tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2025-12-06 20:32:14 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

fix merge conflict

Browse Source
This commit is contained in:
Quanyi Mo 2025-11-02 22:49:30 -08:00
parent 5ca0950c9c
commit e86f8fc030
1 changed files with 1 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
scripts/base_train.py
View File

@ -141,13 +141,9 @@ adamw_optimizer, muon_optimizer = optimizers
# Initialize the DataLoaders for train/val # Initialize the DataLoaders for train/val
base_dir = get_base_dir() base_dir = get_base_dir()
tokens_dir = os.path.join(base_dir, "tokenized_data") tokens_dir = os.path.join(base_dir, "tokenized_data")
<<<<<<< HEAD
train_loader = tokenizing_distributed_data_loader(device_batch_size, max_seq_len, split="train")
build_val_loader = lambda: tokenizing_distributed_data_loader(device_batch_size_val, max_seq_len, split="val")
=======
train_loader = tokenizing_distributed_data_loader(device_batch_size, max_seq_len, split="train", device=device) train_loader = tokenizing_distributed_data_loader(device_batch_size, max_seq_len, split="train", device=device)
build_val_loader = lambda: tokenizing_distributed_data_loader(device_batch_size, max_seq_len, split="val", device=device) build_val_loader = lambda: tokenizing_distributed_data_loader(device_batch_size, max_seq_len, split="val", device=device)
>>>>>>> 722da4f... trying to add basic cpu support, will try mps too
x, y = next(train_loader) # kick off load of the very first batch of data x, y = next(train_loader) # kick off load of the very first batch of data
# ----------------------------------------------------------------------------- # -----------------------------------------------------------------------------