Update rapid_prototype_output_bigger_bank.txt

rapid_prototype_output_bigger_bank.txt

@@ -10,7 +10,7 @@ PHASE 0: EXTRACTION
 
   Extracting: bert...
 Loading weights: 100%
- 199/199 [00:00<00:00, 4157.84it/s, Materializing param=pooler.dense.weight]
+ 199/199 [00:00<00:00, 4263.57it/s, Materializing param=pooler.dense.weight]
 BertModel LOAD REPORT from: google-bert/bert-base-uncased
 Key                                        | Status     |  | 
 -------------------------------------------+------------+--+-
@@ -29,7 +29,7 @@ Notes:
 
   Extracting: modern...
 Loading weights: 100%
- 134/134 [00:00<00:00, 3957.73it/s, Materializing param=layers.21.mlp_norm.weight]
+ 134/134 [00:00<00:00, 4171.61it/s, Materializing param=layers.21.mlp_norm.weight]
 ModernBertModel LOAD REPORT from: answerdotai/ModernBERT-base
 Key               | Status     |  | 
 ------------------+------------+--+-
@@ -71,42 +71,42 @@ PHASE 2: TRAIN ALIGNMENT BANK (student frozen)
   Student embeddings: torch.Size([18000, 768])
     Expert 0 (bert): rotation loaded, cos_after=1.0000
     Expert 1 (modern): rotation loaded, cos_after=0.4849
-    Anchors: 128 initialized from consensus embeddings
-  Bank: 1,305,152 params
-  E 1: 1s  loss=0.3517  v_loss=0.3123  expert_agr=0.00029  ortho=0.00018  spread=0.02575  cv=0.2469  anchor_max=0.560  expert_cos=0.657±0.061
-  E 2: 1s  loss=0.2758  v_loss=0.2718  expert_agr=0.00017  ortho=0.00027  spread=0.02053  cv=0.2049  anchor_max=0.587  expert_cos=0.634±0.064
-  E 3: 1s  loss=0.2505  v_loss=0.2533  expert_agr=0.00016  ortho=0.00023  spread=0.01885  cv=0.1988  anchor_max=0.590  expert_cos=0.619±0.067
-  E 4: 1s  loss=0.2391  v_loss=0.2338  expert_agr=0.00017  ortho=0.00022  spread=0.01824  cv=0.1965  anchor_max=0.593  expert_cos=0.627±0.069
-  E 5: 1s  loss=0.2327  v_loss=0.2376  expert_agr=0.00018  ortho=0.00023  spread=0.01752  cv=0.1933  anchor_max=0.595  expert_cos=0.613±0.070
-  E 6: 1s  loss=0.2274  v_loss=0.2334  expert_agr=0.00017  ortho=0.00022  spread=0.01680  cv=0.1882  anchor_max=0.597  expert_cos=0.610±0.070
-  E 7: 1s  loss=0.2249  v_loss=0.2297  expert_agr=0.00018  ortho=0.00021  spread=0.01603  cv=0.1880  anchor_max=0.597  expert_cos=0.614±0.074
-  E 8: 1s  loss=0.2221  v_loss=0.2236  expert_agr=0.00017  ortho=0.00021  spread=0.01550  cv=0.1857  anchor_max=0.598  expert_cos=0.601±0.074
-  E 9: 1s  loss=0.2206  v_loss=0.2351  expert_agr=0.00019  ortho=0.00021  spread=0.01500  cv=0.1850  anchor_max=0.599  expert_cos=0.588±0.077
-  E10: 1s  loss=0.2200  v_loss=0.2142  expert_agr=0.00024  ortho=0.00022  spread=0.01470  cv=0.1831  anchor_max=0.599  expert_cos=0.605±0.075
-  E11: 1s  loss=0.2181  v_loss=0.2254  expert_agr=0.00028  ortho=0.00021  spread=0.01445  cv=0.1782  anchor_max=0.599  expert_cos=0.629±0.072
-  E12: 1s  loss=0.2179  v_loss=0.2212  expert_agr=0.00021  ortho=0.00023  spread=0.01419  cv=0.1812  anchor_max=0.599  expert_cos=0.634±0.070
-  E13: 1s  loss=0.2170  v_loss=0.2259  expert_agr=0.00022  ortho=0.00023  spread=0.01387  cv=0.1792  anchor_max=0.599  expert_cos=0.614±0.072
-  E14: 1s  loss=0.2152  v_loss=0.2106  expert_agr=0.00016  ortho=0.00020  spread=0.01400  cv=0.1750  anchor_max=0.599  expert_cos=0.647±0.069
-  E15: 1s  loss=0.2151  v_loss=0.2301  expert_agr=0.00021  ortho=0.00021  spread=0.01368  cv=0.1766  anchor_max=0.599  expert_cos=0.639±0.073
-  E16: 1s  loss=0.2149  v_loss=0.2134  expert_agr=0.00022  ortho=0.00023  spread=0.01338  cv=0.1754  anchor_max=0.599  expert_cos=0.631±0.070
-  E17: 1s  loss=0.2151  v_loss=0.2110  expert_agr=0.00019  ortho=0.00022  spread=0.01341  cv=0.1778  anchor_max=0.599  expert_cos=0.642±0.073
-  E18: 1s  loss=0.2146  v_loss=0.2114  expert_agr=0.00023  ortho=0.00022  spread=0.01306  cv=0.1734  anchor_max=0.599  expert_cos=0.630±0.069
-  E19: 1s  loss=0.2147  v_loss=0.2127  expert_agr=0.00020  ortho=0.00023  spread=0.01300  cv=0.1768  anchor_max=0.599  expert_cos=0.610±0.072
