upload checkpoints

gen_A_rev_stage1_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ae534bcfce05f750c0fd498ebbae5fa7f1ca6c7d7897306fc8d2898d654da5
+size 37324521

gen_A_rev_stage1_history.json

@@ -0,0 +1,322 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 4.992077810197829,
+    "val_loss": 4.41277737521948,
+    "val_ppl": 82.49827427305421,
+    "lr": 0.002,
+    "seconds": 19.9
+  },
+  {
+    "epoch": 2,
+    "train_loss": 4.260214457938811,
+    "val_loss": 4.112561335225806,
+    "val_ppl": 61.10302263361123,
+    "lr": 0.002,
+    "seconds": 18.7
+  },
+  {
+    "epoch": 3,
+    "train_loss": 3.9886283273230534,
+    "val_loss": 3.9292949989348793,
+    "val_ppl": 50.871100843808605,
+    "lr": 0.002,
+    "seconds": 19.1
+  },
+  {
+    "epoch": 4,
+    "train_loss": 3.7803154315973813,
+    "val_loss": 3.7937495158541625,
+    "val_ppl": 44.42265183712277,
+    "lr": 0.002,
+    "seconds": 19.6
+  },
+  {
+    "epoch": 5,
+    "train_loss": 3.616203447472029,
+    "val_loss": 3.7077650537079117,
+    "val_ppl": 40.762602419679396,
+    "lr": 0.002,
+    "seconds": 19.6
+  },
+  {
+    "epoch": 6,
+    "train_loss": 3.4830308563066237,
+    "val_loss": 3.6489066978349,
+    "val_ppl": 38.432624599530804,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 7,
+    "train_loss": 3.379891736834745,
+    "val_loss": 3.6045697113522515,
+    "val_ppl": 36.76586052078049,
+    "lr": 0.002,
+    "seconds": 20.5
+  },
+  {
+    "epoch": 8,
+    "train_loss": 3.2958684243057643,
+    "val_loss": 3.580038021586449,
+    "val_ppl": 35.87490484192777,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 9,
+    "train_loss": 3.228247439424415,
+    "val_loss": 3.5683264127375542,
+    "val_ppl": 35.45720274510057,
+    "lr": 0.002,
+    "seconds": 19.6
+  },
+  {
+    "epoch": 10,
+    "train_loss": 3.1711336345614445,
+    "val_loss": 3.5545490948086655,
+    "val_ppl": 34.972047334285044,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 11,
+    "train_loss": 3.123712276886865,
+    "val_loss": 3.5554114694955845,
+    "val_ppl": 35.00221935057753,
+    "lr": 0.002,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 12,
+    "train_loss": 3.080217482419472,
+    "val_loss": 3.5458265216703677,
+    "val_ppl": 34.6683276279553,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 13,
+    "train_loss": 3.0456921475699392,
+    "val_loss": 3.5443911805573487,
+    "val_ppl": 34.6186024468267,
+    "lr": 0.002,
+    "seconds": 19.5
+  },
+  {
+    "epoch": 14,
+    "train_loss": 3.0139478940138638,
+    "val_loss": 3.541763680751007,
+    "val_ppl": 34.52776147018809,
+    "lr": 0.002,
+    "seconds": 19.5
+  },
+  {
+    "epoch": 15,
+    "train_loss": 2.983558714782092,
+    "val_loss": 3.5486448758004543,
+    "val_ppl": 34.76617306909382,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 16,
+    "train_loss": 2.9571208010084207,
+    "val_loss": 3.5478270929624562,
+    "val_ppl": 34.73775351151211,
+    "lr": 0.001,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 17,
+    "train_loss": 2.8425049404718488,
+    "val_loss": 3.5187574336558822,
+    "val_ppl": 33.7424751403769,
+    "lr": 0.001,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 18,
+    "train_loss": 2.7967806634551944,
+    "val_loss": 3.5161163071614854,
+    "val_ppl": 33.65347457790455,
+    "lr": 0.001,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 19,
+    "train_loss": 2.7684797937201666,
+    "val_loss": 3.5135782936441333,
+    "val_ppl": 33.568169902520495,
+    "lr": 0.001,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 20,
+    "train_loss": 2.745720855696675,
+    "val_loss": 3.504698383194975,
+    "val_ppl": 33.27140712334154,
+    "lr": 0.001,
+    "seconds": 19.2
+  },
+  {
+    "epoch": 21,
+    "train_loss": 2.7261419312461452,
+    "val_loss": 3.508754920132075,
+    "val_ppl": 33.40664793450516,
+    "lr": 0.001,
+    "seconds": 19.1
+  },
+  {
+    "epoch": 22,
+    "train_loss": 2.7051943964719625,
+    "val_loss": 3.507384847929792,
+    "val_ppl": 33.3609097542579,
+    "lr": 0.0005,
+    "seconds": 19.1
+  },
+  {
+    "epoch": 23,
+    "train_loss": 2.647555171671701,
+    "val_loss": 3.495823213340477,
+    "val_ppl": 32.97742423756333,
+    "lr": 0.0005,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 24,
+    "train_loss": 2.6293580891331443,
+    "val_loss": 3.4945959439875542,
+    "val_ppl": 32.93697688043593,
+    "lr": 0.0005,
+    "seconds": 19.5
+  },
+  {
+    "epoch": 25,
+    "train_loss": 2.6161078629503325,
+    "val_loss": 3.4926407210222576,
+    "val_ppl": 32.87264066315252,
+    "lr": 0.0005,
+    "seconds": 19.1
+  },
+  {
+    "epoch": 26,
+    "train_loss": 2.6033430786534315,
+    "val_loss": 3.4917688348869036,
+    "val_ppl": 32.84399195454661,
+    "lr": 0.0005,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 27,
+    "train_loss": 2.5901879300017043,
+    "val_loss": 3.493470093101245,
+    "val_ppl": 32.89991562246252,
+    "lr": 0.0005,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 28,
+    "train_loss": 2.5796319272207264,
+    "val_loss": 3.4908660844544,
+    "val_ppl": 32.8143554058208,
+    "lr": 0.0005,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 29,
+    "train_loss": 2.5706618013652034,
+    "val_loss": 3.4890450001452438,
+    "val_ppl": 32.75465207697362,
+    "lr": 0.0005,
+    "seconds": 19.5
+  },
+  {
+    "epoch": 30,
+    "train_loss": 2.560567700614365,
+    "val_loss": 3.4866200245946084,
+    "val_ppl": 32.675319075688144,
+    "lr": 0.0005,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 31,
+    "train_loss": 2.5524816759293127,
+    "val_loss": 3.487865550280159,
+    "val_ppl": 32.71604238057697,
+    "lr": 0.0005,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 32,
+    "train_loss": 2.542680621168711,
+    "val_loss": 3.4919517008043277,
+    "val_ppl": 32.849998550451346,
+    "lr": 0.00025,
+    "seconds": 19.2
+  },
+  {
+    "epoch": 33,
+    "train_loss": 2.5139937203319493,
+    "val_loss": 3.486225879450914,
+    "val_ppl": 32.662442795084225,
+    "lr": 0.00025,
+    "seconds": 19.2
+  },
+  {
+    "epoch": 34,
+    "train_loss": 2.505656928123776,
+    "val_loss": 3.4882017391325397,
+    "val_ppl": 32.727042998358264,
+    "lr": 0.00025,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 35,
+    "train_loss": 2.4978103072764366,
+    "val_loss": 3.486869904365059,
+    "val_ppl": 32.68348499712497,
+    "lr": 0.000125,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 36,
+    "train_loss": 2.482506708720772,
+    "val_loss": 3.486085174566851,
+    "val_ppl": 32.657847353165664,
+    "lr": 0.000125,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 37,
+    "train_loss": 2.478956270798748,
+    "val_loss": 3.4853489803888658,
+    "val_ppl": 32.63381368388792,
+    "lr": 0.000125,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 38,
+    "train_loss": 2.475499158148589,
+    "val_loss": 3.4855384226205848,
+    "val_ppl": 32.63999649200569,
+    "lr": 0.000125,
+    "seconds": 19.2
+  },
+  {
+    "epoch": 39,
+    "train_loss": 2.4725484151009813,
+    "val_loss": 3.485003784406631,
+    "val_ppl": 32.62255056662251,
+    "lr": 6.25e-05,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 40,
+    "train_loss": 2.4635073027057732,
+    "val_loss": 3.485256175683614,
+    "val_ppl": 32.630785252956244,
+    "lr": 6.25e-05,
+    "seconds": 19.3
+  }
+]

