tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-03-09 18:55:30 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

clarify that this is bf16 mfu we're talking about

Browse Source
This commit is contained in:
Andrej Karpathy 2026-02-10 23:35:00 +00:00
parent e569b59f92
commit 2f09686724
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/base_train.py
View File

@ -531,7 +531,7 @@ while True:
else:
eta_str = ""
epoch = dataloader_state_dict["epoch"]
print0(f"step {step:05d}/{num_iterations:05d} ({pct_done:.2f}%) | loss: {debiased_smooth_loss:.6f} | lrm: {lrm:.2f} | dt: {dt * 1000:.2f}ms | tok/sec: {tok_per_sec:,} | mfu: {mfu:.2f} | epoch: {epoch} | total time: {total_training_time/60:.2f}m{eta_str}")
print0(f"step {step:05d}/{num_iterations:05d} ({pct_done:.2f}%) | loss: {debiased_smooth_loss:.6f} | lrm: {lrm:.2f} | dt: {dt * 1000:.2f}ms | tok/sec: {tok_per_sec:,} | bf16_mfu: {mfu:.2f} | epoch: {epoch} | total time: {total_training_time/60:.2f}m{eta_str}")
if step % 100 == 0:
log_data = {
"step": step,