yujiepan
commited on
Commit
•
0cbcfe1
0
Parent(s):
upload model
Browse files- .gitattributes +35 -0
- README.md +108 -0
- compressed_graph.dot +0 -0
- conda-requirements.txt +229 -0
- config.json +35 -0
- eval_results.json +8 -0
- nncf_config.json +49 -0
- nncf_output.log +0 -0
- openvino_config.json +82 -0
- openvino_model.bin +3 -0
- openvino_model.xml +0 -0
- original_graph.dot +0 -0
- pip-requirements.txt +213 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- train_results.json +8 -0
- trainer_state.json +3 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitattributes
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
trainer_state.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- glue
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: yujiepan/bert-base-uncased-sst2-int8-unstructured80-17epoch
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: GLUE SST2
|
18 |
+
type: glue
|
19 |
+
config: sst2
|
20 |
+
split: validation
|
21 |
+
args: sst2
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.91284
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# Joint magnitude pruning, quantization and distillation on BERT-base/SST-2
|
32 |
+
|
33 |
+
This model conducts unstructured magnitude pruning, quantization and distillation at the same time when finetuning on the GLUE SST2 dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Torch loss: 0.3858
|
36 |
+
- Torch accuracy: 0.9128
|
37 |
+
- OpenVINO IR accuracy: 0.9128
|
38 |
+
- Sparsity in transformer block linear layers: 0.80
|
39 |
+
|
40 |
+
## Setup
|
41 |
+
|
42 |
+
```
|
43 |
+
conda install pytorch torchvision torchaudio pytorch-cuda=11.6 -c pytorch -c nvidia
|
44 |
+
git clone https://github.com/yujiepan-work/optimum-intel.git
|
45 |
+
git checkout -b "magnitude-pruning" 01927af543eaea8678671bf8f4eb78fdb29f8930
|
46 |
+
cd optimum-intel
|
47 |
+
pip install -e .[openvino,nncf]
|
48 |
+
|
49 |
+
cd examples/openvino/text-classification/
|
50 |
+
pip install -r requirements.txt
|
51 |
+
pip install wandb # optional
|
52 |
+
```
|
53 |
+
|
54 |
+
## NNCF config
|
55 |
+
|
56 |
+
See `nncf_config.json` in this repo.
|
57 |
+
|
58 |
+
|
59 |
+
## Run
|
60 |
+
|
61 |
+
We use one card for training.
|
62 |
+
|
63 |
+
```
|
64 |
+
NNCFCFG=/path/to/nncf/config
|
65 |
+
python run_glue.py \
|
66 |
+
--lr_scheduler_type cosine_with_restarts \
|
67 |
+
--cosine_cycle_ratios 11,6 \
|
68 |
+
--cosine_cycle_decays 1,1 \
|
69 |
+
--save_best_model_after_epoch -1 \
|
70 |
+
--save_best_model_after_sparsity 0.7999 \
|
71 |
+
--model_name_or_path textattack/bert-base-uncased-SST-2 \
|
72 |
+
--teacher_model_or_path yoshitomo-matsubara/bert-large-uncased-sst2 \
|
73 |
+
--distillation_temperature 2 \
|
74 |
+
--task_name sst2 \
|
75 |
+
--nncf_compression_config $NNCFCFG \
|
76 |
+
--distillation_weight 0.95 \
|
77 |
+
--output_dir /tmp/bert-base-uncased-sst2-int8-unstructured80-17epoch \
|
78 |
+
--run_name bert-base-uncased-sst2-int8-unstructured80-17epoch \
|
79 |
+
--overwrite_output_dir \
|
80 |
+
--do_train \
|
81 |
+
--do_eval \
|
82 |
+
--max_seq_length 128 \
|
83 |
+
--per_device_train_batch_size 32 \
|
84 |
+
--per_device_eval_batch_size 32 \
|
85 |
+
--learning_rate 5e-05 \
|
86 |
+
--optim adamw_torch \
|
87 |
+
--num_train_epochs 17 \
|
88 |
+
--logging_steps 1 \
|
89 |
+
--evaluation_strategy steps \
|
90 |
+
--eval_steps 250 \
|
91 |
+
--save_strategy steps \
|
92 |
+
--save_steps 250 \
|
93 |
+
--save_total_limit 1 \
|
94 |
+
--fp16 \
|
95 |
+
--seed 1
|
96 |
+
```
|
97 |
+
|
98 |
+
The best model checkpoint is stored in the `best_model` folder. Here we only upload that checkpoint folder together with some config files.
