ros/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-30 04:22:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix args in readme (#438)

Browse Source 
* fix commands in readme, using new arg format

* fix typo

* add required -i flag to chat_eval example runs
This commit is contained in:
Sofie Van Landeghem
2026-01-16 01:26:38 +01:00
committed by GitHub
parent bdcc030ffa
commit d4ea28d4e2
3 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -82,10 +82,10 @@ That said, to give a sense, the example changes needed for the [speedrun.sh](spe
python -m nanochat.dataset -n 450 &
...
# use --depth to increase model size. to not oom, halve device batch size 32 -> 16:
torchrun --standalone --nproc_per_node=8 -m scripts.base_train -- --depth=26 --device_batch_size=16
torchrun --standalone --nproc_per_node=8 -m scripts.base_train -- --depth=26 --device-batch-size=16
...
# make sure to use the same later during midtraining:
torchrun --standalone --nproc_per_node=8 -m scripts.mid_train -- --device_batch_size=16
torchrun --standalone --nproc_per_node=8 -m scripts.mid_train -- --device-batch-size=16
```
That's it! The biggest thing to pay attention to is making sure you have enough data shards to train on (the code will loop and do more epochs over the same training set otherwise, decreasing learning speed a bit), and managing your memory/VRAM, primarily by decreasing the `device_batch_size` until things fit (the scripts automatically compensate by increasing the number of gradient accumulation loops, simply turning parallel compute to sequential compute).