": 364.0, "codebook_commit": 0.17587202787399292} | |
| {"step": 25300, "epoch": 67, "loss": 0.06574142724275589, "task_loss": 0.024423517286777496, "partitioner_loss": 0.03183714672923088, "running_macro_f1": 0.748966030264943, "running_accuracy": 0.9616796875, "lr": 6.06888264011415e-05, "codebook_loss": 0.037923045456409454, "codebook_perplexity": 213.56072998046875, "codebook_active": 391.0, "codebook_commit": 0.15169218182563782} | |
| {"epoch": 67, "split": "val", "val_macro_f1": 0.38917941109326104, "val_accuracy": 0.6821976315278586} | |
| {"step": 25350, "epoch": 68, "loss": 0.1468765288591385, "task_loss": 0.10179439187049866, "partitioner_loss": 0.035397060215473175, "running_macro_f1": 0.802311616958304, "running_accuracy": 0.969296875, "lr": 5.750000000000003e-05, "codebook_loss": 0.03874035179615021, "codebook_perplexity": 138.88917541503906, "codebook_active": 329.0, "codebook_commit": 0.15496140718460083} | |
| {"step": 25400, "epoch": 68, "loss": 0.06040599197149277, "task_loss": 0.020181670784950256, "partitioner_loss": 0.03199581056833267, "running_macro_f1": 0.7691274587700033, "running_accuracy": 0.9678125, "lr": 5.750000000000003e-05, "codebook_loss": 0.032914042472839355, "codebook_perplexity": 186.9556121826172, "codebook_active": 384.0, "codebook_commit": 0.13165616989135742} | |
| {"step": 25450, "epoch": 68, "loss": 0.06775954365730286, "task_loss": 0.025240084156394005, "partitioner_loss": 0.033567771315574646, "running_macro_f1": 0.7942472790797145, "running_accuracy": 0.971953125, "lr": 5.750000000000003e-05, "codebook_loss": 0.035806745290756226, "codebook_perplexity": 135.88351440429688, "codebook_active": 307.0, "codebook_commit": 0.1432269811630249} | |
| {"step": 25500, "epoch": 68, "loss": 0.2564103603363037, "task_loss": 0.19885779917240143, "partitioner_loss": 0.04794588312506676, "running_macro_f1": 0.7925987638893062, "running_accuracy": 0.9719921875, "lr": 5.750000000000003e-05, "codebook_loss": 0.038426753133535385, "codebook_perplexity": 55.375022888183594, "codebook_active": 154.0, "codebook_commit": 0.15370701253414154} | |
| {"step": 25550, "epoch": 68, "loss": 0.1364780217409134, "task_loss": 0.09411860257387161, "partitioner_loss": 0.032307788729667664, "running_macro_f1": 0.8095411786349709, "running_accuracy": 0.969609375, "lr": 5.750000000000003e-05, "codebook_loss": 0.04020646959543228, "codebook_perplexity": 188.16424560546875, "codebook_active": 364.0, "codebook_commit": 0.16082587838172913} | |
| {"step": 25600, "epoch": 68, "loss": 0.07632870972156525, "task_loss": 0.030692828819155693, "partitioner_loss": 0.03558219596743584, "running_macro_f1": 0.7680415059828342, "running_accuracy": 0.9651953125, "lr": 5.750000000000003e-05, "codebook_loss": 0.04021473228931427, "codebook_perplexity": 141.52664184570312, "codebook_active": 284.0, "codebook_commit": 0.16085892915725708} | |
| {"step": 25650, "epoch": 68, "loss": 0.0903298556804657, "task_loss": 0.047508660703897476, "partitioner_loss": 0.031915005296468735, "running_macro_f1": 0.7757366707167842, "running_accuracy": 0.9514954588161604, "lr": 5.750000000000003e-05, "codebook_loss": 0.043624743819236755, "codebook_perplexity": 139.63589477539062, "codebook_active": 311.0, "codebook_commit": 0.17449897527694702} | |
| {"step": 25700, "epoch": 68, "loss": 0.15951572358608246, "task_loss": 0.11472148448228836, "partitioner_loss": 0.03500841557979584, "running_macro_f1": 0.7642009762101616, "running_accuracy": 0.9572265625, "lr": 5.750000000000003e-05, "codebook_loss": 0.03914327919483185, "codebook_perplexity": 162.16346740722656, "codebook_active": 359.0, "codebook_commit": 0.1565731167793274} | |
| {"epoch": 68, "split": "val", "val_macro_f1": 0.38564029347925105, "val_accuracy": 0.671034750533877} | |
| {"step": 25750, "epoch": 69, "loss": 0.08856303989887238, "task_loss": 0.04367082193493843, "partitioner_loss": 0.0331549234688282, "running_macro_f1": 0.7536583712947236, "running_accuracy": 0.969921875, "lr": 5.436907122479222e-05, "codebook_loss": 0.04694917052984238, "codebook_perplexity": 76.25129699707031, "codebook_active": 200.0, "codebook_commit": 0.1877966821193695} | |
| {"step": 25800, "epoch": 69, "loss": 0.1534276157617569, "task_loss": 0.11057616025209427, "partitioner_loss": 0.0330243818461895, "running_macro_f1": 0.7662820872316954, "running_accuracy": 0.94796875, "lr": 5.436907122479222e-05, "codebook_loss": 0.039308324456214905, "codebook_perplexity": 177.902099609375, "codebook_active": 354.0, "codebook_commit": 0.15723329782485962} | |
| {"step": 25850, "epoch": 69, "loss": 0.06853219866752625, "task_loss": 0.026593273505568504, "partitioner_loss": 0.03172452375292778, "running_macro_f1": 0.7778021281283937, "running_accuracy": 0.9699609375, "lr": 5.436907122479222e-05, "codebook_loss": 0.04085760936141014, "codebook_perplexity": 167.5345458984375, "codebook_active": 316.0, "codebook_commit": 0.16343043744564056} | |
| {"step": 25900, "epoch": 69, "loss": 0.05991993099451065, "task_loss": 0.014972464181482792, "partitioner_loss": 0.03496517986059189, "running_macro_f1": 0.7992912763382366, "running_accuracy": 0.9706640625, "lr": 5.436907122479222e-05, "codebook_loss": 0.03992914780974388, "codebook_perplexity": 181.60546875, "codebook_active": 312.0, "codebook_commit": 0.15971659123897552} | |
| {"step": 25950, "epoch": 69, "loss": 0.2539026141166687, "task_loss": 0.21248558163642883, "partitioner_loss": 0.03127491474151611, "running_macro_f1": 0.7950165099812062, "running_accuracy": 0.9672721578452865, "lr": 5.436907122479222e-05, "codebook_loss": 0.04056841880083084, "codebook_perplexity": 100.64950561523438, "codebook_active": 312.0, "codebook_commit": 0.16227367520332336} | |
| {"step": 26000, "epoch": 69, "loss": 0.08887672424316406, "task_loss": 0.04741048440337181, "partitioner_loss": 0.032946616411209106, "running_macro_f1": 0.8114308737412671, "running_accuracy": 0.9660546875, "lr": 5.436907122479222e-05, "codebook_loss": 0.03407848998904228, "codebook_perplexity": 203.1982879638672, "codebook_active": 387.0, "codebook_commit": 0.13631395995616913} | |
| {"step": 26050, "epoch": 69, "loss": 0.15289618074893951, "task_loss": 0.10889119654893875, "partitioner_loss": 0.033492736518383026, "running_macro_f1": 0.7583652999362004, "running_accuracy": 0.9687109375, "lr": 5.436907122479222e-05, "codebook_loss": 0.042048968374729156, "codebook_perplexity": 179.40028381347656, "codebook_active": 365.0, "codebook_commit": 0.16819587349891663} | |
| {"epoch": 69, "split": "val", "val_macro_f1": 0.38318958259780556, "val_accuracy": 0.6798679867986799} | |
| {"step": 26100, "epoch": 70, "loss": 0.10938934236764908, "task_loss": 0.06432164460420609, "partitioner_loss": 0.03532284498214722, "running_macro_f1": 0.788303172259183, "running_accuracy": 0.9698828125, "lr": 5.129919265539732e-05, "codebook_loss": 0.038979422301054, "codebook_perplexity": 184.249267578125, "codebook_active": 333.0, "codebook_commit": 0.155917689204216} | |
| {"step": 26150, "epoch": 70, "loss": 0.09565292298793793, "task_loss": 0.054643664509058, "partitioner_loss": 0.03243579715490341, "running_macro_f1": 0.7673096445808918, "running_accuracy": 0.9559583463827122, "lr": 5.129919265539732e-05, "codebook_loss": 0.03429384529590607, "codebook_perplexity": 144.2621307373047, "codebook_active": 338.0, "codebook_commit": 0.13717538118362427} | |
| {"step": 26200, "epoch": 70, "loss": 0.07771045714616776, "task_loss": 0.03446996957063675, "partitioner_loss": 0.03407738357782364, "running_macro_f1": 0.7857499497827024, "running_accuracy": 0.9730859375, "lr": 5.129919265539732e-05, "codebook_loss": 0.036652423441410065, "codebook_perplexity": 187.71275329589844, "codebook_active": 365.0, "codebook_commit": 0.14660969376564026} | |
| {"step": 26250, "epoch": 70, "loss": 0.06968874484300613, "task_loss": 0.02555060014128685, "partitioner_loss": 0.03467460721731186, "running_macro_f1": 0.8056060188305169, "running_accuracy": 0.9702734375, "lr": 5.129919265539732e-05, "codebook_loss": 0.0378541573882103, "codebook_perplexity": 156.42311096191406, "codebook_active": 288.0, "codebook_commit": 0.1514166295528412} | |
| {"step": 26300, "epoch": 70, "loss": 0.13528135418891907, "task_loss": 0.084556445479393, "partitioner_loss": 0.037754833698272705, "running_macro_f1": 0.795929528177313, "running_accuracy": 0.9671484375, "lr": 5.129919265539732e-05, "codebook_loss": 0.05188027024269104, "codebook_perplexity": 135.52806091308594, "codebook_active": 272.0, "codebook_commit": 0.20752108097076416} | |
| {"step": 26350, "epoch": 70, "loss": 0.20512905716896057, "task_loss": 0.16291280090808868, "partitioner_loss": 0.03216126561164856, "running_macro_f1": 0.768306728466491, "running_accuracy": 0.9642578125, "lr": 5.129919265539732e-05, "codebook_loss": 0.0402199849486351, "codebook_perplexity": 126.45375061035156, "codebook_active": 260.0, "codebook_commit": 0.1608799397945404} | |
| {"step": 26400, "epoch": 70, "loss": 0.08828295767307281, "task_loss": 0.04477507993578911, "partitioner_loss": 0.033063411712646484, "running_macro_f1": 0.7895113904929293, "running_accuracy": 0.9711328125, "lr": 5.129919265539732e-05, "codebook_loss": 0.0417778380215168, "codebook_perplexity": 219.34922790527344, "codebook_active": 351.0, "codebook_commit": 0.1671113520860672} | |
| {"step": 26450, "epoch": 70, "loss": 0.08751824498176575, "task_loss": 0.0431160032749176, "partitioner_loss": 0.03563101589679718, "running_macro_f1": 0.7944379073521414, "running_accuracy": 0.9670703125, "lr": 5.129919265539732e-05, "codebook_loss": 0.03508491441607475, "codebook_perplexity": 136.07408142089844, "codebook_active": 328.0, "codebook_commit": 0.140339657664299} | |
| {"epoch": 70, "split": "val", "val_macro_f1": 0.37843304073862194, "val_accuracy": 0.6972432537371385} | |
| {"step": 26500, "epoch": 71, "loss": 0.06507442146539688, "task_loss": 0.0243556909263134, "partitioner_loss": 0.031105544418096542, "running_macro_f1": 0.7725432350168183, "running_accuracy": 0.9546875, "lr": 4.829345539931223e-05, "codebook_loss": 0.03845274820923805, "codebook_perplexity": 162.46121215820312, "codebook_active": 271.0, "codebook_commit": 0.1538109928369522} | |
| {"step": 26550, "epoch": 71, "loss": 0.07791675627231598, "task_loss": 0.027844633907079697, "partitioner_loss": 0.03950997814536095, "running_macro_f1": 0.7928558997877888, "running_accuracy": 0.9644143438772315, "lr": 4.829345539931223e-05, "codebook_loss": 0.04224859178066254, "codebook_perplexity": 144.35447692871094, "codebook_active": 297.0, "codebook_commit": 0.16899436712265015} | |
| {"step": 26600, "epoch": 71, "loss": 0.04940754547715187, "task_loss": 0.013769634068012238, "partitioner_loss": 0.02816440723836422, "running_macro_f1": 0.7954855897732732, "running_accuracy": 0.9703515625, "lr": 4.829345539931223e-05, "codebook_loss": 0.02989400550723076, "codebook_perplexity": 141.42584228515625, "codebook_active": 297.0, "codebook_commit": 0.11957602202892303} | |
| {"step": 26650, "epoch": 71, "loss": 0.07113738358020782, "task_loss": 0.029940983280539513, "partitioner_loss": 0.03183089941740036, "running_macro_f1": 0.7845154050414664, "running_accuracy": 0.97078125, "lr": 4.829345539931223e-05, "codebook_loss": 0.03746199607849121, "codebook_perplexity": 210.2561798095703, "codebook_active": 373.0, "codebook_commit": 0.14984798431396484} | |
| {"step": 26700, "epoch": 71, "loss": 0.07648904621601105, "task_loss": 0.033759187906980515, "partitioner_loss": 0.03347861021757126, "running_macro_f1": 0.8021708403397512, "running_accuracy": 0.9745703125, "lr": 4.829345539931223e-05, "codebook_loss": 0.03700500726699829, "codebook_perplexity": 204.72384643554688, "codebook_active": 386.0, "codebook_commit": 0.14802002906799316} | |
| {"step": 26750, "epoch": 71, "loss": 0.09493126720190048, "task_loss": 0.04581079259514809, "partitioner_loss": 0.03945118933916092, "running_macro_f1": 0.7845412103653872, "running_accuracy": 0.971640625, "lr": 4.829345539931223e-05, "codebook_loss": 0.03867712616920471, "codebook_perplexity": 172.32391357421875, "codebook_active": 380.0, "codebook_commit": 0.15470850467681885} | |
| {"step": 26800, "epoch": 71, "loss": 0.08205877989530563, "task_loss": 0.0400383323431015, "partitioner_loss": 0.029020804911851883, "running_macro_f1": 0.7819090201134158, "running_accuracy": 0.965859375, "lr": 4.829345539931223e-05, "codebook_loss": 0.05199858173727989, "codebook_perplexity": 101.6207046508789, "codebook_active": 273.0, "codebook_commit": 0.20799432694911957} | |
| {"epoch": 71, "split": "val", "val_macro_f1": 0.3825043081105273, "val_accuracy": 0.7026790914385557} | |