gen_A_rev_stage2_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4d853e0d0226eda34ec0b9feef92c01c9985ca29bf798d663a413776c5cfad
+size 37324521

gen_A_rev_stage2_history.json

@@ -0,0 +1,394 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 4.666991148905057,
+    "val_loss": 3.9494607115903033,
+    "val_ppl": 51.90736624431965,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 2,
+    "train_loss": 4.076495732756263,
+    "val_loss": 3.6341390095563586,
+    "val_ppl": 37.869233808378304,
+    "lr": 0.0004,
+    "seconds": 6.3
+  },
+  {
+    "epoch": 3,
+    "train_loss": 3.805675631155638,
+    "val_loss": 3.448179912463148,
+    "val_ppl": 31.443110981628692,
+    "lr": 0.0004,
+    "seconds": 4.6
+  },
+  {
+    "epoch": 4,
+    "train_loss": 3.6183973438446166,
+    "val_loss": 3.3285773715469893,
+    "val_ppl": 27.898624081807327,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 5,
+    "train_loss": 3.4808991059774725,
+    "val_loss": 3.245634397654073,
+    "val_ppl": 25.67799495389298,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 6,
+    "train_loss": 3.3808598321805494,
+    "val_loss": 3.187024536601157,
+    "val_ppl": 24.216265527031936,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 7,
+    "train_loss": 3.287910554096465,
+    "val_loss": 3.1382375273237146,
+    "val_ppl": 23.063182787480557,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 8,
+    "train_loss": 3.218911797190256,
+    "val_loss": 3.1003892919434795,
+    "val_ppl": 22.206594447285507,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 9,
+    "train_loss": 3.151564878332727,
+    "val_loss": 3.0647989309044466,
+    "val_ppl": 21.43015261255174,
+    "lr": 0.0004,
+    "seconds": 5.0
+  },
+  {
+    "epoch": 10,
+    "train_loss": 3.090452167862704,
+    "val_loss": 3.032177696907435,
+    "val_ppl": 20.74235400133967,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 11,
+    "train_loss": 3.0310602352865783,
+    "val_loss": 3.005298623591535,
+    "val_ppl": 20.192245076490607,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 12,
+    "train_loss": 2.9826101190911603,
+    "val_loss": 2.9789097049038813,
+    "val_ppl": 19.66636281245067,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 13,
+    "train_loss": 2.930248495319425,
+    "val_loss": 2.9580906552580166,
+    "val_ppl": 19.26116042854051,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 14,
+    "train_loss": 2.883981997661144,
+    "val_loss": 2.935293002668006,
+    "val_ppl": 18.827018693816374,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 15,
+    "train_loss": 2.835729065424365,
+    "val_loss": 2.917664158416966,
+    "val_ppl": 18.49802849221198,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 16,
+    "train_loss": 2.791768442345319,
+    "val_loss": 2.9017998787155204,
+    "val_ppl": 18.20688608268394,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 17,
+    "train_loss": 2.752450607008554,
+    "val_loss": 2.883409378028957,
+    "val_ppl": 17.87511242425237,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 18,
+    "train_loss": 2.7091256090042464,
+    "val_loss": 2.8703617126605345,
+    "val_ppl": 17.643398886532292,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 19,
+    "train_loss": 2.66722221391788,
+    "val_loss": 2.8540471517078267,
+    "val_ppl": 17.357889889629302,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 20,
+    "train_loss": 2.634758474099887,
+    "val_loss": 2.839842014660151,
+    "val_ppl": 17.11306171069881,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 21,
+    "train_loss": 2.593531661502249,
+    "val_loss": 2.8295983626910766,
+    "val_ppl": 16.93865626183158,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 22,
+    "train_loss": 2.562237200693833,
+    "val_loss": 2.81832660074058,
+    "val_ppl": 16.748799779367136,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 23,
+    "train_loss": 2.5283983512320183,
+    "val_loss": 2.8074369882325025,
+    "val_ppl": 16.56740131187571,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 24,
+    "train_loss": 2.4903672430971304,
+    "val_loss": 2.7987347716040345,
+    "val_ppl": 16.423853693810347,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 25,
+    "train_loss": 2.4526975113396676,
+    "val_loss": 2.7888471601005613,
+    "val_ppl": 16.26226120746295,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 26,
+    "train_loss": 2.420793698430034,
+    "val_loss": 2.7804741650491196,
+    "val_ppl": 16.1266658367134,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 27,
+    "train_loss": 2.395538880899935,
+    "val_loss": 2.773624364550099,
+    "val_ppl": 16.016578860367897,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 28,
+    "train_loss": 2.363249254815582,
+    "val_loss": 2.7686515115756634,
+    "val_ppl": 15.937128479801565,
+    "lr": 0.0004,
+    "seconds": 4.7
+  },
+  {
+    "epoch": 29,
+    "train_loss": 2.3345101003308555,
+    "val_loss": 2.758594921354398,
+    "val_ppl": 15.777658515416153,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 30,
+    "train_loss": 2.304782961286428,
+    "val_loss": 2.753860776208049,
+    "val_ppl": 15.703141316725937,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 31,
+    "train_loss": 2.277701916174873,
+    "val_loss": 2.7470435922102805,
+    "val_ppl": 15.596454179131605,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 32,
+    "train_loss": 2.2499211040544522,
+    "val_loss": 2.7422916992700213,
+    "val_ppl": 15.522517307800657,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 33,
+    "train_loss": 2.2210964990465203,
+    "val_loss": 2.7403235083649693,
+    "val_ppl": 15.491996076069983,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 34,
+    "train_loss": 2.1986916084033123,
+    "val_loss": 2.737847355878448,
+    "val_ppl": 15.45368298556805,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 35,
+    "train_loss": 2.171640456439519,
+    "val_loss": 2.732111051969327,
+    "val_ppl": 15.365289731116025,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 36,
+    "train_loss": 2.150857142965049,
+    "val_loss": 2.7281495866104963,
+    "val_ppl": 15.304541074412466,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 37,
+    "train_loss": 2.1273359565624412,
+    "val_loss": 2.725361092670934,
+    "val_ppl": 15.261923900858626,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 38,
+    "train_loss": 2.1043629420617873,
+    "val_loss": 2.724955693618493,
+    "val_ppl": 15.255737985337655,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 39,
+    "train_loss": 2.0805757883899676,
+    "val_loss": 2.7237084181020554,
+    "val_ppl": 15.236721738578149,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 40,
+    "train_loss": 2.060234374701839,
+    "val_loss": 2.7203605531379993,
+    "val_ppl": 15.185796544603809,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 41,
+    "train_loss": 2.040445105914024,
+    "val_loss": 2.7177206673927747,
+    "val_ppl": 15.145760645126828,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 42,
+    "train_loss": 2.0218897177351387,
+    "val_loss": 2.719962095444954,
+    "val_ppl": 15.17974685249881,
+    "lr": 0.0004,
+    "seconds": 4.3
+  },
+  {
+    "epoch": 43,
+    "train_loss": 1.9983945036601478,
+    "val_loss": 2.716163199878337,
+    "val_ppl": 15.122189974981737,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 44,
+    "train_loss": 1.9815523349880353,
+    "val_loss": 2.7161132299785953,
+    "val_ppl": 15.121434339544486,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 45,
+    "train_loss": 1.9650619021469835,
+    "val_loss": 2.715126768153548,
+    "val_ppl": 15.106524976796193,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 46,
+    "train_loss": 1.9483707471673888,
+    "val_loss": 2.7119292467236784,
+    "val_ppl": 15.058298682845592,
+    "lr": 0.0004,
+    "seconds": 4.5
+  },
+  {
+    "epoch": 47,
+    "train_loss": 1.9271366834874655,
+    "val_loss": 2.713654273132396,
+    "val_ppl": 15.084297063243259,
+    "lr": 0.0004,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 48,
+    "train_loss": 1.9113683797473628,
+    "val_loss": 2.714448368591232,
+    "val_ppl": 15.096280192285395,
+    "lr": 0.0002,
+    "seconds": 4.4
+  },
+  {
+    "epoch": 49,
+    "train_loss": 1.8892786902461047,
+    "val_loss": 2.7126965627334823,
+    "val_ppl": 15.069857590605707,
+    "lr": 0.0002,
+    "seconds": 4.4
+  }
+]