-  E20: 1s  loss=0.2151  v_loss=0.2211  expert_agr=0.00019  ortho=0.00020  spread=0.01300  cv=0.1779  anchor_max=0.599  expert_cos=0.626±0.072
+    Anchors: 512 initialized from consensus embeddings
+  Bank: 1,649,216 params
+  E 1: 1s  loss=0.4828  v_loss=0.4384  expert_agr=0.00011  ortho=0.00007  spread=0.02783  cv=0.2529  anchor_max=0.625  expert_cos=0.827±0.045
+  E 2: 1s  loss=0.3974  v_loss=0.3863  expert_agr=0.00007  ortho=0.00009  spread=0.02224  cv=0.2140  anchor_max=0.653  expert_cos=0.832±0.052
+  E 3: 1s  loss=0.3647  v_loss=0.3696  expert_agr=0.00006  ortho=0.00008  spread=0.02128  cv=0.2076  anchor_max=0.656  expert_cos=0.788±0.056
+  E 4: 1s  loss=0.3518  v_loss=0.3461  expert_agr=0.00005  ortho=0.00010  spread=0.02102  cv=0.2051  anchor_max=0.656  expert_cos=0.800±0.053
+  E 5: 1s  loss=0.3428  v_loss=0.3584  expert_agr=0.00005  ortho=0.00011  spread=0.02022  cv=0.1954  anchor_max=0.657  expert_cos=0.787±0.055
+  E 6: 1s  loss=0.3386  v_loss=0.3424  expert_agr=0.00005  ortho=0.00014  spread=0.01978  cv=0.1941  anchor_max=0.656  expert_cos=0.755±0.061
+  E 7: 1s  loss=0.3365  v_loss=0.3332  expert_agr=0.00004  ortho=0.00013  spread=0.01886  cv=0.1947  anchor_max=0.656  expert_cos=0.763±0.060
+  E 8: 1s  loss=0.3337  v_loss=0.3413  expert_agr=0.00004  ortho=0.00013  spread=0.01852  cv=0.1900  anchor_max=0.656  expert_cos=0.792±0.053
+  E 9: 1s  loss=0.3332  v_loss=0.3489  expert_agr=0.00004  ortho=0.00014  spread=0.01789  cv=0.1942  anchor_max=0.655  expert_cos=0.735±0.060
+  E10: 1s  loss=0.3314  v_loss=0.3395  expert_agr=0.00004  ortho=0.00013  spread=0.01814  cv=0.1903  anchor_max=0.655  expert_cos=0.721±0.065
+  E11: 1s  loss=0.3286  v_loss=0.3470  expert_agr=0.00004  ortho=0.00013  spread=0.01801  cv=0.1832  anchor_max=0.655  expert_cos=0.775±0.060
+  E12: 1s  loss=0.3285  v_loss=0.3399  expert_agr=0.00004  ortho=0.00016  spread=0.01787  cv=0.1861  anchor_max=0.654  expert_cos=0.761±0.058
+  E13: 1s  loss=0.3275  v_loss=0.3392  expert_agr=0.00004  ortho=0.00015  spread=0.01772  cv=0.1839  anchor_max=0.655  expert_cos=0.729±0.065
+  E14: 1s  loss=0.3267  v_loss=0.3351  expert_agr=0.00004  ortho=0.00013  spread=0.01753  cv=0.1809  anchor_max=0.654  expert_cos=0.735±0.065
+  E15: 1s  loss=0.3260  v_loss=0.3497  expert_agr=0.00004  ortho=0.00014  spread=0.01737  cv=0.1809  anchor_max=0.654  expert_cos=0.772±0.061
+  E16: 1s  loss=0.3266  v_loss=0.3403  expert_agr=0.00003  ortho=0.00015  spread=0.01730  cv=0.1845  anchor_max=0.654  expert_cos=0.715±0.070
+  E17: 1s  loss=0.3245  v_loss=0.3252  expert_agr=0.00003  ortho=0.00014  spread=0.01732  cv=0.1788  anchor_max=0.654  expert_cos=0.744±0.067
+  E18: 1s  loss=0.3237  v_loss=0.3254  expert_agr=0.00003  ortho=0.00014  spread=0.01707  cv=0.1782  anchor_max=0.654  expert_cos=0.721±0.064
+  E19: 1s  loss=0.3231  v_loss=0.3327  expert_agr=0.00003  ortho=0.00015  spread=0.01721  cv=0.1784  anchor_max=0.653  expert_cos=0.690±0.072
+  E20: 1s  loss=0.3237  v_loss=0.3267  expert_agr=0.00003  ortho=0.00013  spread=0.01693  cv=0.1800  anchor_max=0.653  expert_cos=0.723±0.071
 
 =================================================================
 PHASE 3: GEOMETRIC VERIFICATION
 =================================================================
   Passthrough integrity: 1.000000 (should be ~1.000)
-  Geo context CV: 0.1691
-  Geo context eff_dim: 21.9
+  Geo context CV: 0.1651
+  Geo context eff_dim: 21.5
   Geo context shape: torch.Size([2000, 64])
 
 =================================================================
 PHASE 4: CLASSIFIER STABILITY TEST
 =================================================================
-  with_bank      : train_acc=0.499  val_acc=0.390  gap=0.109
-  without_bank   : train_acc=0.442  val_acc=0.372  gap=0.070
+  with_bank      : train_acc=0.481  val_acc=0.390  gap=0.091
+  without_bank   : train_acc=0.443  val_acc=0.330  gap=0.113
 
 =================================================================
 DONE