| {"step": 26850, "epoch": 72, "loss": 0.13745521008968353, "task_loss": 0.09045527130365372, "partitioner_loss": 0.03594375401735306, "running_macro_f1": 0.7820293315925784, "running_accuracy": 0.9682421875, "lr": 4.535488597916835e-05, "codebook_loss": 0.044224753975868225, "codebook_perplexity": 168.1127166748047, "codebook_active": 263.0, "codebook_commit": 0.1768990159034729} | |
| {"step": 26900, "epoch": 72, "loss": 0.13171084225177765, "task_loss": 0.08890552818775177, "partitioner_loss": 0.032560888677835464, "running_macro_f1": 0.7630729007261497, "running_accuracy": 0.972265625, "lr": 4.535488597916835e-05, "codebook_loss": 0.04097773879766464, "codebook_perplexity": 193.8352813720703, "codebook_active": 365.0, "codebook_commit": 0.16391095519065857} | |
| {"step": 26950, "epoch": 72, "loss": 0.07722573727369308, "task_loss": 0.03708789870142937, "partitioner_loss": 0.030539413914084435, "running_macro_f1": 0.818867028924132, "running_accuracy": 0.957265625, "lr": 4.535488597916835e-05, "codebook_loss": 0.038393717259168625, "codebook_perplexity": 195.0130615234375, "codebook_active": 344.0, "codebook_commit": 0.1535748690366745} | |
| {"step": 27000, "epoch": 72, "loss": 0.13736268877983093, "task_loss": 0.0976153016090393, "partitioner_loss": 0.03339693695306778, "running_macro_f1": 0.7989846342805439, "running_accuracy": 0.9708984375, "lr": 4.535488597916835e-05, "codebook_loss": 0.025401819497346878, "codebook_perplexity": 171.50440979003906, "codebook_active": 341.0, "codebook_commit": 0.10160727798938751} | |
| {"step": 27050, "epoch": 72, "loss": 0.08374173939228058, "task_loss": 0.044589076191186905, "partitioner_loss": 0.030334971845149994, "running_macro_f1": 0.7697714842201349, "running_accuracy": 0.9580078125, "lr": 4.535488597916835e-05, "codebook_loss": 0.035270750522613525, "codebook_perplexity": 108.4480972290039, "codebook_active": 309.0, "codebook_commit": 0.1410830020904541} | |
| {"step": 27100, "epoch": 72, "loss": 0.07274651527404785, "task_loss": 0.029145309701561928, "partitioner_loss": 0.033861029893159866, "running_macro_f1": 0.7933551000554905, "running_accuracy": 0.9741622298778578, "lr": 4.535488597916835e-05, "codebook_loss": 0.03896071016788483, "codebook_perplexity": 179.78256225585938, "codebook_active": 321.0, "codebook_commit": 0.1558428406715393} | |
| {"step": 27150, "epoch": 72, "loss": 0.16591408848762512, "task_loss": 0.11801639199256897, "partitioner_loss": 0.037306301295757294, "running_macro_f1": 0.7716072149116266, "running_accuracy": 0.9681640625, "lr": 4.535488597916835e-05, "codebook_loss": 0.042365580797195435, "codebook_perplexity": 152.13479614257812, "codebook_active": 348.0, "codebook_commit": 0.16946232318878174} | |
| {"step": 27200, "epoch": 72, "loss": 0.1622287780046463, "task_loss": 0.1192999929189682, "partitioner_loss": 0.03238088637590408, "running_macro_f1": 0.8115438224072254, "running_accuracy": 0.966171875, "lr": 4.535488597916835e-05, "codebook_loss": 0.04219156503677368, "codebook_perplexity": 123.12557983398438, "codebook_active": 292.0, "codebook_commit": 0.16876626014709473} | |
| {"epoch": 72, "split": "val", "val_macro_f1": 0.37641319238776166, "val_accuracy": 0.6926810328091633} | |
| {"step": 27250, "epoch": 73, "loss": 0.08924160897731781, "task_loss": 0.04732435196638107, "partitioner_loss": 0.032598137855529785, "running_macro_f1": 0.7568162989090031, "running_accuracy": 0.9697265625, "lr": 4.248644328527995e-05, "codebook_loss": 0.037276491522789, "codebook_perplexity": 190.96778869628906, "codebook_active": 379.0, "codebook_commit": 0.149105966091156} | |
| {"step": 27300, "epoch": 73, "loss": 0.1009584590792656, "task_loss": 0.055160511285066605, "partitioner_loss": 0.03480764105916023, "running_macro_f1": 0.7794658799581359, "running_accuracy": 0.9707421875, "lr": 4.248644328527995e-05, "codebook_loss": 0.043961215764284134, "codebook_perplexity": 126.63725280761719, "codebook_active": 310.0, "codebook_commit": 0.17584486305713654} | |
| {"step": 27350, "epoch": 73, "loss": 0.3960302472114563, "task_loss": 0.3295363187789917, "partitioner_loss": 0.05637706071138382, "running_macro_f1": 0.7726701052641942, "running_accuracy": 0.9649609375, "lr": 4.248644328527995e-05, "codebook_loss": 0.04046747460961342, "codebook_perplexity": 28.11342430114746, "codebook_active": 114.0, "codebook_commit": 0.16186989843845367} | |
| {"step": 27400, "epoch": 73, "loss": 0.06883842498064041, "task_loss": 0.030696654692292213, "partitioner_loss": 0.029612286016345024, "running_macro_f1": 0.7957210986915144, "running_accuracy": 0.956171875, "lr": 4.248644328527995e-05, "codebook_loss": 0.034117940813302994, "codebook_perplexity": 87.52870178222656, "codebook_active": 263.0, "codebook_commit": 0.13647176325321198} | |
| {"step": 27450, "epoch": 73, "loss": 0.06540567427873611, "task_loss": 0.02452757954597473, "partitioner_loss": 0.031438179314136505, "running_macro_f1": 0.7876053663225192, "running_accuracy": 0.965703125, "lr": 4.248644328527995e-05, "codebook_loss": 0.03775966912508011, "codebook_perplexity": 140.09921264648438, "codebook_active": 344.0, "codebook_commit": 0.15103867650032043} | |
| {"step": 27500, "epoch": 73, "loss": 0.09364008158445358, "task_loss": 0.05190613493323326, "partitioner_loss": 0.032348234206438065, "running_macro_f1": 0.7678028659441393, "running_accuracy": 0.971796875, "lr": 4.248644328527995e-05, "codebook_loss": 0.03754284977912903, "codebook_perplexity": 163.99061584472656, "codebook_active": 291.0, "codebook_commit": 0.1501713991165161} | |
| {"step": 27550, "epoch": 73, "loss": 0.04898316413164139, "task_loss": 0.013380697928369045, "partitioner_loss": 0.02739562839269638, "running_macro_f1": 0.808511804062408, "running_accuracy": 0.9736533041027247, "lr": 4.248644328527995e-05, "codebook_loss": 0.03282734006643295, "codebook_perplexity": 123.27168273925781, "codebook_active": 299.0, "codebook_commit": 0.1313093602657318} | |
| {"epoch": 73, "split": "val", "val_macro_f1": 0.3685922920808322, "val_accuracy": 0.665890118423607} | |
| {"step": 27600, "epoch": 74, "loss": 0.09602849185466766, "task_loss": 0.05431295186281204, "partitioner_loss": 0.03179115802049637, "running_macro_f1": 0.7759097053523901, "running_accuracy": 0.96984375, "lr": 3.9691015596292226e-05, "codebook_loss": 0.03969752788543701, "codebook_perplexity": 172.17311096191406, "codebook_active": 356.0, "codebook_commit": 0.15879011154174805} | |
| {"step": 27650, "epoch": 74, "loss": 0.06573725491762161, "task_loss": 0.024559330195188522, "partitioner_loss": 0.030138462781906128, "running_macro_f1": 0.7887890202759205, "running_accuracy": 0.968984375, "lr": 3.9691015596292226e-05, "codebook_loss": 0.04415784776210785, "codebook_perplexity": 96.11602020263672, "codebook_active": 265.0, "codebook_commit": 0.1766313910484314} | |
| {"step": 27700, "epoch": 74, "loss": 0.07675562053918839, "task_loss": 0.03145214170217514, "partitioner_loss": 0.034442238509655, "running_macro_f1": 0.7847797731403992, "running_accuracy": 0.9690729721265268, "lr": 3.9691015596292226e-05, "codebook_loss": 0.04344497248530388, "codebook_perplexity": 190.5479278564453, "codebook_active": 351.0, "codebook_commit": 0.17377988994121552} | |
| {"step": 27750, "epoch": 74, "loss": 0.07737082988023758, "task_loss": 0.03628797456622124, "partitioner_loss": 0.03167365491390228, "running_macro_f1": 0.7630249486112015, "running_accuracy": 0.974140625, "lr": 3.9691015596292226e-05, "codebook_loss": 0.037636786699295044, "codebook_perplexity": 143.31349182128906, "codebook_active": 330.0, "codebook_commit": 0.15054714679718018} | |
| {"step": 27800, "epoch": 74, "loss": 0.1004369705915451, "task_loss": 0.05424511432647705, "partitioner_loss": 0.03594444692134857, "running_macro_f1": 0.8145826068006564, "running_accuracy": 0.963828125, "lr": 3.9691015596292226e-05, "codebook_loss": 0.040989622473716736, "codebook_perplexity": 156.1566925048828, "codebook_active": 329.0, "codebook_commit": 0.16395848989486694} | |
| {"step": 27850, "epoch": 74, "loss": 0.09572754800319672, "task_loss": 0.048931483179330826, "partitioner_loss": 0.03553903475403786, "running_macro_f1": 0.7760416358948066, "running_accuracy": 0.9575, "lr": 3.9691015596292226e-05, "codebook_loss": 0.04502810537815094, "codebook_perplexity": 182.74449157714844, "codebook_active": 349.0, "codebook_commit": 0.18011242151260376} | |
| {"step": 27900, "epoch": 74, "loss": 0.05624082311987877, "task_loss": 0.014803612604737282, "partitioner_loss": 0.032916538417339325, "running_macro_f1": 0.7905047322065699, "running_accuracy": 0.968046875, "lr": 3.9691015596292226e-05, "codebook_loss": 0.034082695841789246, "codebook_perplexity": 150.85438537597656, "codebook_active": 359.0, "codebook_commit": 0.13633078336715698} | |
| {"step": 27950, "epoch": 74, "loss": 0.05556335672736168, "task_loss": 0.015391074120998383, "partitioner_loss": 0.03181939572095871, "running_macro_f1": 0.7638938539193324, "running_accuracy": 0.9727734375, "lr": 3.9691015596292226e-05, "codebook_loss": 0.03341154381632805, "codebook_perplexity": 158.3888397216797, "codebook_active": 318.0, "codebook_commit": 0.1336461752653122} | |
| {"epoch": 74, "split": "val", "val_macro_f1": 0.39276310342047455, "val_accuracy": 0.6784119588429431} | |
| {"step": 28000, "epoch": 75, "loss": 0.09958618134260178, "task_loss": 0.05411659926176071, "partitioner_loss": 0.03858476132154465, "running_macro_f1": 0.8125720383667473, "running_accuracy": 0.9726171875, "lr": 3.697141767092981e-05, "codebook_loss": 0.02753927931189537, "codebook_perplexity": 193.23092651367188, "codebook_active": 395.0, "codebook_commit": 0.11015711724758148} | |
| {"step": 28050, "epoch": 75, "loss": 0.0778278112411499, "task_loss": 0.03463125601410866, "partitioner_loss": 0.03270693123340607, "running_macro_f1": 0.8142704460672422, "running_accuracy": 0.9731640625, "lr": 3.697141767092981e-05, "codebook_loss": 0.0419585183262825, "codebook_perplexity": 191.24417114257812, "codebook_active": 378.0, "codebook_commit": 0.16783407330513} | |
| {"step": 28100, "epoch": 75, "loss": 0.09143822640180588, "task_loss": 0.049914658069610596, "partitioner_loss": 0.03248728811740875, "running_macro_f1": 0.7991003398118923, "running_accuracy": 0.9709129345443157, "lr": 3.697141767092981e-05, "codebook_loss": 0.03614511340856552, "codebook_perplexity": 158.8087158203125, "codebook_active": 289.0, "codebook_commit": 0.14458045363426208} | |
| {"step": 28150, "epoch": 75, "loss": 0.08084842562675476, "task_loss": 0.039554983377456665, "partitioner_loss": 0.03083774819970131, "running_macro_f1": 0.7941412535377481, "running_accuracy": 0.9676953125, "lr": 3.697141767092981e-05, "codebook_loss": 0.04182279109954834, "codebook_perplexity": 146.79058837890625, "codebook_active": 327.0, "codebook_commit": 0.16729116439819336} | |
| {"step": 28200, "epoch": 75, "loss": 0.17939543724060059, "task_loss": 0.11737421154975891, "partitioner_loss": 0.04961983487010002, "running_macro_f1": 0.79448391032534, "running_accuracy": 0.9680859375, "lr": 3.697141767092981e-05, "codebook_loss": 0.04960551857948303, "codebook_perplexity": 42.60746383666992, "codebook_active": 123.0, "codebook_commit": 0.19842207431793213} | |
| {"step": 28250, "epoch": 75, "loss": 0.11019974201917648, "task_loss": 0.06677644699811935, "partitioner_loss": 0.03440489619970322, "running_macro_f1": 0.7596770553195548, "running_accuracy": 0.973515625, "lr": 3.697141767092981e-05, "codebook_loss": 0.03607359528541565, "codebook_perplexity": 122.92577362060547, "codebook_active": 254.0, "codebook_commit": 0.1442943811416626} | |
| {"step": 28300, "epoch": 75, "loss": 0.10035091638565063, "task_loss": 0.06315577775239944, "partitioner_loss": 0.0285983607172966, "running_macro_f1": 0.8127139896830868, "running_accuracy": 0.9727734375, "lr": 3.697141767092981e-05, "codebook_loss": 0.03438711166381836, "codebook_perplexity": 151.9434051513672, "codebook_active": 329.0, "codebook_commit": 0.13754844665527344} | |
| {"step": 28350, "epoch": 75, "loss": 0.0951649621129036, "task_loss": 0.048291049897670746, "partitioner_loss": 0.03504548594355583, "running_macro_f1": 0.753926347556106, "running_accuracy": 0.951484375, "lr": 3.697141767092981e-05, "codebook_loss": 0.04731371998786926, "codebook_perplexity": 155.93740844726562, "codebook_active": 345.0, "codebook_commit": 0.18925487995147705} | |
| {"epoch": 75, "split": "val", "val_macro_f1": 0.37362031363195436, "val_accuracy": 0.6748204232187924} | |
| {"step": 28400, "epoch": 76, "loss": 0.09865805506706238, "task_loss": 0.05553394556045532, "partitioner_loss": 0.03136628866195679, "running_macro_f1": 0.7707455058889512, "running_accuracy": 0.9618359375, "lr": 3.433038791377304e-05, "codebook_loss": 0.04703126847743988, "codebook_perplexity": 150.35462951660156, "codebook_active": 311.0, "codebook_commit": 0.18812507390975952} | |