gen_A_rev_summary.json

@@ -0,0 +1,69 @@
+{
+  "name": "gen_A_rev",
+  "reverse": true,
+  "model": {
+    "emb_dim": 300,
+    "hidden": 512,
+    "layers": 2,
+    "dropout": 0.3
+  },
+  "batch_size": 64,
+  "lr": [
+    0.002,
+    0.0004
+  ],
+  "sampling": {
+    "temperature": 0.8,
+    "top_p": 0.9,
+    "rep_penalty": 1.2
+  },
+  "stage1": {
+    "epochs": 40,
+    "best_val_loss": 3.485003784406631,
+    "samples": {
+      "samples": 200,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0
+    }
+  },
+  "stage2": {
+    "epochs": 49,
+    "best_val_loss": 2.7119292467236784,
+    "samples": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0
+    },
+    "samples_heldout": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0
+    }
+  },
+  "test_loss": {
+    "seen_traits": 2.7077140186638435,
+    "heldout_traits": 3.7020773536165326
+  },
+  "comparison": {
+    "baseline": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 0.2734375,
+      "couplets_rhyme": 0.3125,
+      "aabb": 0.05625
+    },
+    "reversed": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0
+    }
+  }
+}

gen_A_stage1_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afe3b6338e0b2f05a16328caa90645a1a9a5947fbdd3596ce12e2096f7ea5bf
+size 37324481

