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 #73 from danielgross/master

Browse Source 
Use relative paths
This commit is contained in:
Andrej 2023-01-20 12:21:33 -08:00 committed by GitHub
commit a6bffeee59
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
data/openwebtext/prepare.py
View File

@ -1,6 +1,7 @@
# saves the openwebtext dataset to a binary file for training. following was helpful: # saves the openwebtext dataset to a binary file for training. following was helpful:
# https://github.com/HazyResearch/flash-attention/blob/main/training/src/datamodules/language_modeling_hf.py # https://github.com/HazyResearch/flash-attention/blob/main/training/src/datamodules/language_modeling_hf.py
import os
from tqdm import tqdm from tqdm import tqdm
import numpy as np import numpy as np
import tiktoken import tiktoken
@ -50,7 +51,7 @@ tokenized = split_dataset.map(
# concatenate all the ids in each dataset into one large file we can use for training # concatenate all the ids in each dataset into one large file we can use for training
for split, dset in tokenized.items(): for split, dset in tokenized.items():
arr_len = np.sum(dset['len']) arr_len = np.sum(dset['len'])
filename = f'{split}.bin' filename = os.path.join(os.path.dirname(__file__), f'{split}.bin')
dtype = np.uint16 # (can do since enc.max_token_value == 50256 is < 2**16) dtype = np.uint16 # (can do since enc.max_token_value == 50256 is < 2**16)
arr = np.memmap(filename, dtype=dtype, mode='w+', shape=(arr_len,)) arr = np.memmap(filename, dtype=dtype, mode='w+', shape=(arr_len,))

4
data/shakespeare/prepare.py
View File

@ -25,8 +25,8 @@ print(f"val has {len(val_ids):,} tokens")
# export to bin files # export to bin files
train_ids = np.array(train_ids, dtype=np.uint16) train_ids = np.array(train_ids, dtype=np.uint16)
val_ids = np.array(val_ids, dtype=np.uint16) val_ids = np.array(val_ids, dtype=np.uint16)
train_ids.tofile('train.bin') train_ids.tofile(os.path.join(os.path.dirname(__file__), 'train.bin'))
val_ids.tofile('val.bin') val_ids.tofile(os.path.join(os.path.dirname(__file__), 'val.bin'))
# train.bin has 301,966 tokens # train.bin has 301,966 tokens
# val.bin has 36,059 tokens # val.bin has 36,059 tokens

6
data/shakespeare_char/prepare.py
View File

@ -47,8 +47,8 @@ print(f"val has {len(val_ids):,} tokens")
# export to bin files # export to bin files
train_ids = np.array(train_ids, dtype=np.uint16) train_ids = np.array(train_ids, dtype=np.uint16)
val_ids = np.array(val_ids, dtype=np.uint16) val_ids = np.array(val_ids, dtype=np.uint16)
train_ids.tofile('train.bin') train_ids.tofile(os.path.join(os.path.dirname(__file__), 'train.bin'))
val_ids.tofile('val.bin') val_ids.tofile(os.path.join(os.path.dirname(__file__), 'val.bin'))
# save the meta information as well, to help us encode/decode later # save the meta information as well, to help us encode/decode later
meta = { meta = {
@ -56,7 +56,7 @@ meta = {
'itos': itos, 'itos': itos,
'stoi': stoi, 'stoi': stoi,
} }
with open('meta.pkl', 'wb') as f: with open(os.path.join(os.path.dirname(__file__), 'meta.pkl'), 'wb') as f:
pickle.dump(meta, f) pickle.dump(meta, f)
# length of dataset in characters: 1115394 # length of dataset in characters: 1115394