| {"step": 28450, "epoch": 76, "loss": 0.08351711928844452, "task_loss": 0.03730551525950432, "partitioner_loss": 0.03479256108403206, "running_macro_f1": 0.7914747768746762, "running_accuracy": 0.97, "lr": 3.433038791377304e-05, "codebook_loss": 0.04567617550492287, "codebook_perplexity": 125.41064453125, "codebook_active": 331.0, "codebook_commit": 0.18270470201969147} | |
| {"step": 28500, "epoch": 76, "loss": 0.07195484638214111, "task_loss": 0.03186095505952835, "partitioner_loss": 0.02982594259083271, "running_macro_f1": 0.8043963777871582, "running_accuracy": 0.9712890625, "lr": 3.433038791377304e-05, "codebook_loss": 0.04107178747653961, "codebook_perplexity": 90.35713195800781, "codebook_active": 281.0, "codebook_commit": 0.16428714990615845} | |
| {"step": 28550, "epoch": 76, "loss": 0.04989832639694214, "task_loss": 0.00996217131614685, "partitioner_loss": 0.03018542192876339, "running_macro_f1": 0.819788767131565, "running_accuracy": 0.9714218603194488, "lr": 3.433038791377304e-05, "codebook_loss": 0.039002932608127594, "codebook_perplexity": 199.6314697265625, "codebook_active": 386.0, "codebook_commit": 0.15601173043251038} | |
| {"step": 28600, "epoch": 76, "loss": 0.07854413241147995, "task_loss": 0.03675717115402222, "partitioner_loss": 0.03181396424770355, "running_macro_f1": 0.7340619732472015, "running_accuracy": 0.9670703125, "lr": 3.433038791377304e-05, "codebook_loss": 0.03989199548959732, "codebook_perplexity": 154.31466674804688, "codebook_active": 238.0, "codebook_commit": 0.15956798195838928} | |
| {"step": 28650, "epoch": 76, "loss": 0.1337103545665741, "task_loss": 0.09059656411409378, "partitioner_loss": 0.03189467638731003, "running_macro_f1": 0.7910678067307292, "running_accuracy": 0.97703125, "lr": 3.433038791377304e-05, "codebook_loss": 0.04487643390893936, "codebook_perplexity": 115.61659240722656, "codebook_active": 326.0, "codebook_commit": 0.17950573563575745} | |
| {"step": 28700, "epoch": 76, "loss": 0.07182682305574417, "task_loss": 0.02300148829817772, "partitioner_loss": 0.040581490844488144, "running_macro_f1": 0.7832566921469246, "running_accuracy": 0.9726953125, "lr": 3.433038791377304e-05, "codebook_loss": 0.03297538682818413, "codebook_perplexity": 118.44813537597656, "codebook_active": 334.0, "codebook_commit": 0.1319015473127365} | |
| {"epoch": 76, "split": "val", "val_macro_f1": 0.37702138765737975, "val_accuracy": 0.6774412735391186} | |
| {"step": 28750, "epoch": 77, "loss": 0.10199062526226044, "task_loss": 0.05640536919236183, "partitioner_loss": 0.035272687673568726, "running_macro_f1": 0.7774388250461767, "running_accuracy": 0.972109375, "lr": 3.177058561791693e-05, "codebook_loss": 0.04125029593706131, "codebook_perplexity": 138.2405242919922, "codebook_active": 291.0, "codebook_commit": 0.16500118374824524} | |
| {"step": 28800, "epoch": 77, "loss": 0.06576167047023773, "task_loss": 0.021316170692443848, "partitioner_loss": 0.03542651981115341, "running_macro_f1": 0.7708244066392412, "running_accuracy": 0.9720703125, "lr": 3.177058561791693e-05, "codebook_loss": 0.03607592731714249, "codebook_perplexity": 180.25193786621094, "codebook_active": 364.0, "codebook_commit": 0.14430370926856995} | |
| {"step": 28850, "epoch": 77, "loss": 0.14182628691196442, "task_loss": 0.10030939429998398, "partitioner_loss": 0.03208941966295242, "running_macro_f1": 0.7860201276655429, "running_accuracy": 0.9746875, "lr": 3.177058561791693e-05, "codebook_loss": 0.03770986944437027, "codebook_perplexity": 189.15939331054688, "codebook_active": 375.0, "codebook_commit": 0.15083947777748108} | |
| {"step": 28900, "epoch": 77, "loss": 0.07051317393779755, "task_loss": 0.026966679841279984, "partitioner_loss": 0.03435276448726654, "running_macro_f1": 0.7658458007418896, "running_accuracy": 0.9590234375, "lr": 3.177058561791693e-05, "codebook_loss": 0.036774925887584686, "codebook_perplexity": 145.18284606933594, "codebook_active": 296.0, "codebook_commit": 0.14709970355033875} | |
| {"step": 28950, "epoch": 77, "loss": 0.10578689724206924, "task_loss": 0.06755794584751129, "partitioner_loss": 0.030817512422800064, "running_macro_f1": 0.8007841306528978, "running_accuracy": 0.970090823676793, "lr": 3.177058561791693e-05, "codebook_loss": 0.02964576706290245, "codebook_perplexity": 186.94241333007812, "codebook_active": 334.0, "codebook_commit": 0.1185830682516098} | |
| {"step": 29000, "epoch": 77, "loss": 0.12717437744140625, "task_loss": 0.07305745780467987, "partitioner_loss": 0.043691497296094894, "running_macro_f1": 0.8113295893386765, "running_accuracy": 0.9709765625, "lr": 3.177058561791693e-05, "codebook_loss": 0.04170167073607445, "codebook_perplexity": 106.38581848144531, "codebook_active": 211.0, "codebook_commit": 0.1668066829442978} | |
| {"step": 29050, "epoch": 77, "loss": 0.08642776310443878, "task_loss": 0.04010403901338577, "partitioner_loss": 0.035803355276584625, "running_macro_f1": 0.819068566372439, "running_accuracy": 0.972265625, "lr": 3.177058561791693e-05, "codebook_loss": 0.04208146408200264, "codebook_perplexity": 202.51441955566406, "codebook_active": 375.0, "codebook_commit": 0.16832585632801056} | |
| {"step": 29100, "epoch": 77, "loss": 0.12076435983181, "task_loss": 0.07534321397542953, "partitioner_loss": 0.034190524369478226, "running_macro_f1": 0.8062327509342078, "running_accuracy": 0.969921875, "lr": 3.177058561791693e-05, "codebook_loss": 0.04492245614528656, "codebook_perplexity": 182.870361328125, "codebook_active": 366.0, "codebook_commit": 0.17968982458114624} | |
| {"epoch": 77, "split": "val", "val_macro_f1": 0.3888514240464535, "val_accuracy": 0.6919044845661037} | |
| {"step": 29150, "epoch": 78, "loss": 0.06632274389266968, "task_loss": 0.022516420111060143, "partitioner_loss": 0.03146274387836456, "running_macro_f1": 0.7953872430513937, "running_accuracy": 0.9723046875, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04937431588768959, "codebook_perplexity": 137.2919464111328, "codebook_active": 286.0, "codebook_commit": 0.19749726355075836} | |
| {"step": 29200, "epoch": 78, "loss": 0.09419332444667816, "task_loss": 0.04892444610595703, "partitioner_loss": 0.034721799194812775, "running_macro_f1": 0.8039788061741322, "running_accuracy": 0.9721875, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04218831658363342, "codebook_perplexity": 197.33900451660156, "codebook_active": 335.0, "codebook_commit": 0.1687532663345337} | |
| {"step": 29250, "epoch": 78, "loss": 0.11890369653701782, "task_loss": 0.06947484612464905, "partitioner_loss": 0.03825710713863373, "running_macro_f1": 0.8069601487959881, "running_accuracy": 0.9755859375, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04468698799610138, "codebook_perplexity": 131.9828338623047, "codebook_active": 219.0, "codebook_commit": 0.17874795198440552} | |
| {"step": 29300, "epoch": 78, "loss": 0.06106724217534065, "task_loss": 0.021808583289384842, "partitioner_loss": 0.03252070024609566, "running_macro_f1": 0.788431116444813, "running_accuracy": 0.9735546875, "lr": 2.9294588287288215e-05, "codebook_loss": 0.026951830834150314, "codebook_perplexity": 165.96632385253906, "codebook_active": 401.0, "codebook_commit": 0.10780732333660126} | |
| {"step": 29350, "epoch": 78, "loss": 0.10493254661560059, "task_loss": 0.061222225427627563, "partitioner_loss": 0.033148735761642456, "running_macro_f1": 0.7914112159665264, "running_accuracy": 0.9732421875, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04224632680416107, "codebook_perplexity": 206.3365936279297, "codebook_active": 342.0, "codebook_commit": 0.1689853072166443} | |
| {"step": 29400, "epoch": 78, "loss": 0.06905454397201538, "task_loss": 0.02948877587914467, "partitioner_loss": 0.029409587383270264, "running_macro_f1": 0.7720536419879231, "running_accuracy": 0.9571719386157219, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04062473401427269, "codebook_perplexity": 181.52635192871094, "codebook_active": 361.0, "codebook_commit": 0.16249893605709076} | |
| {"step": 29450, "epoch": 78, "loss": 0.07653948664665222, "task_loss": 0.03480291739106178, "partitioner_loss": 0.03163677453994751, "running_macro_f1": 0.8014538689569511, "running_accuracy": 0.9737890625, "lr": 2.9294588287288215e-05, "codebook_loss": 0.04039920121431351, "codebook_perplexity": 131.53756713867188, "codebook_active": 300.0, "codebook_commit": 0.16159680485725403} | |
| {"epoch": 78, "split": "val", "val_macro_f1": 0.3849058421830843, "val_accuracy": 0.6996699669966997} | |
| {"step": 29500, "epoch": 79, "loss": 0.081392802298069, "task_loss": 0.0356108620762825, "partitioner_loss": 0.03586660325527191, "running_macro_f1": 0.7891687617283201, "running_accuracy": 0.967265625, "lr": 2.6904889041317543e-05, "codebook_loss": 0.039661359041929245, "codebook_perplexity": 189.86180114746094, "codebook_active": 410.0, "codebook_commit": 0.15864543616771698} | |
| {"step": 29550, "epoch": 79, "loss": 0.05244531109929085, "task_loss": 0.012871475890278816, "partitioner_loss": 0.0306378286331892, "running_macro_f1": 0.7740138242969135, "running_accuracy": 0.9726171875, "lr": 2.6904889041317543e-05, "codebook_loss": 0.03574402257800102, "codebook_perplexity": 169.60592651367188, "codebook_active": 338.0, "codebook_commit": 0.1429760903120041} | |
| {"step": 29600, "epoch": 79, "loss": 0.0625302866101265, "task_loss": 0.023100515827536583, "partitioner_loss": 0.029895372688770294, "running_macro_f1": 0.8124120303579907, "running_accuracy": 0.9726171875, "lr": 2.6904889041317543e-05, "codebook_loss": 0.03813757747411728, "codebook_perplexity": 203.21185302734375, "codebook_active": 371.0, "codebook_commit": 0.15255030989646912} | |
| {"step": 29650, "epoch": 79, "loss": 0.11547990143299103, "task_loss": 0.06734663993120193, "partitioner_loss": 0.03705012798309326, "running_macro_f1": 0.814281697083371, "running_accuracy": 0.976640625, "lr": 2.6904889041317543e-05, "codebook_loss": 0.04433254152536392, "codebook_perplexity": 174.5690155029297, "codebook_active": 343.0, "codebook_commit": 0.1773301661014557} | |
| {"step": 29700, "epoch": 79, "loss": 0.159096360206604, "task_loss": 0.11121921986341476, "partitioner_loss": 0.03461431711912155, "running_macro_f1": 0.7892211364759781, "running_accuracy": 0.9698828125, "lr": 2.6904889041317543e-05, "codebook_loss": 0.05305129289627075, "codebook_perplexity": 151.02401733398438, "codebook_active": 266.0, "codebook_commit": 0.212205171585083} | |
| {"step": 29750, "epoch": 79, "loss": 0.10123618692159653, "task_loss": 0.053477346897125244, "partitioner_loss": 0.03632422909140587, "running_macro_f1": 0.81710359170027, "running_accuracy": 0.9699609375, "lr": 2.6904889041317543e-05, "codebook_loss": 0.04573844000697136, "codebook_perplexity": 164.7357177734375, "codebook_active": 339.0, "codebook_commit": 0.18295376002788544} | |
| {"step": 29800, "epoch": 79, "loss": 0.05600447580218315, "task_loss": 0.014489911496639252, "partitioner_loss": 0.030701979994773865, "running_macro_f1": 0.78337617145899, "running_accuracy": 0.9728515625, "lr": 2.6904889041317543e-05, "codebook_loss": 0.04325033351778984, "codebook_perplexity": 205.39952087402344, "codebook_active": 355.0, "codebook_commit": 0.17300133407115936} | |
| {"step": 29850, "epoch": 79, "loss": 0.108648382127285, "task_loss": 0.06502004712820053, "partitioner_loss": 0.03219688683748245, "running_macro_f1": 0.7600250045546474, "running_accuracy": 0.9613216410898842, "lr": 2.6904889041317543e-05, "codebook_loss": 0.04572579264640808, "codebook_perplexity": 159.7154541015625, "codebook_active": 321.0, "codebook_commit": 0.18290317058563232} | |
| {"epoch": 79, "split": "val", "val_macro_f1": 0.3964375103789099, "val_accuracy": 0.6953989516598719} | |
| {"step": 29900, "epoch": 80, "loss": 0.06488420069217682, "task_loss": 0.023166486993432045, "partitioner_loss": 0.03223082423210144, "running_macro_f1": 0.8044911407907583, "running_accuracy": 0.9586328125, "lr": 2.4603894104579462e-05, "codebook_loss": 0.03794755041599274, "codebook_perplexity": 223.3365936279297, "codebook_active": 385.0, "codebook_commit": 0.15179020166397095} | |
| {"step": 29950, "epoch": 80, "loss": 0.10658662021160126, "task_loss": 0.06443256884813309, "partitioner_loss": 0.03286997228860855, "running_macro_f1": 0.7746170601936843, "running_accuracy": 0.9728125, "lr": 2.4603894104579462e-05, "codebook_loss": 0.03713630884885788, "codebook_perplexity": 181.69468688964844, "codebook_active": 337.0, "codebook_commit": 0.14854523539543152} | |