gen_A_stage1_history.json

@@ -0,0 +1,234 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 4.829981294126383,
+    "val_loss": 4.245892536972604,
+    "val_ppl": 69.81804753164695,
+    "lr": 0.002,
+    "seconds": 19.2
+  },
+  {
+    "epoch": 2,
+    "train_loss": 4.093596008643176,
+    "val_loss": 4.013924387313442,
+    "val_ppl": 55.363713452123356,
+    "lr": 0.002,
+    "seconds": 18.2
+  },
+  {
+    "epoch": 3,
+    "train_loss": 3.87012337646873,
+    "val_loss": 3.894028706620533,
+    "val_ppl": 49.10833159316314,
+    "lr": 0.002,
+    "seconds": 18.5
+  },
+  {
+    "epoch": 4,
+    "train_loss": 3.709806584858199,
+    "val_loss": 3.8066714388652914,
+    "val_ppl": 45.00040271107567,
+    "lr": 0.002,
+    "seconds": 18.7
+  },
+  {
+    "epoch": 5,
+    "train_loss": 3.572864166958266,
+    "val_loss": 3.740215574003305,
+    "val_ppl": 42.10706637553023,
+    "lr": 0.002,
+    "seconds": 19.0
+  },
+  {
+    "epoch": 6,
+    "train_loss": 3.4593184986045884,
+    "val_loss": 3.7063769672459204,
+    "val_ppl": 40.70605965530679,
+    "lr": 0.002,
+    "seconds": 19.3
+  },
+  {
+    "epoch": 7,
+    "train_loss": 3.3679065372686807,
+    "val_loss": 3.6757238484591253,
+    "val_ppl": 39.4772220438671,
+    "lr": 0.002,
+    "seconds": 19.4
+  },
+  {
+    "epoch": 8,
+    "train_loss": 3.297483525773392,
+    "val_loss": 3.6513486588353388,
+    "val_ppl": 38.52659025348408,
+    "lr": 0.002,
+    "seconds": 19.7
+  },
+  {
+    "epoch": 9,
+    "train_loss": 3.236621219739334,
+    "val_loss": 3.6450068123353905,
+    "val_ppl": 38.28303364753463,
+    "lr": 0.002,
+    "seconds": 19.9
+  },
+  {
+    "epoch": 10,
+    "train_loss": 3.1841582190475384,
+    "val_loss": 3.6355990114548904,
+    "val_ppl": 37.92456334241846,
+    "lr": 0.002,
+    "seconds": 20.1
+  },
+  {
+    "epoch": 11,
+    "train_loss": 3.141668359596429,
+    "val_loss": 3.636127668450475,
+    "val_ppl": 37.94461772861264,
+    "lr": 0.002,
+    "seconds": 20.2
+  },
+  {
+    "epoch": 12,
+    "train_loss": 3.1020901158132954,
+    "val_loss": 3.623792298208015,
+    "val_ppl": 37.47943183890694,
+    "lr": 0.002,
+    "seconds": 20.3
+  },
+  {
+    "epoch": 13,
+    "train_loss": 3.0695216856437733,
+    "val_loss": 3.612478959828806,
+    "val_ppl": 37.057803851360866,
+    "lr": 0.002,
+    "seconds": 20.6
+  },
+  {
+    "epoch": 14,
+    "train_loss": 3.0379031966338736,
+    "val_loss": 3.6165150416042655,
+    "val_ppl": 37.207674419609795,
+    "lr": 0.002,
+    "seconds": 20.6
+  },
+  {
+    "epoch": 15,
+    "train_loss": 3.010851276063304,
+    "val_loss": 3.6205424491001343,
+    "val_ppl": 37.35782704642217,
+    "lr": 0.001,
+    "seconds": 20.7
+  },
+  {
+    "epoch": 16,
+    "train_loss": 2.89185258947665,
+    "val_loss": 3.579367499774065,
+    "val_ppl": 35.85085799858151,
+    "lr": 0.001,
+    "seconds": 21.0
+  },
+  {
+    "epoch": 17,
+    "train_loss": 2.842992280864271,
+    "val_loss": 3.5759147431283567,
+    "val_ppl": 35.727287163146926,
+    "lr": 0.001,
+    "seconds": 21.1
+  },
+  {
+    "epoch": 18,
+    "train_loss": 2.8154241360611314,
+    "val_loss": 3.573992906053114,
+    "val_ppl": 35.65869107444525,
+    "lr": 0.001,
+    "seconds": 21.2
+  },
+  {
+    "epoch": 19,
+    "train_loss": 2.790438276440956,
+    "val_loss": 3.5689031716393824,
+    "val_ppl": 35.477658900985666,
+    "lr": 0.001,
+    "seconds": 21.3
+  },
+  {
+    "epoch": 20,
+    "train_loss": 2.769956391419181,
+    "val_loss": 3.565130344163138,
+    "val_ppl": 35.34405999597407,
+    "lr": 0.001,
+    "seconds": 21.2
+  },
+  {
+    "epoch": 21,
+    "train_loss": 2.751856006506709,
+    "val_loss": 3.5704078767300143,
+    "val_ppl": 35.53108249823719,
+    "lr": 0.001,
+    "seconds": 21.2
+  },
+  {
+    "epoch": 22,
+    "train_loss": 2.7341743936730274,
+    "val_loss": 3.5654833268242614,
+    "val_ppl": 35.35653803846312,
+    "lr": 0.0005,
+    "seconds": 21.2
+  },
+  {
+    "epoch": 23,
+    "train_loss": 2.673041177530502,
+    "val_loss": 3.552708765702463,
+    "val_ppl": 34.90774644322088,
+    "lr": 0.0005,
+    "seconds": 21.3
+  },
+  {
+    "epoch": 24,
+    "train_loss": 2.6520412434349483,
+    "val_loss": 3.551742622424344,
+    "val_ppl": 34.87403684541328,
+    "lr": 0.0005,
+    "seconds": 21.3
+  },
+  {
+    "epoch": 25,
+    "train_loss": 2.6387730087939385,
+    "val_loss": 3.548803312525821,
+    "val_ppl": 34.771681744085114,
+    "lr": 0.0005,
+    "seconds": 21.4
+  },
+  {
+    "epoch": 26,
+    "train_loss": 2.626833282927489,
+    "val_loss": 3.547162824700475,
+    "val_ppl": 34.71468598672241,
+    "lr": 0.0005,
+    "seconds": 21.4
+  },
+  {
+    "epoch": 27,
+    "train_loss": 2.6161732333231806,
+    "val_loss": 3.5509774198415873,
+    "val_ppl": 34.84736134972873,
+    "lr": 0.0005,
+    "seconds": 21.4
+  },
+  {
+    "epoch": 28,
+    "train_loss": 2.6040847690859694,
+    "val_loss": 3.5509475944407147,
+    "val_ppl": 34.84632202870628,
+    "lr": 0.00025,
+    "seconds": 21.4
+  },
+  {
+    "epoch": 29,
+    "train_loss": 2.573186530926445,
+    "val_loss": 3.547201737922175,
+    "val_ppl": 34.716036873277965,
+    "lr": 0.00025,
+    "seconds": 21.4
+  }
+]

gen_A_stage2_best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b2f269d52b5ac69271b36167d8a96663b43778ae088a2e189d10dcccf858d5
+size 37324481

