mirror of
https://github.com/osmarks/nanogpt-experiments.git
synced 2024-12-21 23:50:28 +00:00
add benchmarking script v0
This commit is contained in:
parent
5d2b4807bf
commit
70b5d93aee
@ -57,3 +57,7 @@ and observe the following losses on train and val:
|
||||
| gpt2-xl | 1558M | 2.56 | 2.54 |
|
||||
|
||||
I briefly tried finetuning gpt2 a bit more on our OWT and didn't notice dramatic improvements, suggesting that OWT is not much much different from WT in terms of the data distribution, but this needs a bit more thorough attempt once the code is in a better place.
|
||||
|
||||
## benchmarking
|
||||
|
||||
For model benchmarking `bench.py` might be useful. It's identical what happens in `train.py` except we're measuring just the fwd+bwd+update time of the model on a fixed random batch of data.
|
||||
|
48
bench.py
Normal file
48
bench.py
Normal file
@ -0,0 +1,48 @@
|
||||
"""
|
||||
A much shorter version of train.py for benchmarking the model
|
||||
"""
|
||||
|
||||
import time
|
||||
import torch
|
||||
from model import GPTConfig, GPT
|
||||
|
||||
device = 'cuda:3'
|
||||
torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
|
||||
torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
|
||||
torch.manual_seed(1337)
|
||||
|
||||
batch_size = 8
|
||||
block_size = 1024
|
||||
|
||||
gptconf = GPTConfig(
|
||||
block_size = block_size, # how far back does the model look? i.e. context size
|
||||
n_layer = 12, n_head = 12, n_embd = 768, # size of the model
|
||||
dropout = 0, # for determinism
|
||||
)
|
||||
model = GPT(gptconf)
|
||||
model.to(device)
|
||||
|
||||
x = torch.randint(50257, (batch_size, block_size), device=device)
|
||||
y = torch.randint(50257, (batch_size, block_size), device=device)
|
||||
|
||||
optimizer = model.configure_optimizers(weight_decay=1e-2, learning_rate=1e-4, betas=(0.9, 0.95))
|
||||
|
||||
burn_in = 10 # number of burn in steps where we don't measure time
|
||||
num_steps = 30
|
||||
for k in range(num_steps):
|
||||
|
||||
if k == burn_in:
|
||||
t0 = time.time() # start the timer
|
||||
|
||||
with torch.autocast(device_type='cuda', dtype=torch.bfloat16):
|
||||
logits, loss = model(x, y)
|
||||
|
||||
optimizer.zero_grad(set_to_none=True)
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
lossf = loss.item()
|
||||
print(f"{k}/{num_steps} loss: {lossf:.4f}")
|
||||
|
||||
torch.cuda.synchronize()
|
||||
t1 = time.time()
|
||||
print("time in ms per iteration: %.2f" % ((t1 - t0) / (num_steps - burn_in) * 1000))
|
Loading…
Reference in New Issue
Block a user