-
Notifications
You must be signed in to change notification settings - Fork 5
/
finetune_alpaca.py
286 lines (249 loc) · 9.56 KB
/
finetune_alpaca.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
import os
import sys
from typing import List
import fire
import torch
import transformers
from datasets import load_dataset
"""
Unused imports:
import torch.nn as nn
import bitsandbytes as bnb
"""
from peft import ( # noqa: E402
LoraConfig,
get_peft_model,
get_peft_model_state_dict,
prepare_model_for_int8_training,
set_peft_model_state_dict,
)
from transformers import LlamaForCausalLM, LlamaTokenizer # noqa: F402
def train(
# model/data params
base_model: str = "", # the only required argument
data_path: str = "./alpaca_data_cleaned.json",
output_dir: str = "./lora-alpaca",
# training hyperparams
batch_size: int = 128,
micro_batch_size: int = 4,
num_epochs: int = 3,
learning_rate: float = 3e-4,
cutoff_len: int = 256,
val_set_size: int = 2000,
# lora hyperparams
lora_r: int = 8,
lora_alpha: int = 16,
lora_dropout: float = 0.05,
lora_target_modules: List[str] = [
"q_proj",
"v_proj",
],
# llm hyperparams
train_on_inputs: bool = True, # if False, masks out inputs in loss
group_by_length: bool = False, # faster, but produces an odd training loss curve
# wandb params
wandb_project: str = "",
wandb_run_name: str = "",
wandb_watch: str = "", # options: false | gradients | all
wandb_log_model: str = "", # options: false | true
resume_from_checkpoint: str = None, # either training checkpoint or final adapter
):
print(
f"Training Alpaca-LoRA model with params:\n"
f"base_model: {base_model}\n"
f"data_path: {data_path}\n"
f"output_dir: {output_dir}\n"
f"batch_size: {batch_size}\n"
f"micro_batch_size: {micro_batch_size}\n"
f"num_epochs: {num_epochs}\n"
f"learning_rate: {learning_rate}\n"
f"cutoff_len: {cutoff_len}\n"
f"val_set_size: {val_set_size}\n"
f"lora_r: {lora_r}\n"
f"lora_alpha: {lora_alpha}\n"
f"lora_dropout: {lora_dropout}\n"
f"lora_target_modules: {lora_target_modules}\n"
f"train_on_inputs: {train_on_inputs}\n"
f"group_by_length: {group_by_length}\n"
f"wandb_project: {wandb_project}\n"
f"wandb_run_name: {wandb_run_name}\n"
f"wandb_watch: {wandb_watch}\n"
f"wandb_log_model: {wandb_log_model}\n"
f"resume_from_checkpoint: {resume_from_checkpoint}\n"
)
assert (
base_model
), "Please specify a --base_model, e.g. --base_model='decapoda-research/llama-7b-hf'"
gradient_accumulation_steps = batch_size // micro_batch_size
device_map = "auto"
world_size = int(os.environ.get("WORLD_SIZE", 1))
ddp = world_size != 1
if ddp:
device_map = {"": int(os.environ.get("LOCAL_RANK") or 0)}
gradient_accumulation_steps = gradient_accumulation_steps // world_size
# Check if parameter passed or if set within environ
use_wandb = len(wandb_project) > 0 or (
"WANDB_PROJECT" in os.environ and len(os.environ["WANDB_PROJECT"]) > 0
)
# Only overwrite environ if wandb param passed
if len(wandb_project) > 0:
os.environ["WANDB_PROJECT"] = wandb_project
if len(wandb_watch) > 0:
os.environ["WANDB_WATCH"] = wandb_watch
if len(wandb_log_model) > 0:
os.environ["WANDB_LOG_MODEL"] = wandb_log_model
model = LlamaForCausalLM.from_pretrained(
base_model,
load_in_8bit=True,
torch_dtype=torch.float16,
device_map=device_map,
)
tokenizer = LlamaTokenizer.from_pretrained(base_model)
tokenizer.pad_token_id = (
0 # unk. we want this to be different from the eos token
)
tokenizer.padding_side = "left" # Allow batched inference
def tokenize(prompt, add_eos_token=True):
# there's probably a way to do this with the tokenizer settings
# but again, gotta move fast
result = tokenizer(
prompt,
truncation=True,
max_length=cutoff_len,
padding=False,
return_tensors=None,
)
if (
result["input_ids"][-1] != tokenizer.eos_token_id
and len(result["input_ids"]) < cutoff_len
and add_eos_token
):
result["input_ids"].append(tokenizer.eos_token_id)
result["attention_mask"].append(1)
result["labels"] = result["input_ids"].copy()
return result
def generate_and_tokenize_prompt(data_point):
full_prompt = generate_prompt(data_point)
tokenized_full_prompt = tokenize(full_prompt)