| {"step": 30000, "epoch": 80, "loss": 0.09167374670505524, "task_loss": 0.05053550377488136, "partitioner_loss": 0.03179111331701279, "running_macro_f1": 0.7999477685101243, "running_accuracy": 0.96859375, "lr": 2.4603894104579462e-05, "codebook_loss": 0.03738851472735405, "codebook_perplexity": 148.9357147216797, "codebook_active": 313.0, "codebook_commit": 0.1495540589094162} | |
| {"step": 30050, "epoch": 80, "loss": 0.0935983955860138, "task_loss": 0.051060035824775696, "partitioner_loss": 0.03194791078567505, "running_macro_f1": 0.8157571861203501, "running_accuracy": 0.973203125, "lr": 2.4603894104579462e-05, "codebook_loss": 0.04236181080341339, "codebook_perplexity": 196.1840362548828, "codebook_active": 351.0, "codebook_commit": 0.16944724321365356} | |
| {"step": 30100, "epoch": 80, "loss": 0.08289533108472824, "task_loss": 0.04217919334769249, "partitioner_loss": 0.02985454350709915, "running_macro_f1": 0.8002195012190578, "running_accuracy": 0.976484375, "lr": 2.4603894104579462e-05, "codebook_loss": 0.043446384370326996, "codebook_perplexity": 193.9376220703125, "codebook_active": 373.0, "codebook_commit": 0.17378553748130798} | |
| {"step": 30150, "epoch": 80, "loss": 0.0677717924118042, "task_loss": 0.02373606152832508, "partitioner_loss": 0.035344578325748444, "running_macro_f1": 0.7869990887165829, "running_accuracy": 0.9651973066082055, "lr": 2.4603894104579462e-05, "codebook_loss": 0.0347646102309227, "codebook_perplexity": 173.33758544921875, "codebook_active": 368.0, "codebook_commit": 0.1390584409236908} | |
| {"step": 30200, "epoch": 80, "loss": 0.060437388718128204, "task_loss": 0.020264187827706337, "partitioner_loss": 0.030332067981362343, "running_macro_f1": 0.7790272151261322, "running_accuracy": 0.9719140625, "lr": 2.4603894104579462e-05, "codebook_loss": 0.0393645316362381, "codebook_perplexity": 188.72476196289062, "codebook_active": 338.0, "codebook_commit": 0.1574581265449524} | |
| {"epoch": 80, "split": "val", "val_macro_f1": 0.4007275194950139, "val_accuracy": 0.7218986604542807} | |
| {"step": 30250, "epoch": 81, "loss": 0.07940956950187683, "task_loss": 0.03878229111433029, "partitioner_loss": 0.03138913959264755, "running_macro_f1": 0.7842581992387577, "running_accuracy": 0.9740234375, "lr": 2.2393920383928258e-05, "codebook_loss": 0.036952562630176544, "codebook_perplexity": 188.97511291503906, "codebook_active": 352.0, "codebook_commit": 0.14781025052070618} | |
| {"step": 30300, "epoch": 81, "loss": 0.06397420912981033, "task_loss": 0.02464894764125347, "partitioner_loss": 0.02901485748589039, "running_macro_f1": 0.7619521387032737, "running_accuracy": 0.960078125, "lr": 2.2393920383928258e-05, "codebook_loss": 0.04124161973595619, "codebook_perplexity": 179.12606811523438, "codebook_active": 329.0, "codebook_commit": 0.16496647894382477} | |
| {"step": 30350, "epoch": 81, "loss": 0.06827562302350998, "task_loss": 0.025572216138243675, "partitioner_loss": 0.03188970685005188, "running_macro_f1": 0.8231541757425375, "running_accuracy": 0.97203125, "lr": 2.2393920383928258e-05, "codebook_loss": 0.0432547926902771, "codebook_perplexity": 189.5396728515625, "codebook_active": 392.0, "codebook_commit": 0.1730191707611084} | |
| {"step": 30400, "epoch": 81, "loss": 0.044630251824855804, "task_loss": 0.006035613361746073, "partitioner_loss": 0.02837635949254036, "running_macro_f1": 0.797598433253577, "running_accuracy": 0.9726953125, "lr": 2.2393920383928258e-05, "codebook_loss": 0.04087311029434204, "codebook_perplexity": 202.2862548828125, "codebook_active": 389.0, "codebook_commit": 0.16349244117736816} | |
| {"step": 30450, "epoch": 81, "loss": 0.05549250543117523, "task_loss": 0.014597310684621334, "partitioner_loss": 0.031018566340208054, "running_macro_f1": 0.7817699300015192, "running_accuracy": 0.9726354525524585, "lr": 2.2393920383928258e-05, "codebook_loss": 0.03950650990009308, "codebook_perplexity": 147.1190948486328, "codebook_active": 253.0, "codebook_commit": 0.15802603960037231} | |
| {"step": 30500, "epoch": 81, "loss": 0.07377082109451294, "task_loss": 0.03114205040037632, "partitioner_loss": 0.03284968063235283, "running_macro_f1": 0.8047390147917431, "running_accuracy": 0.9755859375, "lr": 2.2393920383928258e-05, "codebook_loss": 0.03911634534597397, "codebook_perplexity": 184.11077880859375, "codebook_active": 344.0, "codebook_commit": 0.15646538138389587} | |
| {"step": 30550, "epoch": 81, "loss": 0.07203853875398636, "task_loss": 0.03303293511271477, "partitioner_loss": 0.030796948820352554, "running_macro_f1": 0.7601228918018629, "running_accuracy": 0.9690625, "lr": 2.2393920383928258e-05, "codebook_loss": 0.03283460810780525, "codebook_perplexity": 235.06582641601562, "codebook_active": 409.0, "codebook_commit": 0.131338432431221} | |
| {"step": 30600, "epoch": 81, "loss": 0.056507520377635956, "task_loss": 0.013304708525538445, "partitioner_loss": 0.03282277658581734, "running_macro_f1": 0.7897767274743138, "running_accuracy": 0.9744140625, "lr": 2.2393920383928258e-05, "codebook_loss": 0.0415201410651207, "codebook_perplexity": 179.8636016845703, "codebook_active": 303.0, "codebook_commit": 0.1660805642604828} | |
| {"epoch": 81, "split": "val", "val_macro_f1": 0.3929731040986511, "val_accuracy": 0.6957872257814016} | |
| {"step": 30650, "epoch": 82, "loss": 0.06650412827730179, "task_loss": 0.026395903900265694, "partitioner_loss": 0.031441062688827515, "running_macro_f1": 0.7806260656928099, "running_accuracy": 0.975546875, "lr": 2.027719313556924e-05, "codebook_loss": 0.034668661653995514, "codebook_perplexity": 201.0223846435547, "codebook_active": 340.0, "codebook_commit": 0.13867464661598206} | |
| {"step": 30700, "epoch": 82, "loss": 0.12284374237060547, "task_loss": 0.08165428042411804, "partitioner_loss": 0.030685745179653168, "running_macro_f1": 0.7899895933707236, "running_accuracy": 0.974296875, "lr": 2.027719313556924e-05, "codebook_loss": 0.04201486334204674, "codebook_perplexity": 195.33506774902344, "codebook_active": 364.0, "codebook_commit": 0.16805945336818695} | |
| {"step": 30750, "epoch": 82, "loss": 0.08037960529327393, "task_loss": 0.03723692521452904, "partitioner_loss": 0.032020196318626404, "running_macro_f1": 0.7805542018084058, "running_accuracy": 0.9734375, "lr": 2.027719313556924e-05, "codebook_loss": 0.044489920139312744, "codebook_perplexity": 145.08193969726562, "codebook_active": 252.0, "codebook_commit": 0.17795968055725098} | |
| {"step": 30800, "epoch": 82, "loss": 0.08465221524238586, "task_loss": 0.04215433448553085, "partitioner_loss": 0.03165373578667641, "running_macro_f1": 0.803809039079322, "running_accuracy": 0.9686328125, "lr": 2.027719313556924e-05, "codebook_loss": 0.04337655007839203, "codebook_perplexity": 223.29762268066406, "codebook_active": 381.0, "codebook_commit": 0.17350620031356812} | |
| {"step": 30850, "epoch": 82, "loss": 0.08634340018033981, "task_loss": 0.04598430544137955, "partitioner_loss": 0.031221527606248856, "running_macro_f1": 0.7804147586435536, "running_accuracy": 0.97390625, "lr": 2.027719313556924e-05, "codebook_loss": 0.03655024617910385, "codebook_perplexity": 145.2112274169922, "codebook_active": 327.0, "codebook_commit": 0.1462009847164154} | |
| {"step": 30900, "epoch": 82, "loss": 0.08444530516862869, "task_loss": 0.04340985417366028, "partitioner_loss": 0.03050980344414711, "running_macro_f1": 0.797114113940329, "running_accuracy": 0.9772549326652051, "lr": 2.027719313556924e-05, "codebook_loss": 0.042102616280317307, "codebook_perplexity": 177.4227752685547, "codebook_active": 355.0, "codebook_commit": 0.16841046512126923} | |
| {"step": 30950, "epoch": 82, "loss": 0.08262459188699722, "task_loss": 0.04018031060695648, "partitioner_loss": 0.03318271040916443, "running_macro_f1": 0.8075026697753073, "running_accuracy": 0.97171875, "lr": 2.027719313556924e-05, "codebook_loss": 0.037046290934085846, "codebook_perplexity": 129.95489501953125, "codebook_active": 248.0, "codebook_commit": 0.14818516373634338} | |
| {"epoch": 82, "split": "val", "val_macro_f1": 0.3941459767002838, "val_accuracy": 0.698213939040963} | |
| {"step": 31000, "epoch": 83, "loss": 0.07165646553039551, "task_loss": 0.020328909158706665, "partitioner_loss": 0.037873025983572006, "running_macro_f1": 0.7993418022728025, "running_accuracy": 0.9634375, "lr": 1.825584372441415e-05, "codebook_loss": 0.05381812900304794, "codebook_perplexity": 127.3727035522461, "codebook_active": 260.0, "codebook_commit": 0.21527251601219177} | |
| {"step": 31050, "epoch": 83, "loss": 0.08585117012262344, "task_loss": 0.04108348861336708, "partitioner_loss": 0.032815538346767426, "running_macro_f1": 0.7565325425295886, "running_accuracy": 0.9737890625, "lr": 1.825584372441415e-05, "codebook_loss": 0.04780855402350426, "codebook_perplexity": 124.99881744384766, "codebook_active": 330.0, "codebook_commit": 0.19123421609401703} | |
| {"step": 31100, "epoch": 83, "loss": 0.061565618962049484, "task_loss": 0.021399885416030884, "partitioner_loss": 0.030399272218346596, "running_macro_f1": 0.8046262612576173, "running_accuracy": 0.9763671875, "lr": 1.825584372441415e-05, "codebook_loss": 0.03906584903597832, "codebook_perplexity": 213.65921020507812, "codebook_active": 379.0, "codebook_commit": 0.15626339614391327} | |
| {"step": 31150, "epoch": 83, "loss": 0.09866392612457275, "task_loss": 0.05638337507843971, "partitioner_loss": 0.031522542238235474, "running_macro_f1": 0.8120395672843198, "running_accuracy": 0.974765625, "lr": 1.825584372441415e-05, "codebook_loss": 0.043032050132751465, "codebook_perplexity": 160.11395263671875, "codebook_active": 314.0, "codebook_commit": 0.17212820053100586} | |
| {"step": 31200, "epoch": 83, "loss": 0.0818706676363945, "task_loss": 0.03905491158366203, "partitioner_loss": 0.03133983165025711, "running_macro_f1": 0.7969203784736079, "running_accuracy": 0.9740447854682117, "lr": 1.825584372441415e-05, "codebook_loss": 0.04590371623635292, "codebook_perplexity": 124.36338806152344, "codebook_active": 270.0, "codebook_commit": 0.18361486494541168} | |
| {"step": 31250, "epoch": 83, "loss": 0.06260959804058075, "task_loss": 0.02517717517912388, "partitioner_loss": 0.03106185793876648, "running_macro_f1": 0.783374935868704, "running_accuracy": 0.9755078125, "lr": 1.825584372441415e-05, "codebook_loss": 0.025482269003987312, "codebook_perplexity": 177.4054412841797, "codebook_active": 303.0, "codebook_commit": 0.10192907601594925} | |
| {"step": 31300, "epoch": 83, "loss": 0.042186472564935684, "task_loss": 0.006214505527168512, "partitioner_loss": 0.027555765584111214, "running_macro_f1": 0.8115541283234584, "running_accuracy": 0.977734375, "lr": 1.825584372441415e-05, "codebook_loss": 0.03366480767726898, "codebook_perplexity": 137.34634399414062, "codebook_active": 331.0, "codebook_commit": 0.13465923070907593} | |
| {"step": 31350, "epoch": 83, "loss": 0.07281454652547836, "task_loss": 0.03467007726430893, "partitioner_loss": 0.028634920716285706, "running_macro_f1": 0.7624827149336015, "running_accuracy": 0.9469921875, "lr": 1.825584372441415e-05, "codebook_loss": 0.03803820163011551, "codebook_perplexity": 150.9868621826172, "codebook_active": 338.0, "codebook_commit": 0.15215280652046204} | |
| {"epoch": 83, "split": "val", "val_macro_f1": 0.3795577241551294, "val_accuracy": 0.6909337992622792} | |
| {"step": 31400, "epoch": 84, "loss": 0.07694324851036072, "task_loss": 0.035998668521642685, "partitioner_loss": 0.03148452937602997, "running_macro_f1": 0.8183114085824797, "running_accuracy": 0.97484375, "lr": 1.6331907477977637e-05, "codebook_loss": 0.03784019500017166, "codebook_perplexity": 187.27923583984375, "codebook_active": 354.0, "codebook_commit": 0.15136078000068665} | |
| {"step": 31450, "epoch": 84, "loss": 0.07296231389045715, "task_loss": 0.02946402132511139, "partitioner_loss": 0.033536188304424286, "running_macro_f1": 0.819203281180985, "running_accuracy": 0.974375, "lr": 1.6331907477977637e-05, "codebook_loss": 0.03984840214252472, "codebook_perplexity": 168.96604919433594, "codebook_active": 267.0, "codebook_commit": 0.15939360857009888} | |
| {"step": 31500, "epoch": 84, "loss": 0.06492830067873001, "task_loss": 0.02361663617193699, "partitioner_loss": 0.03113584965467453, "running_macro_f1": 0.782096094542684, "running_accuracy": 0.9552734375, "lr": 1.6331907477977637e-05, "codebook_loss": 0.040703266859054565, "codebook_perplexity": 164.41529846191406, "codebook_active": 281.0, "codebook_commit": 0.16281306743621826} | |