gen_A_stage2_history.json

@@ -0,0 +1,242 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 4.616285597071436,
+    "val_loss": 3.8839005975248373,
+    "val_ppl": 48.61346730323765,
+    "lr": 0.0004,
+    "seconds": 6.2
+  },
+  {
+    "epoch": 2,
+    "train_loss": 4.0411399632013385,
+    "val_loss": 3.599768829068394,
+    "val_ppl": 36.589774973555976,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 3,
+    "train_loss": 3.7776284790644703,
+    "val_loss": 3.4346891438401115,
+    "val_ppl": 31.02176775893347,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 4,
+    "train_loss": 3.6043900076472393,
+    "val_loss": 3.331649554112314,
+    "val_ppl": 27.98446554110884,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 5,
+    "train_loss": 3.4779846048226744,
+    "val_loss": 3.261255729776665,
+    "val_ppl": 26.082268868777092,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 6,
+    "train_loss": 3.382140250787782,
+    "val_loss": 3.204655214790901,
+    "val_ppl": 24.647000630043188,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 7,
+    "train_loss": 3.2958214125161565,
+    "val_loss": 3.1576460020294013,
+    "val_ppl": 23.515176048819654,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 8,
+    "train_loss": 3.218301520789232,
+    "val_loss": 3.1169851554296577,
+    "val_ppl": 22.578207144850083,
+    "lr": 0.0004,
+    "seconds": 4.9
+  },
+  {
+    "epoch": 9,
+    "train_loss": 3.1488155336513506,
+    "val_loss": 3.0829932987485362,
+    "val_ppl": 21.823629368064477,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 10,
+    "train_loss": 3.0871942197589775,
+    "val_loss": 3.0519879422276968,
+    "val_ppl": 21.15736225804773,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 11,
+    "train_loss": 3.027074639614512,
+    "val_loss": 3.021550199595634,
+    "val_ppl": 20.523081910507482,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 12,
+    "train_loss": 2.9757642130674444,
+    "val_loss": 2.9952286042062113,
+    "val_ppl": 19.98992914944667,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 13,
+    "train_loss": 2.9155534452808154,
+    "val_loss": 2.974422194933565,
+    "val_ppl": 19.578307535486115,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 14,
+    "train_loss": 2.8712283399782206,
+    "val_loss": 2.9506478023656153,
+    "val_ppl": 19.118334620006653,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 15,
+    "train_loss": 2.8206144727221436,
+    "val_loss": 2.931706094639756,
+    "val_ppl": 18.759608877994324,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 16,
+    "train_loss": 2.768709622012663,
+    "val_loss": 2.911202304973042,
+    "val_ppl": 18.378882310261105,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 17,
+    "train_loss": 2.732187525244317,
+    "val_loss": 2.8967026925848613,
+    "val_ppl": 18.11431831345474,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 18,
+    "train_loss": 2.686901987964146,
+    "val_loss": 2.880444116062053,
+    "val_ppl": 17.82218654156057,
+    "lr": 0.0004,
+    "seconds": 4.9
+  },
+  {
+    "epoch": 19,
+    "train_loss": 2.64535913937312,
+    "val_loss": 2.866215828003211,
+    "val_ppl": 17.570402810997248,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 20,
+    "train_loss": 2.605328651493096,
+    "val_loss": 2.8526903525831955,
+    "val_ppl": 17.334354689701442,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 21,
+    "train_loss": 2.565356180818644,
+    "val_loss": 2.8409318869643796,
+    "val_ppl": 17.131722930023724,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 22,
+    "train_loss": 2.5275584857162485,
+    "val_loss": 2.8269803856114453,
+    "val_ppl": 16.89436924447108,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 23,
+    "train_loss": 2.493029917278944,
+    "val_loss": 2.81680733042259,
+    "val_ppl": 16.723373144856712,
+    "lr": 0.0004,
+    "seconds": 4.8
+  },
+  {
+    "epoch": 24,
+    "train_loss": 2.4605441905550793,
+    "val_loss": 2.8085928428905333,
+    "val_ppl": 16.586561891142694,
+    "lr": 0.0004,
+    "seconds": 4.9
+  },
+  {
+    "epoch": 25,
+    "train_loss": 2.4231613296535732,
+    "val_loss": 2.7996008047875187,
+    "val_ppl": 16.438083456944035,
+    "lr": 0.0004,
+    "seconds": 4.9
+  },
+  {
+    "epoch": 26,
+    "train_loss": 2.394393812582054,
+    "val_loss": 2.789438634912261,
+    "val_ppl": 16.271882770524044,
+    "lr": 0.0004,
+    "seconds": 5.0
+  },
+  {
+    "epoch": 27,
+    "train_loss": 2.3637874954639737,
+    "val_loss": 2.7815398214745466,
+    "val_ppl": 16.14386048194788,
+    "lr": 0.0004,
+    "seconds": 5.1
+  },
+  {
+    "epoch": 28,
+    "train_loss": 2.3326300670711695,
+    "val_loss": 2.774357466757199,
+    "val_ppl": 16.028324954698395,
+    "lr": 0.0004,
+    "seconds": 5.2
+  },
+  {
+    "epoch": 29,
+    "train_loss": 2.3038180121662504,
+    "val_loss": 2.768438538048746,
+    "val_ppl": 15.933734654750564,
+    "lr": 0.0004,
+    "seconds": 5.2
+  },
+  {
+    "epoch": 30,
+    "train_loss": 2.2762656586325867,
+    "val_loss": 2.763802755120199,
+    "val_ppl": 15.86004026721918,
+    "lr": 0.0004,
+    "seconds": 5.3
+  }
+]

gen_A_summary.json

@@ -0,0 +1,45 @@
+{
+  "model": {
+    "emb_dim": 300,
+    "hidden": 512,
+    "layers": 2,
+    "dropout": 0.3
+  },
+  "batch_size": 64,
+  "lr": [
+    0.002,
+    0.0004
+  ],
+  "sampling": {
+    "temperature": 0.8,
+    "top_p": 0.9,
+    "rep_penalty": 1.2
+  },
+  "stage1": {
+    "epochs": 29,
+    "best_val_loss": 3.547162824700475,
+    "samples": {
+      "samples": 200,
+      "four_lines": 1.0,
+      "end_word_hit": 0.24
+    }
+  },
+  "stage2": {
+    "epochs": 30,
+    "best_val_loss": 2.763802755120199,
+    "samples": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 0.2734375
+    },
+    "samples_heldout": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 0.1875
+    }
+  },
+  "test_loss": {
+    "seen_traits": 2.7479417456012247,
+    "heldout_traits": 3.7121890360397534
+  }
+}

gen_D_1.5b_best/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-1.5B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.21.2

gen_D_1.5b_best/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.2",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

gen_D_1.5b_best/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d864d9de5bb654b87a66a79b3c0189ae705e471bae5056900bd99e48d26c014e
+size 17462432

gen_D_1.5b_history.json

@@ -0,0 +1,26 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 1.777713284482065,
+    "val_loss": 1.5607523326980999,
+    "val_ppl": 4.762402809059877,
+    "lr": 0.00015898837661756406,
+    "seconds": 283.4
+  },
+  {
+    "epoch": 2,
+    "train_loss": 1.4636819736536841,
+    "val_loss": 1.4744204138554795,
+    "val_ppl": 4.368503115176133,
+    "lr": 5.4716656824812505e-05,
+    "seconds": 269.8
+  },
+  {
+    "epoch": 3,
+    "train_loss": 1.3679931340887337,
+    "val_loss": 1.4625474019787907,
+    "val_ppl": 4.316942521277983,
+    "lr": 0.0,
+    "seconds": 269.7
+  }
+]