|
99 |
+
|
100 |
+
|
101 |
+
### Framework versions
|
102 |
+
|
103 |
+
- Transformers 4.26.0
|
104 |
+
- Pytorch 1.13.1+cu116
|
105 |
+
- Datasets 2.8.0
|
106 |
+
- Tokenizers 0.13.2
|
107 |
+
|
108 |
+
For a full description of the environment, please refer to `pip-requirements.txt` and `conda-requirements.txt`.
|
compressed_graph.dot
ADDED
The diff for this file is too large to render.
See raw diff
|
|
conda-requirements.txt
ADDED
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# This file may be used to create an environment using:
|
2 |
+
# $ conda create --name <env> --file <this file>
|
3 |
+
# platform: linux-64
|
4 |
+
_libgcc_mutex=0.1=main
|
5 |
+
_openmp_mutex=5.1=1_gnu
|
6 |
+
addict=2.4.0=pypi_0
|
7 |
+
aiofiles=22.1.0=pypi_0
|
8 |
+
aiohttp=3.8.3=pypi_0
|
9 |
+
aiosignal=1.3.1=pypi_0
|
10 |
+
aiosqlite=0.18.0=pypi_0
|
11 |
+
alembic=1.9.2=pypi_0
|
12 |
+
anyio=3.6.2=pypi_0
|
13 |
+
appdirs=1.4.4=pypi_0
|
14 |
+
argon2-cffi=21.3.0=pypi_0
|
15 |
+
argon2-cffi-bindings=21.2.0=pypi_0
|
16 |
+
arrow=1.2.3=pypi_0
|
17 |
+
asttokens=2.2.1=pyhd8ed1ab_0
|
18 |
+
async-timeout=4.0.2=pypi_0
|
19 |
+
attrs=22.1.0=pypi_0
|
20 |
+
audioread=3.0.0=pypi_0
|
21 |
+
autoflake=2.0.0=pypi_0
|
22 |
+
autograd=1.5=pypi_0
|
23 |
+
autopep8=2.0.1=pypi_0
|
24 |
+
babel=2.11.0=pypi_0
|
25 |
+
backcall=0.2.0=pyh9f0ad1d_0
|
26 |
+
backports=1.0=pyhd8ed1ab_3
|
27 |
+
backports.functools_lru_cache=1.6.4=pyhd8ed1ab_0
|
28 |
+
beautifulsoup4=4.11.2=pypi_0
|
29 |
+
black=22.12.0=pypi_0
|
30 |
+
bleach=6.0.0=pypi_0
|
31 |
+
ca-certificates=2022.12.7=ha878542_0
|
32 |
+
certifi=2022.12.7=pypi_0
|
33 |
+
cffi=1.15.1=pypi_0
|
34 |
+
charset-normalizer=2.1.1=pypi_0
|
35 |
+
click=8.1.3=pypi_0
|
36 |
+
cma=2.7.0=pypi_0
|
37 |
+
cmaes=0.9.1=pypi_0
|
38 |
+
coloredlogs=15.0.1=pypi_0
|
39 |
+
colorlog=6.7.0=pypi_0
|
40 |
+
comm=0.1.2=pyhd8ed1ab_0
|
41 |
+
cudatoolkit=11.6.0=habf752d_9
|
42 |
+
cycler=0.11.0=pypi_0
|
43 |
+
datasets=2.8.0=pypi_0
|
44 |
+
debugpy=1.6.4=pypi_0
|
45 |
+
decorator=5.1.1=pyhd8ed1ab_0
|
46 |
+
defusedxml=0.7.1=pypi_0
|
47 |
+
dill=0.3.6=pypi_0
|
48 |
+
docker-pycreds=0.4.0=pypi_0
|
49 |
+
entrypoints=0.4=pyhd8ed1ab_0
|
50 |
+
evaluate=0.4.0=pypi_0