if not train_on_inputs:
user_prompt = generate_prompt({**data_point, "output": ""})
tokenized_user_prompt = tokenize(user_prompt, add_eos_token=False)
user_prompt_len = len(tokenized_user_prompt["input_ids"])
tokenized_full_prompt["labels"] = [
-100
] * user_prompt_len + tokenized_full_prompt["labels"][
user_prompt_len:
] # could be sped up, probably
return tokenized_full_prompt
model = prepare_model_for_int8_training(model)
config = LoraConfig(
r=lora_r,
lora_alpha=lora_alpha,
target_modules=lora_target_modules,
lora_dropout=lora_dropout,
bias="none",
task_type="CAUSAL_LM",
)
model = get_peft_model(model, config)
if data_path.endswith(".json"): # todo: support jsonl
data = load_dataset("json", data_files=data_path)
else:
data = load_dataset(data_path)
if resume_from_checkpoint:
# Check the available weights and load them
checkpoint_name = os.path.join(
resume_from_checkpoint, "pytorch_model.bin"
) # Full checkpoint
if not os.path.exists(checkpoint_name):
checkpoint_name = os.path.join(
resume_from_checkpoint, "adapter_model.bin"
) # only LoRA model - LoRA config above has to fit
resume_from_checkpoint = (
False # So the trainer won't try loading its state
)
# The two files above have a different name depending on how they were saved, but are actually the same.
if os.path.exists(checkpoint_name):
print(f"Restarting from {checkpoint_name}")
adapters_weights = torch.load(checkpoint_name)
model = set_peft_model_state_dict(model, adapters_weights)
else:
print(f"Checkpoint {checkpoint_name} not found")
model.print_trainable_parameters() # Be more transparent about the % of trainable params.
if val_set_size > 0:
train_val = data["train"].train_test_split(
test_size=val_set_size, shuffle=True, seed=42
)
train_data = (
train_val["train"].shuffle().map(generate_and_tokenize_prompt)
)
val_data = (
train_val["test"].shuffle().map(generate_and_tokenize_prompt)
)
else:
train_data = data["train"].shuffle().map(generate_and_tokenize_prompt)
val_data = None
if not ddp and torch.cuda.device_count() > 1:
# keeps Trainer from trying its own DataParallelism when more than 1 gpu is available
model.is_parallelizable = True
model.model_parallel = True
trainer = transformers.Trainer(
model=model,
train_dataset=train_data,
eval_dataset=val_data,
args=transformers.TrainingArguments(
per_device_train_batch_size=micro_batch_size,
gradient_accumulation_steps=gradient_accumulation_steps,
warmup_steps=100,
num_train_epochs=num_epochs,
learning_rate=learning_rate,
fp16=True,
logging_steps=10,
optim="adamw_torch",
evaluation_strategy="steps" if val_set_size > 0 else "no",
save_strategy="steps",
eval_steps=200 if val_set_size > 0 else None,
save_steps=200,
output_dir=output_dir,
save_total_limit=3,
load_best_model_at_end=True if val_set_size > 0 else False,
ddp_find_unused_parameters=False if ddp else None,
group_by_length=group_by_length,
report_to="wandb" if use_wandb else None,
run_name=wandb_run_name if use_wandb else None,
),
data_collator=transformers.DataCollatorForSeq2Seq(
tokenizer, pad_to_multiple_of=8, return_tensors="pt", padding=True
),
)
model.config.use_cache = False
old_state_dict = model.state_dict
model.state_dict = (
lambda self, *_, **__: get_peft_model_state_dict(
self, old_state_dict()
)
).__get__(model, type(model))
if torch.__version__ >= "2" and sys.platform != "win32":
model = torch.compile(model)
trainer.train(resume_from_checkpoint=resume_from_checkpoint)
model.save_pretrained(output_dir)
print(
"\n If there's a warning about missing keys above, please disregard :)"
)
def generate_prompt(data_point):
# sorry about the formatting disaster gotta move fast
if data_point["input"]:
return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. # noqa: E501
### Instruction:
{data_point["instruction"]}
### Input:
{data_point["input"]}
### Response:
{data_point["output"]}"""
else:
return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request. # noqa: E501
### Instruction:
{data_point["instruction"]}
### Response:
{data_point["output"]}"""
if __name__ == "__main__":
fire.Fire(train)