alu/cse151b-final-project
1
0
Fork 0
mirror of https://github.com/ltcptgeneral/cse151b-final-project.git synced 2024-11-09 22:54:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

delete tests

Browse Source
This commit is contained in:
ltcptgeneral 2024-03-12 21:42:59 -07:00
parent c121415e31
commit 320f2f81b7
2 changed files with 0 additions and 226 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

165
test.ipynb
View File

File diff suppressed because one or more lines are too long

61
test.py
View File

@ -1,61 +0,0 @@
from torch.utils.data import Dataset
from transformers import BertGenerationEncoder, BertGenerationDecoder, EncoderDecoderModel, BertTokenizer
from tqdm import tqdm as progress_bar
import torch
import matplotlib
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
encoder = BertGenerationEncoder.from_pretrained("google-bert/bert-base-uncased", bos_token_id=101, eos_token_id=102)
# add cross attention layers and use BERT's cls token as BOS token and sep token as EOS token
decoder = BertGenerationDecoder.from_pretrained("google-bert/bert-base-uncased", add_cross_attention=True, is_decoder=True, bos_token_id=101, eos_token_id=102)
model = EncoderDecoderModel(encoder=encoder, decoder=decoder)
# create tokenizer...
tokenizer = BertTokenizer.from_pretrained("google-bert/bert-large-uncased")
import json
class CodeDataset(Dataset):
def __init__(self):
with open("data/conala-train.json") as f:
self.data = json.load(f)
def __len__(self):
return len(self.data)
def __getitem__(self, idx):
intent = self.data[idx]["rewritten_intent"] if self.data[idx]["rewritten_intent"] else self.data[idx]["intent"]
return intent, self.data[idx]["snippet"]
optimizer = torch.optim.AdamW(params=model.parameters(), lr=1e-3)
dataloader = CodeDataset()
model = model.to(device)
losses = []
epochs = 10
for i in range(epochs):
epoch_loss = 0
for idx, (question, answer) in progress_bar(enumerate(dataloader), total=len(dataloader)):
input_ids = tokenizer(question, add_special_tokens=False, return_tensors="pt").input_ids.to(device)
label_ids = tokenizer(answer, return_tensors="pt").input_ids.to(device)
loss = model(input_ids=input_ids, decoder_input_ids=label_ids, labels=label_ids).loss
optimizer.zero_grad()
loss.backward()
optimizer.step()
epoch_loss += loss.item()
losses.append(epoch_loss)
plt.plot(losses, color="green", label="Training Loss")
plt.legend(loc = 'upper left')
plt.savefig("plot.png")