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

Merge pull request #309 from ho2103/master

Browse Source 
Fix AssertionError on macOS - need to check CUDA availability for bf16
This commit is contained in:
Andrej 2023-06-22 08:24:17 -07:00 committed by GitHub
commit eba36e8464
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bench.py
View File

@ -15,7 +15,7 @@ bias = False
real_data = True
seed = 1337
device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
dtype = 'bfloat16' if torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
compile = True # use PyTorch 2.0 to compile the model to be faster
profile = False # use pytorch profiler, or just simple benchmarking?
exec(open('configurator.py').read()) # overrides from command line or config file

2
sample.py
View File

@ -18,7 +18,7 @@ temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, i
top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
seed = 1337
device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
dtype = 'bfloat16' if torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
compile = False # use PyTorch 2.0 to compile the model to be faster
exec(open('configurator.py').read()) # overrides from command line or config file
# -----------------------------------------------------------------------------

2
train.py
View File

@ -70,7 +70,7 @@ min_lr = 6e-5 # minimum learning rate, should be ~= learning_rate/10 per Chinchi
backend = 'nccl' # 'nccl', 'gloo', etc.
# system
device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1' etc., or try 'mps' on macbooks
dtype = 'bfloat16' if torch.cuda.is_bf16_supported() else 'float16' # 'float32', 'bfloat16', or 'float16', the latter will auto implement a GradScaler
dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32', 'bfloat16', or 'float16', the latter will auto implement a GradScaler
compile = True # use PyTorch 2.0 to compile the model to be faster
# -----------------------------------------------------------------------------
config_keys = [k for k,v in globals().items() if not k.startswith('_') and isinstance(v, (int, float, bool, str))]