| {"step": 31550, "epoch": 84, "loss": 0.17931117117404938, "task_loss": 0.12406405061483383, "partitioner_loss": 0.04540001600980759, "running_macro_f1": 0.7705648895479835, "running_accuracy": 0.969375, "lr": 1.6331907477977637e-05, "codebook_loss": 0.03938840702176094, "codebook_perplexity": 47.64581298828125, "codebook_active": 152.0, "codebook_commit": 0.15755362808704376} | |
| {"step": 31600, "epoch": 84, "loss": 0.09017784148454666, "task_loss": 0.04387776181101799, "partitioner_loss": 0.036055292934179306, "running_macro_f1": 0.8054810789945017, "running_accuracy": 0.9765625, "lr": 1.6331907477977637e-05, "codebook_loss": 0.04097915440797806, "codebook_perplexity": 170.5289306640625, "codebook_active": 308.0, "codebook_commit": 0.16391661763191223} | |
| {"step": 31650, "epoch": 84, "loss": 0.11387436091899872, "task_loss": 0.07253608852624893, "partitioner_loss": 0.03264833986759186, "running_macro_f1": 0.7916583090555717, "running_accuracy": 0.9708203125, "lr": 1.6331907477977637e-05, "codebook_loss": 0.03475974500179291, "codebook_perplexity": 206.19259643554688, "codebook_active": 389.0, "codebook_commit": 0.13903898000717163} | |
| {"step": 31700, "epoch": 84, "loss": 0.07665500044822693, "task_loss": 0.024096714332699776, "partitioner_loss": 0.039086971431970596, "running_macro_f1": 0.823693252168457, "running_accuracy": 0.9718133416849358, "lr": 1.6331907477977637e-05, "codebook_loss": 0.05388525873422623, "codebook_perplexity": 116.83026885986328, "codebook_active": 258.0, "codebook_commit": 0.2155410349369049} | |
| {"step": 31750, "epoch": 84, "loss": 0.06359496712684631, "task_loss": 0.020737014710903168, "partitioner_loss": 0.03375890478491783, "running_macro_f1": 0.7800734346326119, "running_accuracy": 0.9745703125, "lr": 1.6331907477977637e-05, "codebook_loss": 0.036396175622940063, "codebook_perplexity": 117.42626190185547, "codebook_active": 234.0, "codebook_commit": 0.14558470249176025} | |
| {"epoch": 84, "split": "val", "val_macro_f1": 0.3710028804732319, "val_accuracy": 0.6744321490972627} | |
| {"step": 31800, "epoch": 85, "loss": 0.049855589866638184, "task_loss": 0.010910219512879848, "partitioner_loss": 0.028926346451044083, "running_macro_f1": 0.7934426069441932, "running_accuracy": 0.971875, "lr": 1.4507321636974733e-05, "codebook_loss": 0.04007609933614731, "codebook_perplexity": 199.796875, "codebook_active": 380.0, "codebook_commit": 0.16030439734458923} | |
| {"step": 31850, "epoch": 85, "loss": 0.07473791390657425, "task_loss": 0.03095649741590023, "partitioner_loss": 0.03387428820133209, "running_macro_f1": 0.7972582669459419, "running_accuracy": 0.9756640625, "lr": 1.4507321636974733e-05, "codebook_loss": 0.039628516882658005, "codebook_perplexity": 159.3516082763672, "codebook_active": 344.0, "codebook_commit": 0.15851406753063202} | |
| {"step": 31900, "epoch": 85, "loss": 0.0869835689663887, "task_loss": 0.04011428356170654, "partitioner_loss": 0.03477758541703224, "running_macro_f1": 0.7993598370697869, "running_accuracy": 0.977265625, "lr": 1.4507321636974733e-05, "codebook_loss": 0.048366814851760864, "codebook_perplexity": 148.8572540283203, "codebook_active": 291.0, "codebook_commit": 0.19346725940704346} | |
| {"step": 31950, "epoch": 85, "loss": 0.0642213523387909, "task_loss": 0.021103691309690475, "partitioner_loss": 0.032478898763656616, "running_macro_f1": 0.7997538970959476, "running_accuracy": 0.975703125, "lr": 1.4507321636974733e-05, "codebook_loss": 0.04255504161119461, "codebook_perplexity": 160.6833038330078, "codebook_active": 302.0, "codebook_commit": 0.17022016644477844} | |
| {"step": 32000, "epoch": 85, "loss": 0.06143898516893387, "task_loss": 0.021399110555648804, "partitioner_loss": 0.03162487968802452, "running_macro_f1": 0.7939326958475453, "running_accuracy": 0.9612109375, "lr": 1.4507321636974733e-05, "codebook_loss": 0.03365997225046158, "codebook_perplexity": 137.08587646484375, "codebook_active": 311.0, "codebook_commit": 0.1346398890018463} | |
| {"step": 32050, "epoch": 85, "loss": 0.07499196380376816, "task_loss": 0.03257822245359421, "partitioner_loss": 0.032392725348472595, "running_macro_f1": 0.7923703323581546, "running_accuracy": 0.9691796875, "lr": 1.4507321636974733e-05, "codebook_loss": 0.040084075182676315, "codebook_perplexity": 163.16513061523438, "codebook_active": 333.0, "codebook_commit": 0.16033630073070526} | |
| {"step": 32100, "epoch": 85, "loss": 0.16406801342964172, "task_loss": 0.11228185892105103, "partitioner_loss": 0.04369407892227173, "running_macro_f1": 0.7801706346288229, "running_accuracy": 0.9702865643595365, "lr": 1.4507321636974733e-05, "codebook_loss": 0.032368309795856476, "codebook_perplexity": 60.200897216796875, "codebook_active": 159.0, "codebook_commit": 0.1294732391834259} | |
| {"epoch": 85, "split": "val", "val_macro_f1": 0.3801928148006681, "val_accuracy": 0.6879246748204232} | |
| {"step": 32150, "epoch": 86, "loss": 0.09579524397850037, "task_loss": 0.052416570484638214, "partitioner_loss": 0.03333165869116783, "running_macro_f1": 0.8100641501461505, "running_accuracy": 0.9728125, "lr": 1.2783923404683813e-05, "codebook_loss": 0.04018807411193848, "codebook_perplexity": 170.1470184326172, "codebook_active": 302.0, "codebook_commit": 0.1607522964477539} | |
| {"step": 32200, "epoch": 86, "loss": 0.0725996345281601, "task_loss": 0.02807622030377388, "partitioner_loss": 0.034367505460977554, "running_macro_f1": 0.7913328202549921, "running_accuracy": 0.9662890625, "lr": 1.2783923404683813e-05, "codebook_loss": 0.04062364995479584, "codebook_perplexity": 175.89405822753906, "codebook_active": 369.0, "codebook_commit": 0.16249459981918335} | |
| {"step": 32250, "epoch": 86, "loss": 0.0649881437420845, "task_loss": 0.028126336634159088, "partitioner_loss": 0.030100777745246887, "running_macro_f1": 0.8196037204114075, "running_accuracy": 0.9759765625, "lr": 1.2783923404683813e-05, "codebook_loss": 0.027044108137488365, "codebook_perplexity": 169.07614135742188, "codebook_active": 363.0, "codebook_commit": 0.10817643254995346} | |
| {"step": 32300, "epoch": 86, "loss": 0.3574124574661255, "task_loss": 0.31110936403274536, "partitioner_loss": 0.034071579575538635, "running_macro_f1": 0.7919878795531954, "running_accuracy": 0.9765894143438772, "lr": 1.2783923404683813e-05, "codebook_loss": 0.048926059156656265, "codebook_perplexity": 135.70596313476562, "codebook_active": 353.0, "codebook_commit": 0.19570423662662506} | |
| {"step": 32350, "epoch": 86, "loss": 1.1788465976715088, "task_loss": 1.1014153957366943, "partitioner_loss": 0.06799875199794769, "running_macro_f1": 0.7807994074252025, "running_accuracy": 0.960234375, "lr": 1.2783923404683813e-05, "codebook_loss": 0.037729810923337936, "codebook_perplexity": 23.657695770263672, "codebook_active": 94.0, "codebook_commit": 0.15091924369335175} | |
| {"step": 32400, "epoch": 86, "loss": 0.06344419717788696, "task_loss": 0.018277084454894066, "partitioner_loss": 0.033633582293987274, "running_macro_f1": 0.8085502895243283, "running_accuracy": 0.9746484375, "lr": 1.2783923404683813e-05, "codebook_loss": 0.0461340993642807, "codebook_perplexity": 176.44712829589844, "codebook_active": 351.0, "codebook_commit": 0.1845363974571228} | |
| {"step": 32450, "epoch": 86, "loss": 0.05927194654941559, "task_loss": 0.018977705389261246, "partitioner_loss": 0.03156616911292076, "running_macro_f1": 0.8133505030232443, "running_accuracy": 0.974453125, "lr": 1.2783923404683813e-05, "codebook_loss": 0.03491228073835373, "codebook_perplexity": 142.33897399902344, "codebook_active": 359.0, "codebook_commit": 0.13964912295341492} | |
| {"step": 32500, "epoch": 86, "loss": 0.05450897663831711, "task_loss": 0.01603631116449833, "partitioner_loss": 0.02948291227221489, "running_macro_f1": 0.805283251079463, "running_accuracy": 0.97578125, "lr": 1.2783923404683813e-05, "codebook_loss": 0.03595900535583496, "codebook_perplexity": 156.8944854736328, "codebook_active": 341.0, "codebook_commit": 0.14383602142333984} | |
| {"epoch": 86, "split": "val", "val_macro_f1": 0.3774535553178259, "val_accuracy": 0.6636575422248108} | |
| {"step": 32550, "epoch": 87, "loss": 0.0978333130478859, "task_loss": 0.04409312829375267, "partitioner_loss": 0.043081074953079224, "running_macro_f1": 0.7720911593598166, "running_accuracy": 0.9747265625, "lr": 1.1163448097038578e-05, "codebook_loss": 0.04263642057776451, "codebook_perplexity": 69.20116424560547, "codebook_active": 158.0, "codebook_commit": 0.17054568231105804} | |
| {"step": 32600, "epoch": 87, "loss": 0.09113665670156479, "task_loss": 0.04928736388683319, "partitioner_loss": 0.030340634286403656, "running_macro_f1": 0.8138136657209707, "running_accuracy": 0.976354525524585, "lr": 1.1163448097038578e-05, "codebook_loss": 0.04603463411331177, "codebook_perplexity": 115.20780181884766, "codebook_active": 322.0, "codebook_commit": 0.18413853645324707} | |
| {"step": 32650, "epoch": 87, "loss": 0.23805806040763855, "task_loss": 0.17043441534042358, "partitioner_loss": 0.057124942541122437, "running_macro_f1": 0.7857532083669004, "running_accuracy": 0.9676953125, "lr": 1.1163448097038578e-05, "codebook_loss": 0.04199482500553131, "codebook_perplexity": 29.023653030395508, "codebook_active": 94.0, "codebook_commit": 0.16797930002212524} | |
| {"step": 32700, "epoch": 87, "loss": 0.05612334981560707, "task_loss": 0.015640633180737495, "partitioner_loss": 0.030569836497306824, "running_macro_f1": 0.8070193614791656, "running_accuracy": 0.9780078125, "lr": 1.1163448097038578e-05, "codebook_loss": 0.039651528000831604, "codebook_perplexity": 206.6266632080078, "codebook_active": 362.0, "codebook_commit": 0.15860611200332642} | |
| {"step": 32750, "epoch": 87, "loss": 0.07432304322719574, "task_loss": 0.034277770668268204, "partitioner_loss": 0.030167991295456886, "running_macro_f1": 0.7910122496941147, "running_accuracy": 0.9766796875, "lr": 1.1163448097038578e-05, "codebook_loss": 0.039509117603302, "codebook_perplexity": 86.67680358886719, "codebook_active": 256.0, "codebook_commit": 0.158036470413208} | |
| {"step": 32800, "epoch": 87, "loss": 0.08784462511539459, "task_loss": 0.04754455387592316, "partitioner_loss": 0.030217325314879417, "running_macro_f1": 0.7934321610279134, "running_accuracy": 0.9733203125, "lr": 1.1163448097038578e-05, "codebook_loss": 0.04033099114894867, "codebook_perplexity": 152.80519104003906, "codebook_active": 324.0, "codebook_commit": 0.16132396459579468} | |
| {"step": 32850, "epoch": 87, "loss": 0.09236361086368561, "task_loss": 0.04984811320900917, "partitioner_loss": 0.03220348805189133, "running_macro_f1": 0.7944870822882377, "running_accuracy": 0.97265625, "lr": 1.1163448097038578e-05, "codebook_loss": 0.041248027235269547, "codebook_perplexity": 177.62135314941406, "codebook_active": 315.0, "codebook_commit": 0.16499210894107819} | |
| {"epoch": 87, "split": "val", "val_macro_f1": 0.3880619428868131, "val_accuracy": 0.6922927586876335} | |
| {"step": 32900, "epoch": 88, "loss": 0.0920155867934227, "task_loss": 0.045584794133901596, "partitioner_loss": 0.036367110908031464, "running_macro_f1": 0.7936756252607973, "running_accuracy": 0.960546875, "lr": 9.647527395311997e-06, "codebook_loss": 0.04025473818182945, "codebook_perplexity": 180.88539123535156, "codebook_active": 397.0, "codebook_commit": 0.1610189527273178} | |
| {"step": 32950, "epoch": 88, "loss": 0.06470036506652832, "task_loss": 0.020711610093712807, "partitioner_loss": 0.03404543548822403, "running_macro_f1": 0.8025506016008104, "running_accuracy": 0.9734184152834325, "lr": 9.647527395311997e-06, "codebook_loss": 0.03977329283952713, "codebook_perplexity": 190.16061401367188, "codebook_active": 351.0, "codebook_commit": 0.15909317135810852} | |
| {"step": 33000, "epoch": 88, "loss": 0.06089382246136665, "task_loss": 0.019649505615234375, "partitioner_loss": 0.03240521252155304, "running_macro_f1": 0.7758906650412002, "running_accuracy": 0.96828125, "lr": 9.647527395311997e-06, "codebook_loss": 0.035356417298316956, "codebook_perplexity": 174.3134765625, "codebook_active": 363.0, "codebook_commit": 0.14142566919326782} | |
| {"step": 33050, "epoch": 88, "loss": 0.06402457505464554, "task_loss": 0.023506538942456245, "partitioner_loss": 0.031928930431604385, "running_macro_f1": 0.8030835873698019, "running_accuracy": 0.9759765625, "lr": 9.647527395311997e-06, "codebook_loss": 0.034356407821178436, "codebook_perplexity": 172.06871032714844, "codebook_active": 330.0, "codebook_commit": 0.13742563128471375} | |
| {"step": 33100, "epoch": 88, "loss": 0.06622800976037979, "task_loss": 0.0249482411891222, "partitioner_loss": 0.030437499284744263, "running_macro_f1": 0.821113050170955, "running_accuracy": 0.975078125, "lr": 9.647527395311997e-06, "codebook_loss": 0.04336908459663391, "codebook_perplexity": 215.7358856201172, "codebook_active": 385.0, "codebook_commit": 0.17347633838653564} | |
