-
Notifications
You must be signed in to change notification settings - Fork 2.7k
/
gpt_instruction_finetuning.py
351 lines (280 loc) · 11.1 KB
/
gpt_instruction_finetuning.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt).
# Source for "Build a Large Language Model From Scratch"
# - https://www.manning.com/books/build-a-large-language-model-from-scratch
# Code: https://github.com/rasbt/LLMs-from-scratch
#
# A minimal instruction finetuning file based on the code in chapter 7
from functools import partial
from importlib.metadata import version
import json
import os
import re
import time
import urllib
import matplotlib.pyplot as plt
import tiktoken
import torch
from torch.utils.data import Dataset, DataLoader
from tqdm import tqdm
# Import from local files in this folder
from gpt_download import download_and_load_gpt2
from previous_chapters import (
calc_loss_loader,
generate,
GPTModel,
load_weights_into_gpt,
text_to_token_ids,
train_model_simple,
token_ids_to_text
)
class InstructionDataset(Dataset):
def __init__(self, data, tokenizer):
self.data = data
# Pre-tokenize texts
self.encoded_texts = []
for entry in data:
instruction_plus_input = format_input(entry)
response_text = f"\n\n### Response:\n{entry['output']}"
full_text = instruction_plus_input + response_text
self.encoded_texts.append(
tokenizer.encode(full_text)
)
def __getitem__(self, index):
return self.encoded_texts[index]
def __len__(self):
return len(self.data)
def custom_collate_fn(
batch,
pad_token_id=50256,
ignore_index=-100,
allowed_max_length=None,
device="cpu"
):
# Find the longest sequence in the batch
batch_max_length = max(len(item)+1 for item in batch)
# Pad and prepare inputs and targets
inputs_lst, targets_lst = [], []
for item in batch:
new_item = item.copy()
# Add an <|endoftext|> token
new_item += [pad_token_id]
# Pad sequences to max_length
padded = new_item + [pad_token_id] * (batch_max_length - len(new_item))
inputs = torch.tensor(padded[:-1]) # Truncate the last token for inputs
targets = torch.tensor(padded[1:]) # Shift +1 to the right for targets
# New: Replace all but the first padding tokens in targets by ignore_index
mask = targets == pad_token_id
indices = torch.nonzero(mask).squeeze()
if indices.numel() > 1:
targets[indices[1:]] = ignore_index
# New: Optionally truncate to maximum sequence length
if allowed_max_length is not None:
inputs = inputs[:allowed_max_length]
targets = targets[:allowed_max_length]
inputs_lst.append(inputs)
targets_lst.append(targets)
# Convert list of inputs and targets to tensors and transfer to target device
inputs_tensor = torch.stack(inputs_lst).to(device)
targets_tensor = torch.stack(targets_lst).to(device)
return inputs_tensor, targets_tensor
def download_and_load_file(file_path, url):
if not os.path.exists(file_path):
with urllib.request.urlopen(url) as response:
text_data = response.read().decode("utf-8")
with open(file_path, "w", encoding="utf-8") as file:
file.write(text_data)
else:
with open(file_path, "r", encoding="utf-8") as file:
text_data = file.read()
with open(file_path, "r") as file:
data = json.load(file)
return data
def format_input(entry):
instruction_text = (
f"Below is an instruction that describes a task. "
f"Write a response that appropriately completes the request."
f"\n\n### Instruction:\n{entry['instruction']}"
)
input_text = f"\n\n### Input:\n{entry['input']}" if entry["input"] else ""
return instruction_text + input_text
def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
fig, ax1 = plt.subplots(figsize=(12, 6))
# Plot training and validation loss against epochs
ax1.plot(epochs_seen, train_losses, label="Training loss")
ax1.plot(epochs_seen, val_losses, linestyle="-.", label="Validation loss")
ax1.set_xlabel("Epochs")
ax1.set_ylabel("Loss")
ax1.legend(loc="upper right")
# Create a second x-axis for tokens seen
ax2 = ax1.twiny() # Create a second x-axis that shares the same y-axis
ax2.plot(tokens_seen, train_losses, alpha=0) # Invisible plot for aligning ticks
ax2.set_xlabel("Tokens seen")
fig.tight_layout() # Adjust layout to make room
plot_name = "loss-plot-standalone.pdf"
print(f"Plot saved as {plot_name}")
plt.savefig(plot_name)
# plt.show()
def main(test_mode=False):
#######################################
# Print package versions
#######################################
print()
pkgs = [
"matplotlib", # Plotting library
"tiktoken", # Tokenizer
"torch", # Deep learning library
"tqdm", # Progress bar
"tensorflow", # For OpenAI's pretrained weights
]
for p in pkgs:
print(f"{p} version: {version(p)}")
print(50*"-")
#######################################
# Download and prepare dataset
#######################################
file_path = "instruction-data.json"
url = "https://github.com/raw/rasbt/LLMs-from-scratch/main/ch07/01_main-chapter-code/instruction-data.json"
data = download_and_load_file(file_path, url)