|
51 |
+
executing=1.2.0=pyhd8ed1ab_0
|
52 |
+
fastjsonschema=2.16.2=pypi_0
|
53 |
+
filelock=3.8.2=pypi_0
|
54 |
+
flake8=6.0.0=pypi_0
|
55 |
+
fonttools=4.38.0=pypi_0
|
56 |
+
fqdn=1.5.1=pypi_0
|
57 |
+
frozenlist=1.3.3=pypi_0
|
58 |
+
fsspec=2022.11.0=pypi_0
|
59 |
+
future=0.18.2=pypi_0
|
60 |
+
gitdb=4.0.10=pypi_0
|
61 |
+
gitpython=3.1.29=pypi_0
|
62 |
+
greenlet=2.0.2=pypi_0
|
63 |
+
huggingface-hub=0.11.1=pypi_0
|
64 |
+
humanfriendly=10.0=pypi_0
|
65 |
+
idna=3.4=pypi_0
|
66 |
+
importlib-metadata=5.2.0=pypi_0
|
67 |
+
importlib-resources=5.10.2=pypi_0
|
68 |
+
ipykernel=6.20.2=pyh210e3f2_0
|
69 |
+
ipython=8.9.0=pyh41d4057_0
|
70 |
+
ipython-genutils=0.2.0=pypi_0
|
71 |
+
ipywidgets=8.0.4=pypi_0
|
72 |
+
isoduration=20.11.0=pypi_0
|
73 |
+
isort=5.11.4=pypi_0
|
74 |
+
jedi=0.18.2=pyhd8ed1ab_0
|
75 |
+
jinja2=3.1.2=pypi_0
|
76 |
+
joblib=1.2.0=pypi_0
|
77 |
+
json5=0.9.11=pypi_0
|
78 |
+
jsonpointer=2.3=pypi_0
|
79 |
+
jsonschema=4.17.3=pypi_0
|
80 |
+
jstyleson=0.0.2=pypi_0
|
81 |
+
jupyter-client=8.0.2=pypi_0
|
82 |
+
jupyter-events=0.5.0=pypi_0
|
83 |
+
jupyter-server=2.2.1=pypi_0
|
84 |
+
jupyter-server-fileid=0.6.0=pypi_0
|
85 |
+
jupyter-server-terminals=0.4.4=pypi_0
|
86 |
+
jupyter-server-ydoc=0.6.1=pypi_0
|
87 |
+
jupyter-ydoc=0.2.2=pypi_0
|
88 |
+
jupyter_core=5.1.5=py38h578d9bd_0
|
89 |
+
jupyterlab=3.6.1=pypi_0
|
90 |
+
jupyterlab-pygments=0.2.2=pypi_0
|
91 |
+
jupyterlab-server=2.19.0=pypi_0
|
92 |
+
jupyterlab-widgets=3.0.5=pypi_0
|
93 |
+
kiwisolver=1.4.4=pypi_0
|
94 |
+
ld_impl_linux-64=2.38=h1181459_1
|
95 |
+
libedit=3.1.20221030=h5eee18b_0
|
96 |
+
libffi=3.4.2=h6a678d5_6
|
97 |
+
libgcc-ng=11.2.0=h1234567_1
|
98 |
+
libgomp=11.2.0=h1234567_1
|
99 |
+
librosa=0.9.2=pypi_0
|
100 |
+
libsodium=1.0.18=h36c2ea0_1
|
101 |
+
libstdcxx-ng=11.2.0=h1234567_1
|
102 |
+
llvmlite=0.39.1=pypi_0
|
103 |
+
mako=1.2.4=pypi_0
|
104 |
+
markupsafe=2.1.2=pypi_0
|
105 |
+
matplotlib=3.5.3=pypi_0
|
106 |
+
matplotlib-inline=0.1.6=pyhd8ed1ab_0
|
107 |
+
mistune=2.0.5=pypi_0
|
108 |
+
mpmath=1.2.1=pypi_0
|
109 |
+
multidict=6.0.3=pypi_0
|
110 |
+
multiprocess=0.70.14=pypi_0
|
111 |
+
mypy-extensions=0.4.3=pypi_0
|
112 |
+
natsort=8.2.0=pypi_0