| {"step": 33150, "epoch": 88, "loss": 0.05037720873951912, "task_loss": 0.010037188418209553, "partitioner_loss": 0.030386850237846375, "running_macro_f1": 0.7901179060681094, "running_accuracy": 0.97828125, "lr": 9.647527395311997e-06, "codebook_loss": 0.039812684059143066, "codebook_perplexity": 221.92849731445312, "codebook_active": 366.0, "codebook_commit": 0.15925073623657227} | |
| {"step": 33200, "epoch": 88, "loss": 0.06191889941692352, "task_loss": 0.020519085228443146, "partitioner_loss": 0.029768899083137512, "running_macro_f1": 0.7699248058896081, "running_accuracy": 0.96375, "lr": 9.647527395311997e-06, "codebook_loss": 0.04652366042137146, "codebook_perplexity": 88.20471954345703, "codebook_active": 248.0, "codebook_commit": 0.18609464168548584} | |
| {"step": 33250, "epoch": 88, "loss": 0.07535824179649353, "task_loss": 0.0317121185362339, "partitioner_loss": 0.03364603966474533, "running_macro_f1": 0.8145403505365134, "running_accuracy": 0.9726171875, "lr": 9.647527395311997e-06, "codebook_loss": 0.040000323206186295, "codebook_perplexity": 205.74916076660156, "codebook_active": 391.0, "codebook_commit": 0.16000129282474518} | |
| {"epoch": 88, "split": "val", "val_macro_f1": 0.3814549540725586, "val_accuracy": 0.6664725296059018} | |
| {"step": 33300, "epoch": 89, "loss": 0.044399335980415344, "task_loss": 0.007044750265777111, "partitioner_loss": 0.028247669339179993, "running_macro_f1": 0.7819458835001246, "running_accuracy": 0.9743359375, "lr": 8.237687703151655e-06, "codebook_loss": 0.036427661776542664, "codebook_perplexity": 150.45086669921875, "codebook_active": 312.0, "codebook_commit": 0.14571064710617065} | |
| {"step": 33350, "epoch": 89, "loss": 0.09249462187290192, "task_loss": 0.04611137509346008, "partitioner_loss": 0.03239840269088745, "running_macro_f1": 0.7901938166285318, "running_accuracy": 0.978194487942374, "lr": 8.237687703151655e-06, "codebook_loss": 0.05593937262892723, "codebook_perplexity": 115.268798828125, "codebook_active": 237.0, "codebook_commit": 0.22375749051570892} | |
| {"step": 33400, "epoch": 89, "loss": 0.0659436285495758, "task_loss": 0.022212328389286995, "partitioner_loss": 0.03162442147731781, "running_macro_f1": 0.8132154658466706, "running_accuracy": 0.97359375, "lr": 8.237687703151655e-06, "codebook_loss": 0.0484275259077549, "codebook_perplexity": 170.2630157470703, "codebook_active": 389.0, "codebook_commit": 0.1937101036310196} | |
| {"step": 33450, "epoch": 89, "loss": 0.09849566221237183, "task_loss": 0.05381936579942703, "partitioner_loss": 0.034553755074739456, "running_macro_f1": 0.8008559905931133, "running_accuracy": 0.9703515625, "lr": 8.237687703151655e-06, "codebook_loss": 0.04049014672636986, "codebook_perplexity": 180.1174774169922, "codebook_active": 308.0, "codebook_commit": 0.16196058690547943} | |
| {"step": 33500, "epoch": 89, "loss": 0.0640053004026413, "task_loss": 0.02456413023173809, "partitioner_loss": 0.02930370718240738, "running_macro_f1": 0.80552246938957, "running_accuracy": 0.9745703125, "lr": 8.237687703151655e-06, "codebook_loss": 0.040549859404563904, "codebook_perplexity": 120.97013854980469, "codebook_active": 349.0, "codebook_commit": 0.16219943761825562} | |
| {"step": 33550, "epoch": 89, "loss": 0.08030197024345398, "task_loss": 0.040919579565525055, "partitioner_loss": 0.0298596378415823, "running_macro_f1": 0.7799772587568734, "running_accuracy": 0.96328125, "lr": 8.237687703151655e-06, "codebook_loss": 0.03809100389480591, "codebook_perplexity": 189.48916625976562, "codebook_active": 368.0, "codebook_commit": 0.15236401557922363} | |
| {"step": 33600, "epoch": 89, "loss": 0.06758932024240494, "task_loss": 0.02685636654496193, "partitioner_loss": 0.03148278594017029, "running_macro_f1": 0.8289579127311147, "running_accuracy": 0.9753515625, "lr": 8.237687703151655e-06, "codebook_loss": 0.03700067847967148, "codebook_perplexity": 199.1981658935547, "codebook_active": 382.0, "codebook_commit": 0.1480027139186859} | |
| {"epoch": 89, "split": "val", "val_macro_f1": 0.3908124854722486, "val_accuracy": 0.6928751698699281} | |
| {"step": 33650, "epoch": 90, "loss": 0.05507149174809456, "task_loss": 0.01609702967107296, "partitioner_loss": 0.03041333146393299, "running_macro_f1": 0.7924610556266943, "running_accuracy": 0.9744140625, "lr": 6.935348609620544e-06, "codebook_loss": 0.03424452245235443, "codebook_perplexity": 191.81260681152344, "codebook_active": 356.0, "codebook_commit": 0.13697808980941772} | |
| {"step": 33700, "epoch": 90, "loss": 0.079155832529068, "task_loss": 0.035268329083919525, "partitioner_loss": 0.033747874200344086, "running_macro_f1": 0.8206641924715968, "running_accuracy": 0.9725, "lr": 6.935348609620544e-06, "codebook_loss": 0.04055850952863693, "codebook_perplexity": 202.86090087890625, "codebook_active": 375.0, "codebook_commit": 0.16223403811454773} | |
| {"step": 33750, "epoch": 90, "loss": 0.07643181085586548, "task_loss": 0.0333394892513752, "partitioner_loss": 0.03245827928185463, "running_macro_f1": 0.8020875295454525, "running_accuracy": 0.9780859375, "lr": 6.935348609620544e-06, "codebook_loss": 0.0425361767411232, "codebook_perplexity": 116.16588592529297, "codebook_active": 296.0, "codebook_commit": 0.1701447069644928} | |
| {"step": 33800, "epoch": 90, "loss": 0.06352595239877701, "task_loss": 0.022670093923807144, "partitioner_loss": 0.03035929799079895, "running_macro_f1": 0.7865233611811189, "running_accuracy": 0.9775, "lr": 6.935348609620544e-06, "codebook_loss": 0.041986241936683655, "codebook_perplexity": 187.4833984375, "codebook_active": 345.0, "codebook_commit": 0.16794496774673462} | |
| {"step": 33850, "epoch": 90, "loss": 0.08840940147638321, "task_loss": 0.04345184564590454, "partitioner_loss": 0.034003786742687225, "running_macro_f1": 0.7686077583065255, "running_accuracy": 0.9620703125, "lr": 6.935348609620544e-06, "codebook_loss": 0.04381508380174637, "codebook_perplexity": 164.2332763671875, "codebook_active": 374.0, "codebook_commit": 0.17526033520698547} | |
| {"step": 33900, "epoch": 90, "loss": 0.07875753194093704, "task_loss": 0.03853446990251541, "partitioner_loss": 0.03046618402004242, "running_macro_f1": 0.8027932605876955, "running_accuracy": 0.9756107109301597, "lr": 6.935348609620544e-06, "codebook_loss": 0.03902750462293625, "codebook_perplexity": 187.25323486328125, "codebook_active": 340.0, "codebook_commit": 0.156110018491745} | |
| {"step": 33950, "epoch": 90, "loss": 0.055775225162506104, "task_loss": 0.01700417697429657, "partitioner_loss": 0.029823020100593567, "running_macro_f1": 0.7889495788519616, "running_accuracy": 0.9740625, "lr": 6.935348609620544e-06, "codebook_loss": 0.03579211235046387, "codebook_perplexity": 182.3513946533203, "codebook_active": 342.0, "codebook_commit": 0.14316844940185547} | |
| {"step": 34000, "epoch": 90, "loss": 0.31914767622947693, "task_loss": 0.2525555491447449, "partitioner_loss": 0.05663799121975899, "running_macro_f1": 0.776412717250759, "running_accuracy": 0.9725, "lr": 6.935348609620544e-06, "codebook_loss": 0.03981654345989227, "codebook_perplexity": 28.348224639892578, "codebook_active": 116.0, "codebook_commit": 0.1592661738395691} | |
| {"epoch": 90, "split": "val", "val_macro_f1": 0.38160729375756325, "val_accuracy": 0.68462434478742} | |
| {"step": 34050, "epoch": 91, "loss": 0.07179044187068939, "task_loss": 0.030444011092185974, "partitioner_loss": 0.029616592451930046, "running_macro_f1": 0.8207213141395555, "running_accuracy": 0.9745703125, "lr": 5.741821459791288e-06, "codebook_loss": 0.0469193309545517, "codebook_perplexity": 96.1164321899414, "codebook_active": 264.0, "codebook_commit": 0.1876773238182068} | |
| {"step": 34100, "epoch": 91, "loss": 0.06215505301952362, "task_loss": 0.020199593156576157, "partitioner_loss": 0.03149322420358658, "running_macro_f1": 0.8060617197177786, "running_accuracy": 0.9762890625, "lr": 5.741821459791288e-06, "codebook_loss": 0.04184895008802414, "codebook_perplexity": 130.0405731201172, "codebook_active": 297.0, "codebook_commit": 0.16739580035209656} | |
| {"step": 34150, "epoch": 91, "loss": 0.05242471396923065, "task_loss": 0.01026976853609085, "partitioner_loss": 0.033519160002470016, "running_macro_f1": 0.7956942370770164, "running_accuracy": 0.97625, "lr": 5.741821459791288e-06, "codebook_loss": 0.03454314172267914, "codebook_perplexity": 188.53282165527344, "codebook_active": 379.0, "codebook_commit": 0.13817256689071655} | |
| {"step": 34200, "epoch": 91, "loss": 0.06986372172832489, "task_loss": 0.02770754136145115, "partitioner_loss": 0.0316939614713192, "running_macro_f1": 0.7826804118549258, "running_accuracy": 0.9603515625, "lr": 5.741821459791288e-06, "codebook_loss": 0.04184887185692787, "codebook_perplexity": 212.49859619140625, "codebook_active": 341.0, "codebook_commit": 0.1673954874277115} | |
| {"step": 34250, "epoch": 91, "loss": 0.05101502686738968, "task_loss": 0.010269722901284695, "partitioner_loss": 0.03062143549323082, "running_macro_f1": 0.8069069535345343, "running_accuracy": 0.97625, "lr": 5.741821459791288e-06, "codebook_loss": 0.04049547761678696, "codebook_perplexity": 203.22813415527344, "codebook_active": 371.0, "codebook_commit": 0.16198191046714783} | |
| {"step": 34300, "epoch": 91, "loss": 0.07831792533397675, "task_loss": 0.035362884402275085, "partitioner_loss": 0.03299565985798836, "running_macro_f1": 0.8106492172084535, "running_accuracy": 0.974765625, "lr": 5.741821459791288e-06, "codebook_loss": 0.03983752429485321, "codebook_perplexity": 152.10643005371094, "codebook_active": 290.0, "codebook_commit": 0.15935009717941284} | |
| {"step": 34350, "epoch": 91, "loss": 0.06212138384580612, "task_loss": 0.017161551862955093, "partitioner_loss": 0.03507116436958313, "running_macro_f1": 0.8110906664599392, "running_accuracy": 0.9770591919824616, "lr": 5.741821459791288e-06, "codebook_loss": 0.03955467790365219, "codebook_perplexity": 193.3070526123047, "codebook_active": 345.0, "codebook_commit": 0.15821871161460876} | |
| {"epoch": 91, "split": "val", "val_macro_f1": 0.3933495517837549, "val_accuracy": 0.691127936323044} | |
| {"step": 34400, "epoch": 92, "loss": 0.14201277494430542, "task_loss": 0.09360513836145401, "partitioner_loss": 0.03547566384077072, "running_macro_f1": 0.7799094384067659, "running_accuracy": 0.971640625, "lr": 4.658308034332815e-06, "codebook_loss": 0.05172789841890335, "codebook_perplexity": 138.06600952148438, "codebook_active": 278.0, "codebook_commit": 0.2069115936756134} | |
| {"step": 34450, "epoch": 92, "loss": 0.04139791429042816, "task_loss": 0.007673528045415878, "partitioner_loss": 0.026370592415332794, "running_macro_f1": 0.8171118786322813, "running_accuracy": 0.9531640625, "lr": 4.658308034332815e-06, "codebook_loss": 0.029415182769298553, "codebook_perplexity": 136.7596893310547, "codebook_active": 310.0, "codebook_commit": 0.11766073107719421} | |
| {"step": 34500, "epoch": 92, "loss": 0.05095759034156799, "task_loss": 0.008101044222712517, "partitioner_loss": 0.032996274530887604, "running_macro_f1": 0.8017052105412473, "running_accuracy": 0.9783203125, "lr": 4.658308034332815e-06, "codebook_loss": 0.03944108635187149, "codebook_perplexity": 175.8267822265625, "codebook_active": 312.0, "codebook_commit": 0.15776434540748596} | |
| {"step": 34550, "epoch": 92, "loss": 0.055976688861846924, "task_loss": 0.02041269652545452, "partitioner_loss": 0.026738885790109634, "running_macro_f1": 0.838142327438341, "running_accuracy": 0.9740447854682117, "lr": 4.658308034332815e-06, "codebook_loss": 0.03530044108629227, "codebook_perplexity": 153.5278778076172, "codebook_active": 314.0, "codebook_commit": 0.14120176434516907} | |
| {"step": 34600, "epoch": 92, "loss": 0.09451758861541748, "task_loss": 0.05229824408888817, "partitioner_loss": 0.029894882813096046, "running_macro_f1": 0.789474063484026, "running_accuracy": 0.976015625, "lr": 4.658308034332815e-06, "codebook_loss": 0.04929784685373306, "codebook_perplexity": 69.62681579589844, "codebook_active": 220.0, "codebook_commit": 0.19719138741493225} | |
| {"step": 34650, "epoch": 92, "loss": 0.06828943639993668, "task_loss": 0.028235577046871185, "partitioner_loss": 0.02950841747224331, "running_macro_f1": 0.7879098195885168, "running_accuracy": 0.9750390625, "lr": 4.658308034332815e-06, "codebook_loss": 0.04218176007270813, "codebook_perplexity": 157.3903045654297, "codebook_active": 331.0, "codebook_commit": 0.16872704029083252} | |
