This commit is contained in:
Sofie Van Landeghem 2026-02-13 11:21:26 +01:00 committed by GitHub
commit 3db2124275
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -69,7 +69,7 @@ python -m scripts.tok_eval
echo "Waiting for dataset download to complete..."
wait $DATASET_DOWNLOAD_PID
# d24 model (slightly overtrained is enough to beat GPT-2 => increase data:params ratio from compute optimal 10.5 (default) to 12)
# d26 model (slightly undertrained to beat GPT-2 => decrease data:params ratio from compute optimal 10.5 (default) to 8.25)
torchrun --standalone --nproc_per_node=8 -m scripts.base_train -- --depth=26 --target-param-data-ratio=8.25 --device-batch-size=16 --fp8 --run=$WANDB_RUN
# evaluate the model: CORE metric, BPB on train/val, and draw samples
torchrun --standalone --nproc_per_node=8 -m scripts.base_eval -- --device-batch-size=16