|
113 |
+
nbclassic=0.5.1=pypi_0
|
114 |
+
nbclient=0.7.2=pypi_0
|
115 |
+
nbconvert=7.2.9=pypi_0
|
116 |
+
nbformat=5.7.3=pypi_0
|
117 |
+
ncurses=6.3=h5eee18b_3
|
118 |
+
nest-asyncio=1.5.6=pyhd8ed1ab_0
|
119 |
+
networkx=2.8.8=pypi_0
|
120 |
+
ninja=1.10.2.4=pypi_0
|
121 |
+
nncf=2.4.0.dev0+c02f9f3=pypi_0
|
122 |
+
notebook=6.5.2=pypi_0
|
123 |
+
notebook-shim=0.2.2=pypi_0
|
124 |
+
ntplib=0.4.0=pypi_0
|
125 |
+
numba=0.56.4=pypi_0
|
126 |
+
numpy=1.23.4=pypi_0
|
127 |
+
onnx=1.13.0=pypi_0
|
128 |
+
opencv-python=4.7.0.68=pypi_0
|
129 |
+
openssl=1.1.1s=h7f8727e_0
|
130 |
+
openvino=2023.0.0.dev20230119=pypi_0
|
131 |
+
openvino-dev=2023.0.0.dev20230119=pypi_0
|
132 |
+
openvino-telemetry=2022.3.0=pypi_0
|
133 |
+
optimum=1.6.3=pypi_0
|
134 |
+
optimum-intel=1.7.0.dev0=pypi_0
|
135 |
+
optuna=3.1.0=pypi_0
|
136 |
+
packaging=22.0=pypi_0
|
137 |
+
pandas=1.3.5=pypi_0
|
138 |
+
pandocfilters=1.5.0=pypi_0
|
139 |
+
parameterized=0.8.1=pypi_0
|
140 |
+
parso=0.8.3=pyhd8ed1ab_0
|
141 |
+
pathspec=0.10.3=pypi_0
|
142 |
+
pathtools=0.1.2=pypi_0
|
143 |
+
pexpect=4.8.0=pyh1a96a4e_2
|
144 |
+
pickleshare=0.7.5=py_1003
|
145 |
+
pillow=9.4.0=pypi_0
|
146 |
+
pip=22.3.1=py38h06a4308_0
|
147 |
+
pkgutil-resolve-name=1.3.10=pypi_0
|
148 |
+
platformdirs=2.6.2=pyhd8ed1ab_0
|
149 |
+
pooch=1.6.0=pypi_0
|
150 |
+
prometheus-client=0.16.0=pypi_0
|
151 |
+
promise=2.3=pypi_0
|
152 |
+
prompt-toolkit=3.0.36=pyha770c72_0
|
153 |
+
protobuf=3.20.2=pypi_0
|
154 |
+
psutil=5.9.0=py38h5eee18b_0
|
155 |
+
ptyprocess=0.7.0=pyhd3deb0d_0
|
156 |
+
pure_eval=0.2.2=pyhd8ed1ab_0
|
157 |
+
pyarrow=10.0.1=pypi_0
|
158 |
+
pycodestyle=2.10.0=pypi_0
|
159 |
+
pycparser=2.21=pypi_0
|
160 |
+
pydot=1.4.2=pypi_0
|
161 |
+
pyflakes=3.0.1=pypi_0
|
162 |
+
pygments=2.14.0=pyhd8ed1ab_0
|
163 |
+
pymoo=0.5.0=pypi_0
|
164 |
+
pyparsing=2.4.7=pypi_0
|
165 |
+
pyrsistent=0.19.2=pypi_0
|
166 |
+
python=3.8.15=h7a1cb2a_2
|
167 |
+
python-dateutil=2.8.2=pyhd8ed1ab_0
|
168 |
+
python-json-logger=2.0.4=pypi_0
|
169 |
+
python_abi=3.8=2_cp38
|
170 |
+
pytz=2022.7.1=pypi_0
|
171 |
+
pyyaml=6.0=pypi_0
|
172 |
+
pyzmq=25.0.0=pypi_0
|
173 |
+
readline=8.2=h5eee18b_0
|
174 |
+
regex=2022.10.31=pypi_0
