osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

make mentions of mps in docs. ty good people in issue #28

Browse Source
This commit is contained in:
Andrej Karpathy 2023-01-20 21:28:20 +00:00
parent a6bffeee59
commit 1f77d03024
2 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -125,6 +125,8 @@ $ python train.py config/train_shakespeare_char.py --device=cpu --compile=False
Where we decrease the context length to just 64 characters and only use a batch size of 8. Where we decrease the context length to just 64 characters and only use a batch size of 8.
Finally, on Apple Silicon Macbooks you can use device `--device mps` ("Metal Performance Shaders"), which can significantly accelerate training (2-3X). You will need a specific version of PyTorch. See [Issue 28](https://github.com/karpathy/nanoGPT/issues/28).
## benchmarking ## benchmarking
For model benchmarking `bench.py` might be useful. It's identical to what happens in the meat of the training loop of `train.py`, but omits much of the other complexities. For model benchmarking `bench.py` might be useful. It's identical to what happens in the meat of the training loop of `train.py`, but omits much of the other complexities.

2
train.py
View File

@ -67,7 +67,7 @@ min_lr = 6e-5 # minimum learning rate, should be ~= learning_rate/10 per Chinchi
# DDP settings # DDP settings
backend = 'nccl' # 'nccl', 'gloo', etc. backend = 'nccl' # 'nccl', 'gloo', etc.
# system # system
device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc. device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1' etc., or try 'mps' on macbooks
dtype = 'bfloat16' # 'float32' or 'bfloat16' dtype = 'bfloat16' # 'float32' or 'bfloat16'
compile = True # use PyTorch 2.0 to compile the model to be faster compile = True # use PyTorch 2.0 to compile the model to be faster
# ----------------------------------------------------------------------------- # -----------------------------------------------------------------------------