faeval.git/experiments/train_vit_dfa_save_checkpoint.py, branch master Unnamed repository; edit this file 'description' to name the repository. Add ViT-Mini DFA training script that saves checkpoint + Bs 2026-04-08T04:10:56+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-04-08T04:10:56+00:00 89fff0048c04bdc4c8beb6d11f8d5564d75cbb0c The existing snapshot_evolution_vit.py and vit_frozen_blocks_baseline.py do not save model checkpoints — they only emit per-epoch JSON logs. This makes it impossible to apply the diagnostic protocol to a trained ViT post-hoc, since the protocol needs an actual model object. This script trains a 4-block d=128 ViT-Mini with block-level DFA on CIFAR-10 (same training rule as snapshot_evolution_vit.py) for 60 epochs and saves: - the final state_dict - the random feedback Bs (so the protocol can also verify bug 4 on this checkpoint) - test_acc and config Output: results/vit_dfa_checkpoints/dfa_vit_s{seed}.pt 
The existing snapshot_evolution_vit.py and vit_frozen_blocks_baseline.py
do not save model checkpoints — they only emit per-epoch JSON logs. This
makes it impossible to apply the diagnostic protocol to a trained ViT
post-hoc, since the protocol needs an actual model object.

This script trains a 4-block d=128 ViT-Mini with block-level DFA on
CIFAR-10 (same training rule as snapshot_evolution_vit.py) for 60 epochs
and saves:
  - the final state_dict
  - the random feedback Bs (so the protocol can also verify bug 4 on
    this checkpoint)
  - test_acc and config

Output: results/vit_dfa_checkpoints/dfa_vit_s{seed}.pt