eval_gpt2_large.py « src - jspace-nanogpt.git - J-space on nanoGPT: Jacobian Lens replication & critique. J-lens norms anti-correlate with token frequency (r ~ -0.61 to -0.69); frequency-matched synthetic pair + causal loss-reweighting tests.

summary refs log tree commit diff

path: root/src/eval_gpt2_large.py

blob: 4cbeaeff29e1be57088b0baa446899b750caf224 (plain)

# evaluate the base gpt2
# n_layer=36, n_head=20, n_embd=1280
# 774M parameters
batch_size = 8
eval_iters = 500 # use more iterations to get good estimate
eval_only = True
wandb_log = False
init_from = 'gpt2-large'