summaryrefslogtreecommitdiff
path: root/results/vit_frozen_blocks_s42.log
diff options
context:
space:
mode:
authorYurenHao0426 <Blackhao0426@gmail.com>2026-06-14 04:06:32 -0500
committerYurenHao0426 <Blackhao0426@gmail.com>2026-06-14 04:06:32 -0500
commitaa73718eb6427d7da3b9cb416275802d90c4b2ed (patch)
treeb68b0a664fb650744ef934a1c22abd740a7b62a6 /results/vit_frozen_blocks_s42.log
parent827c658fa9a750f3c6ebdb87703762f10f69f6ff (diff)
Add new experiment scripts, figures, and paper assets; untrack pyc/build artifactsHEADmaster
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'results/vit_frozen_blocks_s42.log')
-rw-r--r--results/vit_frozen_blocks_s42.log34
1 files changed, 34 insertions, 0 deletions
diff --git a/results/vit_frozen_blocks_s42.log b/results/vit_frozen_blocks_s42.log
new file mode 100644
index 0000000..c2a20f6
--- /dev/null
+++ b/results/vit_frozen_blocks_s42.log
@@ -0,0 +1,34 @@
+Device: cuda:0
+
+=== BP frozen-blocks baseline (4 random-init transformer blocks, frozen) ===
+BP-frozen-blocks: 16266/809354 params trainable
+ BP-frozen ep 1: test_acc=0.3762
+ BP-frozen ep 5: test_acc=0.4724
+ BP-frozen ep 10: test_acc=0.4961
+ BP-frozen ep 15: test_acc=0.5189
+ BP-frozen ep 20: test_acc=0.5252
+ BP-frozen ep 25: test_acc=0.5366
+ BP-frozen ep 30: test_acc=0.5402
+FINAL BP-frozen-blocks acc: 0.5402
+
+=== DFA frozen-blocks baseline ===
+DFA-frozen-blocks: 16266/809354 params trainable
+ DFA-frozen ep 1: test_acc=0.2529
+ DFA-frozen ep 5: test_acc=0.2477
+ DFA-frozen ep 10: test_acc=0.2530
+ DFA-frozen ep 15: test_acc=0.2566
+ DFA-frozen ep 20: test_acc=0.2530
+ DFA-frozen ep 25: test_acc=0.2545
+ DFA-frozen ep 30: test_acc=0.2554
+FINAL DFA-frozen-blocks acc: 0.2554
+
+=== Summary ===
+BP-frozen-blocks: 0.5402 (chance=0.10)
+DFA-frozen-blocks: 0.2554
+Compare to ViT-Mini 4-block trainable (3-seed avg): BP=0.792, DFA=0.237
+Compare to ViT-Mini 0-block (shallow baseline): BP=0.10, DFA=0.10
+
+Interpretation:
+ If DFA-frozen-blocks ≈ 0.237: blocks are passengers, DFA is just learning patch_embed+head
+ If DFA-frozen-blocks << 0.237: trainable blocks ARE doing learned work
+ If DFA-frozen-blocks ~ 0.10: untrained blocks add no useful mixing (less informative)