train_portion = int(len(data) * 0.85) # 85% for training
test_portion = int(len(data) * 0.1) # 10% for testing
train_data = data[:train_portion]
test_data = data[train_portion:train_portion + test_portion]
val_data = data[train_portion + test_portion:]
# Use very small subset for testing purposes
if args.test_mode:
train_data = train_data[:10]
val_data = val_data[:10]
test_data = test_data[:10]
print("Training set length:", len(train_data))
print("Validation set length:", len(val_data))
print("Test set length:", len(test_data))
print(50*"-")
tokenizer = tiktoken.get_encoding("gpt2")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Device:", device)
print(50*"-")
customized_collate_fn = partial(custom_collate_fn, device=device, allowed_max_length=1024)
num_workers = 0
batch_size = 8
torch.manual_seed(123)
train_dataset = InstructionDataset(train_data, tokenizer)
train_loader = DataLoader(
train_dataset,
batch_size=batch_size,
collate_fn=customized_collate_fn,
shuffle=True,
drop_last=True,
num_workers=num_workers
)
val_dataset = InstructionDataset(val_data, tokenizer)
val_loader = DataLoader(
val_dataset,
batch_size=batch_size,
collate_fn=customized_collate_fn,
shuffle=False,
drop_last=False,
num_workers=num_workers
)
#######################################
# Load pretrained model
#######################################
# Small GPT model for testing purposes
if args.test_mode:
BASE_CONFIG = {
"vocab_size": 50257,
"context_length": 120,
"drop_rate": 0.0,
"qkv_bias": False,
"emb_dim": 12,
"n_layers": 1,
"n_heads": 2
}
model = GPTModel(BASE_CONFIG)
model.eval()
device = "cpu"
CHOOSE_MODEL = "Small test model"
# Code as it is used in the main chapter
else:
BASE_CONFIG = {
"vocab_size": 50257, # Vocabulary size
"context_length": 1024, # Context length
"drop_rate": 0.0, # Dropout rate
"qkv_bias": True # Query-key-value bias
}
model_configs = {
"gpt2-small (124M)": {"emb_dim": 768, "n_layers": 12, "n_heads": 12},
"gpt2-medium (355M)": {"emb_dim": 1024, "n_layers": 24, "n_heads": 16},
"gpt2-large (774M)": {"emb_dim": 1280, "n_layers": 36, "n_heads": 20},
"gpt2-xl (1558M)": {"emb_dim": 1600, "n_layers": 48, "n_heads": 25},
}
CHOOSE_MODEL = "gpt2-medium (355M)"
BASE_CONFIG.update(model_configs[CHOOSE_MODEL])
model_size = CHOOSE_MODEL.split(" ")[-1].lstrip("(").rstrip(")")
settings, params = download_and_load_gpt2(model_size=model_size, models_dir="gpt2")
model = GPTModel(BASE_CONFIG)
load_weights_into_gpt(model, params)
model.eval()
model.to(device)
print("Loaded model:", CHOOSE_MODEL)
print(50*"-")
#######################################
# Finetuning the model
#######################################
print("Initial losses")
with torch.no_grad():
train_loss = calc_loss_loader(train_loader, model, device, num_batches=5)
val_loss = calc_loss_loader(val_loader, model, device, num_batches=5)
print(" Training loss:", train_loss)
print(" Validation loss:", val_loss)
start_time = time.time()
optimizer = torch.optim.AdamW(model.parameters(), lr=0.00005, weight_decay=0.1)
num_epochs = 2
torch.manual_seed(123)
train_losses, val_losses, tokens_seen = train_model_simple(
model, train_loader, val_loader, optimizer, device,
num_epochs=num_epochs, eval_freq=5, eval_iter=5,
start_context=format_input(val_data[0]), tokenizer=tokenizer
)
end_time = time.time()
execution_time_minutes = (end_time - start_time) / 60
print(f"Training completed in {execution_time_minutes:.2f} minutes.")
epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
plot_losses(epochs_tensor, tokens_seen, train_losses, val_losses)
print(50*"-")
#######################################
# Saving results
#######################################
print("Generating responses")
for i, entry in tqdm(enumerate(test_data), total=len(test_data)):
input_text = format_input(entry)
token_ids = generate(
model=model,
idx=text_to_token_ids(input_text, tokenizer).to(device),
max_new_tokens=256,
context_size=BASE_CONFIG["context_length"],
eos_id=50256
)
generated_text = token_ids_to_text(token_ids, tokenizer)
response_text = generated_text[len(input_text):].replace("### Response:", "").strip()
test_data[i]["model_response"] = response_text
test_data_path = "instruction-data-with-response-standalone.json"
with open(test_data_path, "w") as file:
json.dump(test_data, file, indent=4) # "indent" for pretty-printing
print(f"Responses saved as {test_data_path}")
file_name = f"{re.sub(r'[ ()]', '', CHOOSE_MODEL) }-sft-standalone.pth"
torch.save(model.state_dict(), file_name)
print(f"Model saved as {file_name}")
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser(
description="Finetune a GPT model for classification"
)
parser.add_argument(
"--test_mode",
default=False,
action="store_true",
help=("This flag runs the model in test mode for internal testing purposes. "
"Otherwise, it runs the model as it is used in the chapter (recommended).")
)
args = parser.parse_args()
main(args.test_mode)