gen_D_1.5b_summary.json

@@ -0,0 +1,96 @@
+{
+  "name": "gen_D_1.5b",
+  "model": "Qwen/Qwen2.5-1.5B-Instruct",
+  "lora": {
+    "r": 16,
+    "alpha": 32,
+    "dropout": 0.05
+  },
+  "lr": 0.0002,
+  "epochs": 3,
+  "batch_size": 16,
+  "sampling": {
+    "temperature": 0.8,
+    "top_p": 0.9,
+    "rep_penalty": 1.2
+  },
+  "history": [
+    {
+      "epoch": 1,
+      "train_loss": 1.777713284482065,
+      "val_loss": 1.5607523326980999,
+      "val_ppl": 4.762402809059877,
+      "lr": 0.00015898837661756406,
+      "seconds": 283.4
+    },
+    {
+      "epoch": 2,
+      "train_loss": 1.4636819736536841,
+      "val_loss": 1.4744204138554795,
+      "val_ppl": 4.368503115176133,
+      "lr": 5.4716656824812505e-05,
+      "seconds": 269.8
+    },
+    {
+      "epoch": 3,
+      "train_loss": 1.3679931340887337,
+      "val_loss": 1.4625474019787907,
+      "val_ppl": 4.316942521277983,
+      "lr": 0.0,
+      "seconds": 269.7
+    }
+  ],
+  "best_val_loss": 1.4625474019787907,
+  "test_loss": {
+    "seen_traits": 1.4553480361331634,
+    "heldout_traits": 1.7033959883628667
+  },
+  "samples": {
+    "seen": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 0.94375,
+      "couplets_rhyme": 0.89375,
+      "aabb": 0.80625,
+      "syllables": 0.9828125,
+      "lexical": 0.995873828282423,
+      "trait_mention": 0.7756410256410257,
+      "distinct_2": 0.6616145994432415
+    },
+    "heldout": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 0.940625,
+      "couplets_rhyme": 0.890625,
+      "aabb": 0.79375,
+      "syllables": 0.9953125,
+      "lexical": 0.9946477018609465,
+      "trait_mention": 0.6875,
+      "distinct_2": 0.6239406779661016
+    }
+  },
+  "comparison_A": {
+    "seen": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0,
+      "syllables": 0.98515625,
+      "lexical": 0.9921457525139301,
+      "trait_mention": 0.6410256410256411,
+      "distinct_2": 0.5546401367946526
+    },
+    "heldout": {
+      "samples": 160,
+      "four_lines": 1.0,
+      "end_word_hit": 1.0,
+      "couplets_rhyme": 1.0,
+      "aabb": 1.0,
+      "syllables": 0.9765625,
+      "lexical": 0.9925916087675922,
+      "trait_mention": 0.0,
+      "distinct_2": 0.5145690312738368
+    }
+  }
+}

nlu_joint_best/config.json

@@ -0,0 +1,26 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.21.0",
+  "vocab_size": 30522
+}

nlu_joint_best/history.json

@@ -0,0 +1,132 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 1.674920692676451,
+    "val_n": 328,
+    "val_intent_acc": 0.8414634146341463,
+    "val_slot_precision": 0.1839080459770115,
+    "val_slot_recall": 0.18285714285714286,
+    "val_slot_f1": 0.18338108882521492,
+    "val_slot_word_f1": 0.5587044534412956,
+    "val_slot_overlap_f1": 0.6307775684533794,
+    "val_score": 0.700083934037721,
+    "seconds": 15.810535907745361
+  },
+  {
+    "epoch": 2,
+    "train_loss": 0.6739254768301801,
+    "val_n": 328,
+    "val_intent_acc": 0.8841463414634146,
+    "val_slot_precision": 0.28061224489795916,
+    "val_slot_recall": 0.3142857142857143,
+    "val_slot_f1": 0.29649595687331537,
+    "val_slot_word_f1": 0.6572700296735905,
+    "val_slot_overlap_f1": 0.7346938775510204,
+    "val_score": 0.7707081855685025,
+    "seconds": 16.214627265930176
+  },
+  {
+    "epoch": 3,
+    "train_loss": 0.35327073418330857,
+    "val_n": 328,
+    "val_intent_acc": 0.9085365853658537,
+    "val_slot_precision": 0.31555555555555553,
+    "val_slot_recall": 0.4057142857142857,
+    "val_slot_f1": 0.355,
+    "val_slot_word_f1": 0.7172582619339046,
+    "val_slot_overlap_f1": 0.742290076335878,
+    "val_score": 0.8128974236498792,
+    "seconds": 16.221457719802856
+  },
+  {
+    "epoch": 4,
+    "train_loss": 0.2046676227005153,
+    "val_n": 328,
+    "val_intent_acc": 0.9298780487804879,
+    "val_slot_precision": 0.3622448979591837,
+    "val_slot_recall": 0.4057142857142857,
+    "val_slot_f1": 0.3827493261455525,
+    "val_slot_word_f1": 0.7181208053691275,
+    "val_slot_overlap_f1": 0.7741984043353906,
+    "val_score": 0.8239994270748077,
+    "seconds": 15.705864191055298
+  },
+  {
+    "epoch": 5,
+    "train_loss": 0.11502567961494006,
+    "val_n": 328,
+    "val_intent_acc": 0.926829268292683,
+    "val_slot_precision": 0.3197969543147208,
+    "val_slot_recall": 0.36,
+    "val_slot_f1": 0.3387096774193548,
+    "val_slot_word_f1": 0.7157001414427157,
+    "val_slot_overlap_f1": 0.787685735854615,
+    "val_score": 0.8212647048676993,
+    "seconds": 15.813506364822388
+  },
+  {
+    "epoch": 6,
+    "train_loss": 0.06787605625406908,
+    "val_n": 328,
+    "val_intent_acc": 0.9298780487804879,
+    "val_slot_precision": 0.3153153153153153,
+    "val_slot_recall": 0.4,
+    "val_slot_f1": 0.35264483627204035,
+    "val_slot_word_f1": 0.7341079972658919,
+    "val_slot_overlap_f1": 0.801001010635738,
+    "val_score": 0.8319930230231899,
+    "seconds": 16.066911935806274
+  },
+  {
+    "epoch": 7,
+    "train_loss": 0.03402301226600596,
+    "val_n": 328,
+    "val_intent_acc": 0.926829268292683,
+    "val_slot_precision": 0.3333333333333333,
+    "val_slot_recall": 0.4114285714285714,
+    "val_slot_f1": 0.3682864450127877,
+    "val_slot_word_f1": 0.726643598615917,
+    "val_slot_overlap_f1": 0.8025542700087227,
+    "val_score": 0.8267364334542999,
+    "seconds": 15.893046379089355
+  },
+  {
+    "epoch": 8,
+    "train_loss": 0.01911875554757965,
+    "val_n": 328,
+    "val_intent_acc": 0.9329268292682927,
+    "val_slot_precision": 0.34051724137931033,
+    "val_slot_recall": 0.4514285714285714,
+    "val_slot_f1": 0.38820638820638814,
+    "val_slot_word_f1": 0.735812133072407,
+    "val_slot_overlap_f1": 0.7777096017998458,
+    "val_score": 0.8343694811703499,
+    "seconds": 15.667986869812012
+  },
+  {
+    "epoch": 9,
+    "train_loss": 0.013022744481554029,
+    "val_n": 328,
+    "val_intent_acc": 0.9329268292682927,
+    "val_slot_precision": 0.3424657534246575,
+    "val_slot_recall": 0.42857142857142855,
+    "val_slot_f1": 0.38071065989847713,
+    "val_slot_word_f1": 0.7223353699932112,
+    "val_slot_overlap_f1": 0.7917960853917072,
+    "val_score": 0.827631099630752,
+    "seconds": 15.945808410644531
+  },
+  {
+    "epoch": 10,
+    "train_loss": 0.009654329250646165,
+    "val_n": 328,
+    "val_intent_acc": 0.9237804878048781,
+    "val_slot_precision": 0.3409090909090909,
+    "val_slot_recall": 0.42857142857142855,
+    "val_slot_f1": 0.379746835443038,
+    "val_slot_word_f1": 0.7184730743012951,
+    "val_slot_overlap_f1": 0.7873725748109176,
+    "val_score": 0.8211267810530867,
+    "seconds": 15.955602407455444
+  }
+]

