Skip to content

The best ChatGPT that $100 can buy.

Python

remove inherited parameters from commandline and replace by model-tag

svlandeg00a562cfe9ce
diff --git a/runs/runcpu.sh b/runs/runcpu.sh
index 853fa1f..4c8db86 100755
--- a/runs/runcpu.sh
+++ b/runs/runcpu.sh
@@ -47,9 +47,7 @@ python -m scripts.base_eval --device-batch-size=1 --split-tokens=16384 --max-per
# SFT (~10 minutes on my MacBook Pro M3 Max)
curl -L -o $NANOCHAT_BASE_DIR/identity_conversations.jsonl https://karpathy-public.s3.us-west-2.amazonaws.com/identity_conversations.jsonl
python -m scripts.chat_sft \
- --max-seq-len=512 \
- --device-batch-size=32 \
- --total-batch-size=16384 \
+ --model-tag=6 \
--eval-every=200 \
--eval-tokens=524288 \
--num-iterations=1500 \
diff --git a/runs/speedrun.sh b/runs/speedrun.sh
index c757253..98aaa8c 100644
--- a/runs/speedrun.sh
+++ b/runs/speedrun.sh
@@ -82,7 +82,7 @@ torchrun --standalone --nproc_per_node=8 -m scripts.base_eval -- --device-batch-
curl -L -o $NANOCHAT_BASE_DIR/identity_conversations.jsonl https://karpathy-public.s3.us-west-2.amazonaws.com/identity_conversations.jsonl
# run SFT and eval the model
-torchrun --standalone --nproc_per_node=8 -m scripts.chat_sft -- --device-batch-size=16 --run=$WANDB_RUN
+torchrun --standalone --nproc_per_node=8 -m scripts.chat_sft -- --model-tag=26 --run=$WANDB_RUN
torchrun --standalone --nproc_per_node=8 -m scripts.chat_eval -- -i sft
# chat with the model over CLI! Leave out the -p to chat interactively