| {"step": 34700, "epoch": 92, "loss": 0.06065363809466362, "task_loss": 0.01696755550801754, "partitioner_loss": 0.034768685698509216, "running_macro_f1": 0.8127994673811799, "running_accuracy": 0.9768359375, "lr": 4.658308034332815e-06, "codebook_loss": 0.03566958010196686, "codebook_perplexity": 172.27749633789062, "codebook_active": 365.0, "codebook_commit": 0.14267832040786743} | |
| {"step": 34750, "epoch": 92, "loss": 0.06998704373836517, "task_loss": 0.029721220955252647, "partitioner_loss": 0.030621131882071495, "running_macro_f1": 0.7915742033551605, "running_accuracy": 0.9791796875, "lr": 4.658308034332815e-06, "codebook_loss": 0.03857877105474472, "codebook_perplexity": 192.95167541503906, "codebook_active": 341.0, "codebook_commit": 0.15431508421897888} | |
| {"epoch": 92, "split": "val", "val_macro_f1": 0.3878767550379159, "val_accuracy": 0.6857891671520093} | |
| {"step": 34800, "epoch": 93, "loss": 0.09187965840101242, "task_loss": 0.04754885286092758, "partitioner_loss": 0.03340250253677368, "running_macro_f1": 0.7928017617212202, "running_accuracy": 0.9783203125, "lr": 3.6858993394190314e-06, "codebook_loss": 0.04371321201324463, "codebook_perplexity": 184.63792419433594, "codebook_active": 355.0, "codebook_commit": 0.17485284805297852} | |
| {"step": 34850, "epoch": 93, "loss": 0.05187779664993286, "task_loss": 0.012646107003092766, "partitioner_loss": 0.02991882525384426, "running_macro_f1": 0.8314307019004572, "running_accuracy": 0.9733203125, "lr": 3.6858993394190314e-06, "codebook_loss": 0.03725145012140274, "codebook_perplexity": 150.2183837890625, "codebook_active": 309.0, "codebook_commit": 0.14900580048561096} | |
| {"step": 34900, "epoch": 93, "loss": 0.08500978350639343, "task_loss": 0.04167186841368675, "partitioner_loss": 0.03288249671459198, "running_macro_f1": 0.802198299915142, "running_accuracy": 0.9793359375, "lr": 3.6858993394190314e-06, "codebook_loss": 0.04182165488600731, "codebook_perplexity": 182.3699951171875, "codebook_active": 347.0, "codebook_commit": 0.16728661954402924} | |
| {"step": 34950, "epoch": 93, "loss": 0.06776545941829681, "task_loss": 0.02788151055574417, "partitioner_loss": 0.03003881312906742, "running_macro_f1": 0.772569662593654, "running_accuracy": 0.9772940808017538, "lr": 3.6858993394190314e-06, "codebook_loss": 0.03938056156039238, "codebook_perplexity": 207.46762084960938, "codebook_active": 358.0, "codebook_commit": 0.15752224624156952} | |
| {"step": 35000, "epoch": 93, "loss": 0.13247331976890564, "task_loss": 0.08083654195070267, "partitioner_loss": 0.03997369110584259, "running_macro_f1": 0.7826265898603569, "running_accuracy": 0.9710546875, "lr": 3.6858993394190314e-06, "codebook_loss": 0.04665233567357063, "codebook_perplexity": 35.60542678833008, "codebook_active": 118.0, "codebook_commit": 0.18660934269428253} | |
| {"step": 35050, "epoch": 93, "loss": 0.052581846714019775, "task_loss": 0.011266729794442654, "partitioner_loss": 0.031705521047115326, "running_macro_f1": 0.7932336650954245, "running_accuracy": 0.9619921875, "lr": 3.6858993394190314e-06, "codebook_loss": 0.038438379764556885, "codebook_perplexity": 173.5679168701172, "codebook_active": 346.0, "codebook_commit": 0.15375351905822754} | |
| {"step": 35100, "epoch": 93, "loss": 0.05717024952173233, "task_loss": 0.014646871946752071, "partitioner_loss": 0.03219389170408249, "running_macro_f1": 0.7863062590362919, "running_accuracy": 0.9766796875, "lr": 3.6858993394190314e-06, "codebook_loss": 0.04131793603301048, "codebook_perplexity": 184.7567138671875, "codebook_active": 319.0, "codebook_commit": 0.16527174413204193} | |
| {"step": 35150, "epoch": 93, "loss": 0.16101990640163422, "task_loss": 0.11718679964542389, "partitioner_loss": 0.03444863110780716, "running_macro_f1": 0.7963090186452022, "running_accuracy": 0.9763671875, "lr": 3.6858993394190314e-06, "codebook_loss": 0.03753788769245148, "codebook_perplexity": 193.124267578125, "codebook_active": 366.0, "codebook_commit": 0.1501515507698059} | |
| {"epoch": 93, "split": "val", "val_macro_f1": 0.3856453227644976, "val_accuracy": 0.6808386721025044} | |
| {"step": 35200, "epoch": 94, "loss": 0.09039454907178879, "task_loss": 0.04577174410223961, "partitioner_loss": 0.03719741851091385, "running_macro_f1": 0.7961102706551152, "running_accuracy": 0.9778125, "lr": 2.82557450817819e-06, "codebook_loss": 0.02970157377421856, "codebook_perplexity": 169.61878967285156, "codebook_active": 302.0, "codebook_commit": 0.11880629509687424} | |
| {"step": 35250, "epoch": 94, "loss": 0.13352125883102417, "task_loss": 0.08052423596382141, "partitioner_loss": 0.04422903060913086, "running_macro_f1": 0.8147160291592555, "running_accuracy": 0.977265625, "lr": 2.82557450817819e-06, "codebook_loss": 0.03507198393344879, "codebook_perplexity": 66.70870971679688, "codebook_active": 160.0, "codebook_commit": 0.14028793573379517} | |
| {"step": 35300, "epoch": 94, "loss": 0.04332578927278519, "task_loss": 0.005476792808622122, "partitioner_loss": 0.028008967638015747, "running_macro_f1": 0.7907532720222573, "running_accuracy": 0.9770983401190103, "lr": 2.82557450817819e-06, "codebook_loss": 0.03936012089252472, "codebook_perplexity": 191.61285400390625, "codebook_active": 360.0, "codebook_commit": 0.15744048357009888} | |
| {"step": 35350, "epoch": 94, "loss": 0.07811249047517776, "task_loss": 0.028408655896782875, "partitioner_loss": 0.04113947972655296, "running_macro_f1": 0.8252465557153061, "running_accuracy": 0.9794140625, "lr": 2.82557450817819e-06, "codebook_loss": 0.034257419407367706, "codebook_perplexity": 119.31430053710938, "codebook_active": 253.0, "codebook_commit": 0.13702967762947083} | |
| {"step": 35400, "epoch": 94, "loss": 0.07275550812482834, "task_loss": 0.03308528661727905, "partitioner_loss": 0.02961725741624832, "running_macro_f1": 0.8029183157302423, "running_accuracy": 0.961640625, "lr": 2.82557450817819e-06, "codebook_loss": 0.04021186754107475, "codebook_perplexity": 169.6217803955078, "codebook_active": 318.0, "codebook_commit": 0.160847470164299} | |
| {"step": 35450, "epoch": 94, "loss": 0.06258302927017212, "task_loss": 0.022650567814707756, "partitioner_loss": 0.03004109114408493, "running_macro_f1": 0.7972502403236794, "running_accuracy": 0.97359375, "lr": 2.82557450817819e-06, "codebook_loss": 0.03956545889377594, "codebook_perplexity": 204.49398803710938, "codebook_active": 398.0, "codebook_commit": 0.15826183557510376} | |
| {"step": 35500, "epoch": 94, "loss": 0.06661565601825714, "task_loss": 0.025497883558273315, "partitioner_loss": 0.03127838671207428, "running_macro_f1": 0.8077290747731991, "running_accuracy": 0.9727734375, "lr": 2.82557450817819e-06, "codebook_loss": 0.03935755789279938, "codebook_perplexity": 156.01788330078125, "codebook_active": 343.0, "codebook_commit": 0.1574302315711975} | |
| {"epoch": 94, "split": "val", "val_macro_f1": 0.3817133325569953, "val_accuracy": 0.6698699281692875} | |
| {"step": 35550, "epoch": 95, "loss": 0.0627356693148613, "task_loss": 0.024660255759954453, "partitioner_loss": 0.028215192258358, "running_macro_f1": 0.7808960043482858, "running_accuracy": 0.9721875, "lr": 2.078199814788729e-06, "codebook_loss": 0.03944089636206627, "codebook_perplexity": 186.7252960205078, "codebook_active": 371.0, "codebook_commit": 0.15776358544826508} | |
| {"step": 35600, "epoch": 95, "loss": 0.09149269759654999, "task_loss": 0.04932485520839691, "partitioner_loss": 0.032288938760757446, "running_macro_f1": 0.7942029980923768, "running_accuracy": 0.979765625, "lr": 2.078199814788729e-06, "codebook_loss": 0.039515599608421326, "codebook_perplexity": 209.46823120117188, "codebook_active": 343.0, "codebook_commit": 0.1580623984336853} | |
| {"step": 35650, "epoch": 95, "loss": 0.09141328930854797, "task_loss": 0.04660354182124138, "partitioner_loss": 0.03377705067396164, "running_macro_f1": 0.803585089231558, "running_accuracy": 0.97359375, "lr": 2.078199814788729e-06, "codebook_loss": 0.04413079097867012, "codebook_perplexity": 139.9536590576172, "codebook_active": 282.0, "codebook_commit": 0.17652316391468048} | |
| {"step": 35700, "epoch": 95, "loss": 0.04985327646136284, "task_loss": 0.009603594429790974, "partitioner_loss": 0.03085758164525032, "running_macro_f1": 0.8122956033656992, "running_accuracy": 0.978359375, "lr": 2.078199814788729e-06, "codebook_loss": 0.037568408995866776, "codebook_perplexity": 165.592041015625, "codebook_active": 282.0, "codebook_commit": 0.1502736359834671} | |
| {"step": 35750, "epoch": 95, "loss": 0.09790991991758347, "task_loss": 0.05432037636637688, "partitioner_loss": 0.03081914409995079, "running_macro_f1": 0.8108032494822449, "running_accuracy": 0.9778125, "lr": 2.078199814788729e-06, "codebook_loss": 0.05108159780502319, "codebook_perplexity": 137.74964904785156, "codebook_active": 302.0, "codebook_commit": 0.20432639122009277} | |
| {"step": 35800, "epoch": 95, "loss": 0.09728460758924484, "task_loss": 0.049771059304475784, "partitioner_loss": 0.03572331368923187, "running_macro_f1": 0.7879685797818154, "running_accuracy": 0.96, "lr": 2.078199814788729e-06, "codebook_loss": 0.047160957008600235, "codebook_perplexity": 185.8621368408203, "codebook_active": 349.0, "codebook_commit": 0.18864382803440094} | |
| {"step": 35850, "epoch": 95, "loss": 0.0638890489935875, "task_loss": 0.02028592862188816, "partitioner_loss": 0.033745892345905304, "running_macro_f1": 0.7783268450775918, "running_accuracy": 0.977109375, "lr": 2.078199814788729e-06, "codebook_loss": 0.039428919553756714, "codebook_perplexity": 192.4404296875, "codebook_active": 364.0, "codebook_commit": 0.15771567821502686} | |
| {"step": 35900, "epoch": 95, "loss": 0.09915298223495483, "task_loss": 0.06088964641094208, "partitioner_loss": 0.030509639531373978, "running_macro_f1": 0.8183240525315234, "running_accuracy": 0.9751800814281241, "lr": 2.078199814788729e-06, "codebook_loss": 0.03101480007171631, "codebook_perplexity": 151.08999633789062, "codebook_active": 340.0, "codebook_commit": 0.12405920028686523} | |
| {"epoch": 95, "split": "val", "val_macro_f1": 0.38779089620635776, "val_accuracy": 0.663948747815958} | |
| {"step": 35950, "epoch": 96, "loss": 0.061498865485191345, "task_loss": 0.02009398303925991, "partitioner_loss": 0.03180457279086113, "running_macro_f1": 0.7894481110273736, "running_accuracy": 0.97640625, "lr": 1.444527802214657e-06, "codebook_loss": 0.03840123862028122, "codebook_perplexity": 153.48190307617188, "codebook_active": 304.0, "codebook_commit": 0.15360495448112488} | |
| {"step": 36000, "epoch": 96, "loss": 0.06615655869245529, "task_loss": 0.022198067978024483, "partitioner_loss": 0.0338999480009079, "running_macro_f1": 0.8089037885613805, "running_accuracy": 0.9807421875, "lr": 1.444527802214657e-06, "codebook_loss": 0.04023417830467224, "codebook_perplexity": 155.67127990722656, "codebook_active": 295.0, "codebook_commit": 0.16093671321868896} | |
| {"step": 36050, "epoch": 96, "loss": 0.05794817581772804, "task_loss": 0.01976986788213253, "partitioner_loss": 0.028250407427549362, "running_macro_f1": 0.7857863977972879, "running_accuracy": 0.9774898214844974, "lr": 1.444527802214657e-06, "codebook_loss": 0.039711613208055496, "codebook_perplexity": 187.45103454589844, "codebook_active": 375.0, "codebook_commit": 0.15884645283222198} | |
| {"step": 36100, "epoch": 96, "loss": 0.11718551814556122, "task_loss": 0.06949968636035919, "partitioner_loss": 0.03793777897953987, "running_macro_f1": 0.775189248663813, "running_accuracy": 0.9694140625, "lr": 1.444527802214657e-06, "codebook_loss": 0.038992226123809814, "codebook_perplexity": 79.64734649658203, "codebook_active": 176.0, "codebook_commit": 0.15596890449523926} | |
| {"step": 36150, "epoch": 96, "loss": 0.07013989239931107, "task_loss": 0.02921663224697113, "partitioner_loss": 0.030461717396974564, "running_macro_f1": 0.8307882748255704, "running_accuracy": 0.976328125, "lr": 1.444527802214657e-06, "codebook_loss": 0.04184617102146149, "codebook_perplexity": 223.0157470703125, "codebook_active": 368.0, "codebook_commit": 0.16738468408584595} | |
| {"step": 36200, "epoch": 96, "loss": 0.07098102569580078, "task_loss": 0.028580162674188614, "partitioner_loss": 0.031124405562877655, "running_macro_f1": 0.7791523282452193, "running_accuracy": 0.9609375, "lr": 1.444527802214657e-06, "codebook_loss": 0.04510582610964775, "codebook_perplexity": 139.8855438232422, "codebook_active": 303.0, "codebook_commit": 0.180423304438591} | |
| {"step": 36250, "epoch": 96, "loss": 0.080378457903862, "task_loss": 0.038475099951028824, "partitioner_loss": 0.03229415789246559, "running_macro_f1": 0.8184143272576268, "running_accuracy": 0.9762109375, "lr": 1.444527802214657e-06, "codebook_loss": 0.03843679279088974, "codebook_perplexity": 123.58001708984375, "codebook_active": 309.0, "codebook_commit": 0.15374717116355896} | |