nlu_joint_best/labels.json

@@ -0,0 +1,26 @@
+{
+  "intents": [
+    "request_diss",
+    "another_one",
+    "make_meaner",
+    "make_softer",
+    "greet",
+    "goodbye",
+    "out_of_scope"
+  ],
+  "tags": [
+    "O",
+    "B-TRAIT",
+    "I-TRAIT"
+  ],
+  "epoch": 8,
+  "val": {
+    "n": 328,
+    "intent_acc": 0.9329268292682927,
+    "slot_precision": 0.34051724137931033,
+    "slot_recall": 0.4514285714285714,
+    "slot_f1": 0.38820638820638814,
+    "slot_word_f1": 0.735812133072407,
+    "slot_overlap_f1": 0.7777096017998458
+  }
+}

nlu_joint_best/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b67acb45bd51000bf66cf5e2df51b7a068f329664b3474da563c7eecb8fe809
+size 265516755

nlu_joint_best/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trait_fit_best/config.json

@@ -0,0 +1,26 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": null,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.21.0",
+  "vocab_size": 30522
+}

trait_fit_best/history.json

@@ -0,0 +1,62 @@
+[
+  {
+    "epoch": 1,
+    "train_loss": 0.35456217235916265,
+    "val_n": 723,
+    "val_positives": 402,
+    "val_auc": 0.9638451046945956,
+    "val_accuracy": 0.9059474412171508,
+    "val_precision": 0.8646288209606987,
+    "val_recall": 0.9850746268656716,
+    "val_f1": 0.9209302325581395,
+    "seconds": 21.273787260055542
+  },
+  {
+    "epoch": 2,
+    "train_loss": 0.1611071231232567,
+    "val_n": 723,
+    "val_positives": 402,
+    "val_auc": 0.972908045442569,
+    "val_accuracy": 0.9571230982019364,
+    "val_precision": 0.9513381995133819,
+    "val_recall": 0.972636815920398,
+    "val_f1": 0.9618696186961869,
+    "seconds": 21.30624794960022
+  },
+  {
+    "epoch": 3,
+    "train_loss": 0.1102666553688123,
+    "val_n": 723,
+    "val_positives": 402,
+    "val_auc": 0.9729506672246245,
+    "val_accuracy": 0.9543568464730291,
+    "val_precision": 0.9382422802850356,
+    "val_recall": 0.9825870646766169,
+    "val_f1": 0.959902794653706,
+    "seconds": 21.03678870201111
+  },
+  {
+    "epoch": 4,
+    "train_loss": 0.09242425882769237,
+    "val_n": 723,
+    "val_positives": 402,
+    "val_auc": 0.9774492025852048,
+    "val_accuracy": 0.9571230982019364,
+    "val_precision": 0.9427207637231504,
+    "val_recall": 0.9825870646766169,
+    "val_f1": 0.9622411693057248,
+    "seconds": 21.15024757385254
+  },
+  {
+    "epoch": 5,
+    "train_loss": 0.06733875241191996,
+    "val_n": 723,
+    "val_positives": 402,
+    "val_auc": 0.9769997365198928,
+    "val_accuracy": 0.9585062240663901,
+    "val_precision": 0.9514563106796117,
+    "val_recall": 0.9751243781094527,
+    "val_f1": 0.9631449631449632,
+    "seconds": 21.16893219947815
+  }
+]

trait_fit_best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59ed883386b6c82ff1c660f2bbd785969507ab347d329e7646d89e5b893478a
+size 267832560

trait_fit_best/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trait_fit_best/trait_fit.json

