File size: 5,536 Bytes
1e6d67a |
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 |
import os
import torch
from datasets import load_dataset
from torch.utils.data import DataLoader
from tqdm import tqdm
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, default_data_collator, get_linear_schedule_with_warmup
from peft import AdaLoraConfig, PeftConfig, PeftModel, TaskType, get_peft_model
os.environ["TOKENIZERS_PARALLELISM"] = "false"
device = "cuda"
model_name_or_path = "facebook/bart-base"
tokenizer_name_or_path = "facebook/bart-base"
checkpoint_name = "financial_sentiment_analysis_lora_v1.pt"
text_column = "sentence"
label_column = "text_label"
max_length = 128
lr = 1e-3
num_epochs = 8
batch_size = 8
# creating model
peft_config = AdaLoraConfig(
init_r=12,
target_r=8,
beta1=0.85,
beta2=0.85,
tinit=200,
tfinal=1000,
deltaT=10,
lora_alpha=32,
lora_dropout=0.1,
task_type=TaskType.SEQ_2_SEQ_LM,
inference_mode=False,
)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name_or_path)
model = get_peft_model(model, peft_config)
model.print_trainable_parameters()
# loading dataset
dataset = load_dataset("financial_phrasebank", "sentences_allagree")
dataset = dataset["train"].train_test_split(test_size=0.1)
dataset["validation"] = dataset["test"]
del dataset["test"]
classes = dataset["train"].features["label"].names
dataset = dataset.map(
lambda x: {"text_label": [classes[label] for label in x["label"]]},
batched=True,
num_proc=1,
)
# data preprocessing
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
def preprocess_function(examples):
inputs = examples[text_column]
targets = examples[label_column]
model_inputs = tokenizer(inputs, max_length=max_length, padding="max_length", truncation=True, return_tensors="pt")
labels = tokenizer(targets, max_length=3, padding="max_length", truncation=True, return_tensors="pt")
labels = labels["input_ids"]
labels[labels == tokenizer.pad_token_id] = -100
model_inputs["labels"] = labels
return model_inputs
processed_datasets = dataset.map(
preprocess_function,
batched=True,
num_proc=1,
remove_columns=dataset["train"].column_names,
load_from_cache_file=False,
desc="Running tokenizer on dataset",
)
train_dataset = processed_datasets["train"]
eval_dataset = processed_datasets["validation"]
train_dataloader = DataLoader(
train_dataset, shuffle=True, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True
)
eval_dataloader = DataLoader(eval_dataset, collate_fn=default_data_collator, batch_size=batch_size, pin_memory=True)
# optimizer and lr scheduler
optimizer = torch.optim.AdamW(model.parameters(), lr=lr)
lr_scheduler = get_linear_schedule_with_warmup(
optimizer=optimizer,
num_warmup_steps=0,
num_training_steps=(len(train_dataloader) * num_epochs),
)
model.base_model.peft_config.total_step = len(train_dataloader) * num_epochs
# training and evaluation
model = model.to(device)
global_step = 0
for epoch in range(num_epochs):
model.train()
total_loss = 0
for step, batch in enumerate(tqdm(train_dataloader)):
batch = {k: v.to(device) for k, v in batch.items()}
outputs = model(**batch)
loss = outputs.loss
total_loss += loss.detach().float()
loss.backward()
optimizer.step()
lr_scheduler.step()
# Update the importance of low-rank matrices
# and allocate the budget accordingly.
model.base_model.update_and_allocate(global_step)
optimizer.zero_grad()
global_step += 1
model.eval()
eval_loss = 0
eval_preds = []
for step, batch in enumerate(tqdm(eval_dataloader)):
batch = {k: v.to(device) for k, v in batch.items()}
with torch.no_grad():
outputs = model(**batch)
loss = outputs.loss
eval_loss += loss.detach().float()
eval_preds.extend(
tokenizer.batch_decode(torch.argmax(outputs.logits, -1).detach().cpu().numpy(), skip_special_tokens=True)
)
eval_epoch_loss = eval_loss / len(train_dataloader)
eval_ppl = torch.exp(eval_epoch_loss)
train_epoch_loss = total_loss / len(eval_dataloader)
train_ppl = torch.exp(train_epoch_loss)
print(f"{epoch=}: {train_ppl=} {train_epoch_loss=} {eval_ppl=} {eval_epoch_loss=}")
# print accuracy
correct = 0
total = 0
for pred, true in zip(eval_preds, dataset["validation"]["text_label"]):
if pred.strip() == true.strip():
correct += 1
total += 1
accuracy = correct / total * 100
print(f"{accuracy=} % on the evaluation dataset")
print(f"{eval_preds[:10]=}")
print(f"{dataset['validation']['text_label'][:10]=}")
# saving model
peft_model_id = f"{model_name_or_path}_{peft_config.peft_type}_{peft_config.task_type}"
model.save_pretrained(peft_model_id)
ckpt = f"{peft_model_id}/adapter_model.bin"
# get_ipython().system('du -h $ckpt')
peft_model_id = f"{model_name_or_path}_{peft_config.peft_type}_{peft_config.task_type}"
config = PeftConfig.from_pretrained(peft_model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(config.base_model_name_or_path)
model = PeftModel.from_pretrained(model, peft_model_id)
model.eval()
i = 13
inputs = tokenizer(dataset["validation"][text_column][i], return_tensors="pt")
print(dataset["validation"][text_column][i])
print(inputs)
with torch.no_grad():
outputs = model.generate(input_ids=inputs["input_ids"], max_new_tokens=10)
print(outputs)
print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True))
|