| {"epoch": 96, "split": "val", "val_macro_f1": 0.38242482527323346, "val_accuracy": 0.6534653465346535} | |
| {"step": 36300, "epoch": 97, "loss": 0.06201300770044327, "task_loss": 0.02169652096927166, "partitioner_loss": 0.030505098402500153, "running_macro_f1": 0.774345463109291, "running_accuracy": 0.9640234375, "lr": 9.251965244585358e-07, "codebook_loss": 0.039245545864105225, "codebook_perplexity": 205.078125, "codebook_active": 349.0, "codebook_commit": 0.1569821834564209} | |
| {"step": 36350, "epoch": 97, "loss": 0.08393498510122299, "task_loss": 0.04371350258588791, "partitioner_loss": 0.031575605273246765, "running_macro_f1": 0.7996144024906652, "running_accuracy": 0.977265625, "lr": 9.251965244585358e-07, "codebook_loss": 0.03458352014422417, "codebook_perplexity": 181.533447265625, "codebook_active": 367.0, "codebook_commit": 0.13833408057689667} | |
| {"step": 36400, "epoch": 97, "loss": 0.13221649825572968, "task_loss": 0.08479948341846466, "partitioner_loss": 0.03814289718866348, "running_macro_f1": 0.8361956271903197, "running_accuracy": 0.976171875, "lr": 9.251965244585358e-07, "codebook_loss": 0.037096478044986725, "codebook_perplexity": 94.8138198852539, "codebook_active": 197.0, "codebook_commit": 0.1483859121799469} | |
| {"step": 36450, "epoch": 97, "loss": 0.13324446976184845, "task_loss": 0.08766321837902069, "partitioner_loss": 0.03412806987762451, "running_macro_f1": 0.8124951774105386, "running_accuracy": 0.9767851550266208, "lr": 9.251965244585358e-07, "codebook_loss": 0.04581271857023239, "codebook_perplexity": 162.56776428222656, "codebook_active": 300.0, "codebook_commit": 0.18325087428092957} | |
| {"step": 36500, "epoch": 97, "loss": 0.09393993765115738, "task_loss": 0.05099908635020256, "partitioner_loss": 0.032560691237449646, "running_macro_f1": 0.7935664825604805, "running_accuracy": 0.9776171875, "lr": 9.251965244585358e-07, "codebook_loss": 0.041520632803440094, "codebook_perplexity": 132.8289031982422, "codebook_active": 304.0, "codebook_commit": 0.16608253121376038} | |
| {"step": 36550, "epoch": 97, "loss": 0.07535569369792938, "task_loss": 0.03115144558250904, "partitioner_loss": 0.03122030198574066, "running_macro_f1": 0.8024341454193893, "running_accuracy": 0.9747265625, "lr": 9.251965244585358e-07, "codebook_loss": 0.051935795694589615, "codebook_perplexity": 121.53414154052734, "codebook_active": 293.0, "codebook_commit": 0.20774318277835846} | |
| {"step": 36600, "epoch": 97, "loss": 0.0708366334438324, "task_loss": 0.028883274644613266, "partitioner_loss": 0.030358927324414253, "running_macro_f1": 0.7862475523971983, "running_accuracy": 0.970390625, "lr": 9.251965244585358e-07, "codebook_loss": 0.04637772589921951, "codebook_perplexity": 202.0936279296875, "codebook_active": 350.0, "codebook_commit": 0.18551090359687805} | |
| {"step": 36650, "epoch": 97, "loss": 0.06415656954050064, "task_loss": 0.024712689220905304, "partitioner_loss": 0.029856247827410698, "running_macro_f1": 0.7994001213278338, "running_accuracy": 0.97734375, "lr": 9.251965244585358e-07, "codebook_loss": 0.03835051506757736, "codebook_perplexity": 220.28366088867188, "codebook_active": 358.0, "codebook_commit": 0.15340206027030945} | |
| {"epoch": 97, "split": "val", "val_macro_f1": 0.3959517736596654, "val_accuracy": 0.6852067559697146} | |
| {"step": 36700, "epoch": 98, "loss": 0.06591479480266571, "task_loss": 0.026332778856158257, "partitioner_loss": 0.030473578721284866, "running_macro_f1": 0.8271931977965633, "running_accuracy": 0.9765625, "lr": 5.207289040952723e-07, "codebook_loss": 0.03643374517560005, "codebook_perplexity": 191.71376037597656, "codebook_active": 371.0, "codebook_commit": 0.1457349807024002} | |
| {"step": 36750, "epoch": 98, "loss": 0.0851285308599472, "task_loss": 0.037426020950078964, "partitioner_loss": 0.036898769438266754, "running_macro_f1": 0.7790773102453523, "running_accuracy": 0.973515625, "lr": 5.207289040952723e-07, "codebook_loss": 0.04321499168872833, "codebook_perplexity": 136.98602294921875, "codebook_active": 258.0, "codebook_commit": 0.17285996675491333} | |
| {"step": 36800, "epoch": 98, "loss": 0.08137903362512589, "task_loss": 0.03715714439749718, "partitioner_loss": 0.03373618796467781, "running_macro_f1": 0.8299404280793832, "running_accuracy": 0.9769140625, "lr": 5.207289040952723e-07, "codebook_loss": 0.04194280877709389, "codebook_perplexity": 189.73336791992188, "codebook_active": 345.0, "codebook_commit": 0.16777123510837555} | |
| {"step": 36850, "epoch": 98, "loss": 0.07681477814912796, "task_loss": 0.03840067610144615, "partitioner_loss": 0.03113163262605667, "running_macro_f1": 0.7897068931182456, "running_accuracy": 0.9789453125, "lr": 5.207289040952723e-07, "codebook_loss": 0.029129883274435997, "codebook_perplexity": 221.5751190185547, "codebook_active": 365.0, "codebook_commit": 0.11651953309774399} | |
| {"step": 36900, "epoch": 98, "loss": 0.04927849397063255, "task_loss": 0.010832131840288639, "partitioner_loss": 0.02942856214940548, "running_macro_f1": 0.7926695299255083, "running_accuracy": 0.9728703413717507, "lr": 5.207289040952723e-07, "codebook_loss": 0.03607119619846344, "codebook_perplexity": 157.48150634765625, "codebook_active": 319.0, "codebook_commit": 0.14428478479385376} | |
| {"step": 36950, "epoch": 98, "loss": 0.07621842622756958, "task_loss": 0.03600440174341202, "partitioner_loss": 0.030389800667762756, "running_macro_f1": 0.7882579208876873, "running_accuracy": 0.961640625, "lr": 5.207289040952723e-07, "codebook_loss": 0.03929688036441803, "codebook_perplexity": 202.4537811279297, "codebook_active": 360.0, "codebook_commit": 0.15718752145767212} | |
| {"step": 37000, "epoch": 98, "loss": 0.08371099084615707, "task_loss": 0.044184207916259766, "partitioner_loss": 0.030448514968156815, "running_macro_f1": 0.7976133635547369, "running_accuracy": 0.9728125, "lr": 5.207289040952723e-07, "codebook_loss": 0.03631308674812317, "codebook_perplexity": 167.47105407714844, "codebook_active": 351.0, "codebook_commit": 0.14525234699249268} | |
| {"epoch": 98, "split": "val", "val_macro_f1": 0.3877010631581715, "val_accuracy": 0.6809357406328869} | |
| {"step": 37050, "epoch": 99, "loss": 0.05692730098962784, "task_loss": 0.018927564844489098, "partitioner_loss": 0.029008232057094574, "running_macro_f1": 0.7833828731749624, "running_accuracy": 0.9749060444722831, "lr": 2.3153220573330248e-07, "codebook_loss": 0.03596600890159607, "codebook_perplexity": 200.61578369140625, "codebook_active": 362.0, "codebook_commit": 0.14386403560638428} | |
| {"step": 37100, "epoch": 99, "loss": 0.1636429727077484, "task_loss": 0.12521828711032867, "partitioner_loss": 0.030975740402936935, "running_macro_f1": 0.7957795248329254, "running_accuracy": 0.977578125, "lr": 2.3153220573330248e-07, "codebook_loss": 0.029795750975608826, "codebook_perplexity": 210.15745544433594, "codebook_active": 367.0, "codebook_commit": 0.1191830039024353} | |
| {"step": 37150, "epoch": 99, "loss": 0.0996580719947815, "task_loss": 0.059736378490924835, "partitioner_loss": 0.029640376567840576, "running_macro_f1": 0.80917312595854, "running_accuracy": 0.9787890625, "lr": 2.3153220573330248e-07, "codebook_loss": 0.04112527519464493, "codebook_perplexity": 178.93943786621094, "codebook_active": 359.0, "codebook_commit": 0.1645011007785797} | |
| {"step": 37200, "epoch": 99, "loss": 0.08815273642539978, "task_loss": 0.045918602496385574, "partitioner_loss": 0.03263915330171585, "running_macro_f1": 0.7839906618607076, "running_accuracy": 0.973828125, "lr": 2.3153220573330248e-07, "codebook_loss": 0.03837990760803223, "codebook_perplexity": 158.7838134765625, "codebook_active": 346.0, "codebook_commit": 0.1535196304321289} | |
| {"step": 37250, "epoch": 99, "loss": 0.06814403086900711, "task_loss": 0.027815666049718857, "partitioner_loss": 0.029369553551077843, "running_macro_f1": 0.7975099062738616, "running_accuracy": 0.961953125, "lr": 2.3153220573330248e-07, "codebook_loss": 0.043835245072841644, "codebook_perplexity": 98.77235412597656, "codebook_active": 267.0, "codebook_commit": 0.17534098029136658} | |
| {"step": 37300, "epoch": 99, "loss": 0.10633865743875504, "task_loss": 0.06086960807442665, "partitioner_loss": 0.029587693512439728, "running_macro_f1": 0.7991885829986849, "running_accuracy": 0.9711328125, "lr": 2.3153220573330248e-07, "codebook_loss": 0.06352540850639343, "codebook_perplexity": 77.20230865478516, "codebook_active": 236.0, "codebook_commit": 0.25410163402557373} | |
| {"step": 37350, "epoch": 99, "loss": 0.09591986238956451, "task_loss": 0.047694601118564606, "partitioner_loss": 0.03432006761431694, "running_macro_f1": 0.7933414416522376, "running_accuracy": 0.973984375, "lr": 2.3153220573330248e-07, "codebook_loss": 0.05562080070376396, "codebook_perplexity": 90.92469787597656, "codebook_active": 254.0, "codebook_commit": 0.22248320281505585} | |
| {"step": 37400, "epoch": 99, "loss": 0.059483908116817474, "task_loss": 0.018848272040486336, "partitioner_loss": 0.031123969703912735, "running_macro_f1": 0.784293232044702, "running_accuracy": 0.9775390625, "lr": 2.3153220573330248e-07, "codebook_loss": 0.03804665803909302, "codebook_perplexity": 194.13619995117188, "codebook_active": 358.0, "codebook_commit": 0.15218663215637207} | |
| {"epoch": 99, "split": "val", "val_macro_f1": 0.38732603127606435, "val_accuracy": 0.6807416035721219} | |
| {"step": 37450, "epoch": 100, "loss": 0.07094701379537582, "task_loss": 0.02834431082010269, "partitioner_loss": 0.03174339234828949, "running_macro_f1": 0.7807365881497549, "running_accuracy": 0.9758984375, "lr": 5.78976259337155e-08, "codebook_loss": 0.04343723505735397, "codebook_perplexity": 132.40635681152344, "codebook_active": 303.0, "codebook_commit": 0.1737489402294159} | |
| {"step": 37500, "epoch": 100, "loss": 0.09396041184663773, "task_loss": 0.04133620113134384, "partitioner_loss": 0.043023914098739624, "running_macro_f1": 0.8184697914186766, "running_accuracy": 0.9723828125, "lr": 5.78976259337155e-08, "codebook_loss": 0.03840119019150734, "codebook_perplexity": 123.21403503417969, "codebook_active": 230.0, "codebook_commit": 0.15360476076602936} | |
| {"step": 37550, "epoch": 100, "loss": 0.06620130687952042, "task_loss": 0.026180529966950417, "partitioner_loss": 0.029909122735261917, "running_macro_f1": 0.8049299171039689, "running_accuracy": 0.9782421875, "lr": 5.78976259337155e-08, "codebook_loss": 0.04044660925865173, "codebook_perplexity": 206.23016357421875, "codebook_active": 375.0, "codebook_commit": 0.16178643703460693} | |
| {"step": 37600, "epoch": 100, "loss": 0.0522761195898056, "task_loss": 0.01319738756865263, "partitioner_loss": 0.030399441719055176, "running_macro_f1": 0.7993200653533578, "running_accuracy": 0.9651953125, "lr": 5.78976259337155e-08, "codebook_loss": 0.03471715375781059, "codebook_perplexity": 212.67396545410156, "codebook_active": 386.0, "codebook_commit": 0.13886861503124237} | |
| {"step": 37650, "epoch": 100, "loss": 0.07054544985294342, "task_loss": 0.0278584286570549, "partitioner_loss": 0.033064939081668854, "running_macro_f1": 0.7932432060574397, "running_accuracy": 0.971875, "lr": 5.78976259337155e-08, "codebook_loss": 0.03848833590745926, "codebook_perplexity": 121.76588439941406, "codebook_active": 289.0, "codebook_commit": 0.15395334362983704} | |
| {"step": 37700, "epoch": 100, "loss": 0.09150581061840057, "task_loss": 0.047931164503097534, "partitioner_loss": 0.03333544731140137, "running_macro_f1": 0.7730587931454149, "running_accuracy": 0.9790625, "lr": 5.78976259337155e-08, "codebook_loss": 0.040956802666187286, "codebook_perplexity": 165.19305419921875, "codebook_active": 371.0, "codebook_commit": 0.16382721066474915} | |
| {"step": 37750, "epoch": 100, "loss": 0.07223247736692429, "task_loss": 0.030925322324037552, "partitioner_loss": 0.0316067710518837, "running_macro_f1": 0.8318052465008765, "running_accuracy": 0.97484375, "lr": 5.78976259337155e-08, "codebook_loss": 0.038801513612270355, "codebook_perplexity": 185.91249084472656, "codebook_active": 327.0, "codebook_commit": 0.15520605444908142} | |
| {"step": 37800, "epoch": 100, "loss": 0.04807329922914505, "task_loss": 0.008744439110159874, "partitioner_loss": 0.029425179585814476, "running_macro_f1": 0.79448228755987, "running_accuracy": 0.9760804885687441, "lr": 5.78976259337155e-08, "codebook_loss": 0.0396147258579731, "codebook_perplexity": 201.17408752441406, "codebook_active": 354.0, "codebook_commit": 0.1584589034318924} | |
| {"epoch": 100, "split": "val", "val_macro_f1": 0.3880236168425272, "val_accuracy": 0.6889924286546302} | |