jiesutd / yato Goto Github PK
View Code? Open in Web Editor NEWYATO: Yet Another deep learning based Text analysis Open toolkit
License: Apache License 2.0
YATO: Yet Another deep learning based Text analysis Open toolkit
License: Apache License 2.0
I got the training type error as follow while training my Sequence Tagging model.
TypeError Traceback (most recent call last)
Cell In[23], line 3
1 from yato import YATO
2 model = YATO(configuration_file_myPOS_MyanBerta)
----> 3 model.train()
File /opt/conda/lib/python3.10/site-packages/yato/yato.py:38, in YATO.train(self, log, metric)
36 self.data.build_pretrain_emb()
37 self.data.summary()
---> 38 train(self.data, log, metric)
File /opt/conda/lib/python3.10/site-packages/yato/main.py:441, in train(data, log, metric)
439 logger.info("Training model...")
440 save_data_name = data.dset_dir
--> 441 data.save(save_data_name)
442 best_test = [{"acc": {"best test": 0, "best dev": 0, "epoch num": 0}},
443 {"f": {"best test": 0, "best dev": 0, "epoch num": 0}}]
444 metric_seq = ["acc", 'f']
File /opt/conda/lib/python3.10/site-packages/yato/utils/data.py:596, in Data.save(self, save_file)
595 def save(self, save_file):
--> 596 f = open(save_file, 'wb')
597 pickle.dump(self.dict, f, 2)
598 f.close()
TypeError: expected str, bytes or os.PathLike object, not NoneType
The following is my Config file
train_dir=/kaggle/input/myposv3-ncrfpp/train.bmes
dev_dir=/kaggle/input/myposv3-ncrfpp/train.bmes
test_dir=/kaggle/input/myposv3-ncrfpp/train.bmes
model_dir=/myPOS_MyanBerta/YATO_MODEL/myPOS_MyanBerta_model
#dset_dir=/myPOS_MyanBerta/YATO_MODEL/myPOS_MyanBerta_c03.dset
norm_word_emb=False
norm_char_emb=False
number_normalized=False
seg=True
word_emb_dim=50
char_emb_dim=30
###NetworkConfiguration###
use_crf=False
use_char=False
char_seq_feature=None
use_word_seq=False
use_word_emb=False
word_seq_feature=None
low_level_transformer=None
low_level_transformer_finetune=False
high_level_transformer=UCSYNLP/MyanBERTa
high_level_transformer_finetune=True
###TrainingSetting###
status=train
optimizer=AdamW
iteration=10
batch_size=16
ave_batch_loss=False
###Hyperparameters###
cnn_layer=4
char_hidden_dim=50
hidden_dim=768
dropout=0.3
lstm_layer=2
bilstm=True
learning_rate=3e-5
gpu=True
device=cuda:0
scheduler=get_cosine_schedule_with_warmup
warmup_step_rate=0.05
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.