I followed the instructions from nlp branch but encountered the following error messages
(conda_BuilT) testmony@testmony-desktop:~/workspace/tweet/BuilT (nlp)$ sh ./train.sh
Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /home/testmony/.kaggle/kaggle.json'
Downloading tweet-sentiment-extraction.zip to input
72%|███████████████████████████████████████▍ | 1.00M/1.39M [00:00<00:00, 3.27MB/s]
100%|███████████████████████████████████████████████████████| 1.39M/1.39M [00:00<00:00, 3.55MB/s]
Archive: input/tweet-sentiment-extraction.zip
inflating: input/tweet-sentiment-extraction/sample_submission.csv
inflating: input/tweet-sentiment-extraction/test.csv
inflating: input/tweet-sentiment-extraction/train.csv
Warning: Your Kaggle API key is readable by other users on this system! To fix this, you can run 'chmod 600 /home/testmony/.kaggle/kaggle.json'
Downloading roberta-base.zip to input/roberta-base
100%|████████████████████████████████████████████████████████▉| 291M/291M [01:11<00:00, 4.86MB/s]
100%|█████████████████████████████████████████████████████████| 291M/291M [01:11<00:00, 4.26MB/s]
WARNING - orsum - No observers have been added to this run
INFO - orsum - Running command 'train'
INFO - orsum - Started
{ 'dataset': { 'name': 'TweetDataset',
'params': { 'csv_path': 'tweet/input/tweet-sentiment-extraction/train.csv',
'max_len': 96,
'model_path': 'tweet/input/roberta-base/'},
'splits': None},
'description': 'Tweet Sentiment Classification',
'evaluation': {'batch_size': 8},
'forward_hook': {'name': 'TweetForwardHook'},
'logger_hook': { 'name': 'DefaultLogger',
'params': {'use_tensorboard': True, 'use_wandb': False}},
'loss': {'name': 'TweetLoss'},
'metric_hook': {'name': 'TweetMetric'},
'model': { 'name': 'TweetExtractModel',
'params': { 'drop_out_rate': 0.1,
'num_classes': 3,
'transformer_path': 'tweet/input/roberta-base/',
'transformer_type': 'roberta'}},
'optimizer': {'name': 'AdamW', 'params': {'lr': 3e-05}},
'post_forward_hook': {'name': 'TweetPostForwardHook'},
'scheduler': { 'name': 'MultiStepLR',
'params': {'gamma': 0.1, 'milestones': [3, 4, 5]}},
'seed': 478623980,
'splitter': { 'name': 'TweetSplitter',
'params': { 'csv_path': 'tweet/input/tweet-sentiment-extraction/train.csv',
'n_splits': 5,
'random_state': 42,
'shuffle': True}},
'train': { 'batch_size': 256,
'dir': 'train_dirs/tweet_classification',
'gradient_accumulation_step': 1,
'name': '',
'num_epochs': 2},
'transforms': { 'name': '',
'num_preprocessor': 1,
'params': [ {'ToTensor': None, 'name': 'ToTensor'},
{ 'Normalize': None,
'name': 'Normalize',
'params': { 'mean': [0.1307],
'std': [0.3081]}}]},
'wandb': {'sweep': {'name': 'Sweep', 'use': False, 'yaml': 'sweep.yaml'}}}
./tweet
<module 'tweet_coverage_model' from './tweet/tweet_coverage_model.py'> is loaded
2020-11-18 23:00:34.809912: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer.so.6'; dlerror: libnvinfer.so.6: cannot open shared object file: No such file or directory
2020-11-18 23:00:34.809979: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libnvinfer_plugin.so.6'; dlerror: libnvinfer_plugin.so.6: cannot open shared object file: No such file or directory
2020-11-18 23:00:34.809986: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:30] Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
INFO - matplotlib.font_manager - Could not open font file /usr/share/fonts/truetype/noto/NotoColorEmoji.ttf: In FT2Font: Can not load face. Unknown file format.