@@ -0,0 +1,411 @@
+{
+  "base_model": "distilbert-base-uncased",
+  "describe_traits": true,
+  "max_len": 192,
+  "traits": {
+    "confident": {
+      "synonyms": [
+        "self-assured",
+        "bold",
+        "sure of myself",
+        "cocky"
+      ],
+      "flip": "arrogant, all talk"
+    },
+    "smart": {
+      "synonyms": [
+        "intelligent",
+        "clever",
+        "brainy",
+        "big brain"
+      ],
+      "flip": "know-it-all who overthinks everything"
+    },
+    "funny": {
+      "synonyms": [
+        "hilarious",
+        "humorous",
+        "the class clown",
+        "a comedian"
+      ],
+      "flip": "tries too hard, laughs at their own jokes"
+    },
+    "hardworking": {
+      "synonyms": [
+        "diligent",
+        "grinder",
+        "always working",
+        "industrious"
+      ],
+      "flip": "workaholic with no life"
+    },
+    "ambitious": {
+      "synonyms": [
+        "driven",
+        "goal-oriented",
+        "aiming high",
+        "go-getter"
+      ],
+      "flip": "all big plans, no results"
+    },
+    "creative": {
+      "synonyms": [
+        "artistic",
+        "imaginative",
+        "inventive",
+        "full of ideas"
+      ],
+      "flip": "pretentious, never finishes anything"
+    },
+    "organized": {
+      "synonyms": [
+        "neat planner",
+        "methodical",
+        "has a planner",
+        "structured"
+      ],
+      "flip": "control freak who colour-codes everything"
+    },
+    "athletic": {
+      "synonyms": [
+        "sporty",
+        "fit",
+        "gym rat",
+        "into sports"
+      ],
+      "flip": "gym bro who only talks about protein"
+    },
+    "generous": {
+      "synonyms": [
+        "giving",
+        "kind-hearted",
+        "always pays",
+        "big-hearted"
+      ],
+      "flip": "pushover who buys friendship"
+    },
+    "honest": {
+      "synonyms": [
+        "truthful",
+        "straightforward",
+        "tells it like it is",
+        "blunt"
+      ],
+      "flip": "tactless, brutally rude"
+    },
+    "loyal": {
+      "synonyms": [
+        "faithful",
+        "devoted",
+        "ride or die",
+        "dependable"
+      ],
+      "flip": "clingy, can't let go"
+    },
+    "adventurous": {
+      "synonyms": [
+        "daring",
+        "fearless",
+        "outdoorsy",
+        "risk-taker"
+      ],
+      "flip": "reckless thrill-seeker"
+    },
+    "calm": {
+      "synonyms": [
+        "relaxed",
+        "composed",
+        "laid-back",
+        "never stressed"
+      ],
+      "flip": "so chill they're basically asleep"
+    },
+    "caring": {
+      "synonyms": [
+        "kind",
+        "thoughtful",
+        "nurturing",
+        "considerate"
+      ],
+      "flip": "smothering, acts like everyone's mum"
+    },
+    "tidy": {
+      "synonyms": [
+        "clean",
+        "neat",
+        "spotless",
+        "minimalist"
+      ],
+      "flip": "neat freak who panics at crumbs"
+    },
+    "knowledgeable": {
+      "synonyms": [
+        "well-informed",
+        "a walking encyclopedia",
+        "knows a lot",
+        "into history"
+      ],
+      "flip": "trivia bore who never stops lecturing"
+    },
+    "musical": {
+      "synonyms": [
+        "plays guitar",
+        "sings",
+        "a musician",
+        "into music"
+      ],
+      "flip": "brings a guitar to every party uninvited"
+    },
+    "bookish": {
+      "synonyms": [
+        "well-read",
+        "bookworm",
+        "reads a lot",
+        "literary"
+      ],
+      "flip": "quotes novels nobody asked about"
+    },
+    "independent": {
+      "synonyms": [
+        "self-reliant",
+        "self-sufficient",
+        "a lone wolf",
+        "does it all alone"
+      ],
+      "flip": "too proud to ever ask for help"
+    },
+    "optimistic": {
+      "synonyms": [
+        "positive",
+        "hopeful",
+        "glass half full",
+        "always upbeat"
+      ],
+      "flip": "naive and delusional"
+    },
+    "outgoing": {
+      "synonyms": [
+        "social",
+        "extroverted",
+        "life of the party",
+        "talks to everyone"
+      ],
+      "flip": "loud attention seeker"
+    },
+    "easygoing": {
+      "synonyms": [
+        "chill",
+        "flexible",
+        "go with the flow",
+        "low-maintenance"
+      ],
+      "flip": "lazy, has no opinions"
+    },
+    "competitive": {
+      "synonyms": [
+        "hates losing",
+        "driven to win",
+        "a winner",
+        "always first"
+      ],
+      "flip": "sore loser who turns everything into a contest"
+    },
+    "meticulous": {
+      "synonyms": [
+        "detail-oriented",
+        "perfectionist",
+        "precise",
+        "thorough"
+      ],
+      "flip": "nitpicker who takes forever"
+    },
+    "helpful": {
+      "synonyms": [
+        "supportive",
+        "always helping",
+        "useful",
+        "there for everyone"
+      ],
+      "flip": "meddling busybody"
+    },
+    "spontaneous": {
+      "synonyms": [
+        "impulsive",
+        "carefree",
+        "random",
+        "up for anything"
+      ],
+      "flip": "chaotic, never makes a plan"
+    },
+    "disciplined": {
+      "synonyms": [
+        "self-controlled",
+        "strict routine",
+        "focused",
+        "wakes up at 5am"
+      ],
+      "flip": "robot with no fun"
+    },
+    "charming": {
+      "synonyms": [
+        "charismatic",
+        "smooth",
+        "rizz",
+        "likeable"
+      ],
+      "flip": "smooth talker, totally insincere"
+    },
+    "humble": {
+      "synonyms": [
+        "modest",
+        "down to earth",
+        "unassuming",
+        "grounded"
+      ],
+      "flip": "fake modesty, master of the humblebrag"
+    },
+    "healthy": {
+      "synonyms": [
+        "health-conscious",
+        "eats clean",
+        "into wellness",
+        "never eats junk"
+      ],
+      "flip": "kale preacher who judges your lunch"
+    },
+    "romantic": {
+      "synonyms": [
+        "sweet",
+        "affectionate",
+        "a hopeless romantic",
+        "lovey-dovey"
+      ],
+      "flip": "cheesy and over the top"
+    },
+    "responsible": {
+      "synonyms": [
+        "reliable",
+        "mature",
+        "trustworthy",
+        "the adult in the room"
+      ],
+      "flip": "the no-fun parent of the friend group"
+    },
+    "curious": {
+      "synonyms": [
+        "inquisitive",
+        "always asking why",
+        "interested in everything",
+        "eager to learn"
+      ],
+      "flip": "nosy, asks way too many questions"
+    },
+    "entrepreneurial": {
+      "synonyms": [
+        "business-minded",
+        "a hustler",
+        "runs a startup",
+        "enterprising"
+      ],
+      "flip": "side-hustle guy pitching crypto at dinner"
+    },
+    "wise": {
+      "synonyms": [
+        "insightful",
+        "sage",
+        "gives good advice",
+        "an old soul"
+      ],
+      "flip": "fortune-cookie philosopher with unsolicited advice"
+    },
+    "eloquent": {
+      "synonyms": [
+        "articulate",
+        "well-spoken",
+        "a good speaker",
+        "great with words"
+      ],
+      "flip": "uses big words to hear their own voice"
+    },
+    "punctual": {
+      "synonyms": [
+        "on time",
+        "never late",
+        "early for everything",
+        "prompt"
+      ],
+      "flip": "judges everyone who's a minute late"
+    },
+    "patient": {
+      "synonyms": [
+        "tolerant",
+        "unhurried",
+        "can wait forever",
+        "even-tempered"
+      ],
+      "flip": "so slow they never get anything done"
+    },
+    "worldly": {
+      "synonyms": [
+        "well-traveled",
+        "a globetrotter",
+        "been everywhere",
+        "cultured"
+      ],
+      "flip": "won't stop saying 'when I was in Bali'"
+    },
+    "frugal": {
+      "synonyms": [
+        "thrifty",
+        "good with money",
+        "saves everything",
+        "budget-savvy"
+      ],
+      "flip": "cheapskate who splits the bill to the cent"
+    }
+  },
+  "epoch": 4,
+  "lr": 5e-05,
+  "seed": 42,
+  "val": {
+    "n": 723,
+    "positives": 402,
+    "auc": 0.9774492025852048,
+    "accuracy": 0.9571230982019364,
+    "precision": 0.9427207637231504,
+    "recall": 0.9825870646766169,
+    "f1": 0.9622411693057248,
+    "by_type": {
+      "flat": {
+        "n": 38,
+        "mean_score": 0.08649065687572338,
+        "scored_fit": 0.07894736842105263
+      },
+      "non_rhyming": {
+        "n": 46,
+        "mean_score": 0.0009681683453812224,
+        "scored_fit": 0.0
+      },
+      "off_topic": {
+        "n": 70,
+        "mean_score": 0.0011165548997398998,
+        "scored_fit": 0.0
+      },
+      "positive": {
+        "n": 402,
+        "mean_score": 0.9695785399225184,
+        "scored_fit": 0.9825870646766169
+      },
+      "shuffled": {
+        "n": 80,
+        "mean_score": 0.2100172968413972,
+        "scored_fit": 0.2125
+      },
+      "wrong_trait": {
+        "n": 87,
+        "mean_score": 0.05152666364895479,
+        "scored_fit": 0.04597701149425287
+      }
+    }
+  }
+}