diff --git a/runs/runcpu.sh b/runs/runcpu.sh index f767b10..be93894 100755 --- a/runs/runcpu.sh +++ b/runs/runcpu.sh @@ -23,6 +23,9 @@ if [ -z "$WANDB_RUN" ]; then WANDB_RUN=dummy fi +# wipe the report +python -m nanochat.report reset + # train tokenizer on ~2B characters (~34 seconds on my MacBook Pro M3 Max) python -m nanochat.dataset -n 8 python -m scripts.tok_train --max-chars=2000000000