INFO - matplotlib.font_manager - generated new fontManager
<module 'tweet_dataset' from './tweet/tweet_dataset.py'> is loaded
<module 'tweet_extract_model' from './tweet/tweet_extract_model.py'> is loaded
<module 'tweet_forward_hook' from './tweet/tweet_forward_hook.py'> is loaded
<module 'tweet_loss' from './tweet/tweet_loss.py'> is loaded
<module 'tweet_metric' from './tweet/tweet_metric.py'> is loaded
<module 'tweet_post_forward_hook' from './tweet/tweet_post_forward_hook.py'> is loaded
<module 'tweet_splitter' from './tweet/tweet_splitter.py'> is loaded
Training start: 0 fold
Segmentation fault (core dumped)
python[10332]: segfault at 7f0b0000556f ip 00007f0b0000556f sp 00007ffe2b94ad48 error 7 in _pywrap_tensorflow_internal.so[7f0af6474000+41514000]
[ 1562.083556] Code: 85 c0 74 5f 48 8d 7d a0 ba 03 00 00 00 48 89 fe c5 f8 77 ff d0 48 8b 83 50 01 00 00 48 85 c0 74 11 48 8d bb 40 01 00 00 ba 03 <00> 00 00 48 89 fe ff d0 48 8b bb 08 01 00 00 48 85 ff 74 05 e8 78
Package Version
---------------------- -------------------
absl-py 0.11.0
astor 0.8.1
astroid 2.4.2
cached-property 1.5.2
cachetools 4.1.1
certifi 2020.6.20
chardet 3.0.4
click 7.1.2
colorama 0.4.4
configparser 5.0.1
cycler 0.10.0
decorator 4.4.2
docker-pycreds 0.4.0
docopt 0.6.2
easydict 1.9
efficientnet-pytorch 0.6.3
filelock 3.0.12
gast 0.2.2
gitdb 4.0.5
GitPython 3.1.11
google-auth 1.23.0
google-auth-oauthlib 0.4.2
google-pasta 0.2.0
gql 0.2.0
graphql-core 1.1
grpcio 1.33.2
h5py 3.1.0
idna 2.10
imageio 2.6.1
importlib-metadata 2.0.0
isort 4.3.21
joblib 0.17.0
jsonpickle 1.4.1
kaggle 1.5.9
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.2
kiwisolver 1.3.1
lazy-object-proxy 1.4.3
Markdown 3.3.3
matplotlib 3.1.3
mccabe 0.6.1
munch 2.5.0
networkx 2.5
numpy 1.18.1
nvidia-ml-py3 7.352.0
oauthlib 3.1.0
opencv-python 4.2.0.32
opt-einsum 3.3.0
packaging 20.4
pandas 1.0.0
pathtools 0.1.2
pep8 1.7.1
pickleshare 0.7.5
Pillow 7.0.0
pip 20.2.4
promise 2.3
protobuf 3.14.0
psutil 5.7.3
py-cpuinfo 7.0.0
pyasn1 0.4.8
pyasn1-modules 0.2.8
pylint 2.3.1
pyparsing 2.4.7
python-dateutil 2.8.1
python-slugify 4.0.1
pytz 2020.4
PyWavelets 1.1.1
PyYAML 5.3.1
regex 2020.11.13
requests 2.25.0
requests-oauthlib 1.3.0
rsa 4.6
sacred 0.8.1
sacremoses 0.0.43
scikit-image 0.16.2
scikit-learn 0.23.1
scipy 1.4.1
sentencepiece 0.1.94
sentry-sdk 0.19.3
setuptools 50.3.1.post20201107
shortuuid 1.0.1
six 1.15.0
slugify 0.0.1
smmap 3.0.4
subprocess32 3.5.4
tensorboard 2.2.2
tensorboard-plugin-wit 1.7.0
tensorflow-estimator 2.1.0
tensorflow-gpu 2.1.0
termcolor 1.1.0
text-unidecode 1.3
threadpoolctl 2.1.0
tokenizer 2.0.6
tokenizers 0.8.1rc2
torch 1.4.0
torchvision 0.5.0
tqdm 4.47.0
transformers 3.1.0
typed-ast 1.4.1
urllib3 1.26.2
wandb 0.9.4
watchdog 0.10.3
Werkzeug 1.0.1
wheel 0.35.1
wrapt 1.12.1
zipp 3.4.0