|
175 |
+
requests=2.28.2=pypi_0
|
176 |
+
resampy=0.4.2=pypi_0
|
177 |
+
responses=0.18.0=pypi_0
|
178 |
+
rfc3339-validator=0.1.4=pypi_0
|
179 |
+
rfc3986-validator=0.1.1=pypi_0
|
180 |
+
scikit-learn=1.2.0=pypi_0
|
181 |
+
scipy=1.10.0=pypi_0
|
182 |
+
send2trash=1.8.0=pypi_0
|
183 |
+
sentencepiece=0.1.97=pypi_0
|
184 |
+
sentry-sdk=1.12.1=pypi_0
|
185 |
+
setproctitle=1.3.2=pypi_0
|
186 |
+
setuptools=65.5.0=py38h06a4308_0
|
187 |
+
shortuuid=1.0.11=pypi_0
|
188 |
+
six=1.16.0=pyh6c4a22f_0
|
189 |
+
smmap=5.0.0=pypi_0
|
190 |
+
sniffio=1.3.0=pypi_0
|
191 |
+
soundfile=0.11.0=pypi_0
|
192 |
+
soupsieve=2.3.2.post1=pypi_0
|
193 |
+
sqlalchemy=2.0.1=pypi_0
|
194 |
+
sqlite=3.40.0=h5082296_0
|
195 |
+
stack_data=0.6.2=pyhd8ed1ab_0
|
196 |
+
sympy=1.11.1=pypi_0
|
197 |
+
terminado=0.17.1=pypi_0
|
198 |
+
texttable=1.6.7=pypi_0
|
199 |
+
threadpoolctl=3.1.0=pypi_0
|
200 |
+
tinycss2=1.2.1=pypi_0
|
201 |
+
tk=8.6.12=h1ccaba5_0
|
202 |
+
tokenizers=0.13.2=pypi_0
|
203 |
+
tomli=2.0.1=pypi_0
|
204 |
+
torch=1.13.1+cu116=pypi_0
|
205 |
+
torchaudio=0.13.1+cu116=pypi_0
|
206 |
+
torchvision=0.14.1+cu116=pypi_0
|
207 |
+
tornado=6.2=pypi_0
|
208 |
+
tqdm=4.64.1=pypi_0
|
209 |
+
traitlets=5.8.1=pyhd8ed1ab_0
|
210 |
+
transformers=4.26.0=pypi_0
|
211 |
+
typing-extensions=4.4.0=hd8ed1ab_0
|
212 |
+
typing_extensions=4.4.0=pyha770c72_0
|
213 |
+
uri-template=1.2.0=pypi_0
|
214 |
+
urllib3=1.26.14=pypi_0
|
215 |
+
wandb=0.13.7=pypi_0
|
216 |
+
wcwidth=0.2.6=pyhd8ed1ab_0
|
217 |
+
webcolors=1.12=pypi_0
|
218 |
+
webencodings=0.5.1=pypi_0
|
219 |
+
websocket-client=1.5.1=pypi_0
|
220 |
+
wheel=0.37.1=pyhd3eb1b0_0
|
221 |
+
widgetsnbextension=4.0.5=pypi_0
|
222 |
+
xxhash=3.1.0=pypi_0
|
223 |
+
xz=5.2.8=h5eee18b_0
|
224 |
+
y-py=0.5.5=pypi_0
|
225 |
+
yarl=1.8.2=pypi_0
|
226 |
+
ypy-websocket=0.8.2=pypi_0
|
227 |
+
zeromq=4.3.4=h9c3ff4c_1
|
228 |
+
zipp=3.11.0=pypi_0
|
229 |
+
zlib=1.2.13=h5eee18b_0
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "textattack/bert-base-uncased-SST-2",
|
3 |
+
"architectures": [
|
4 |
+
"NNCFNetwork"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "sst2",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "negative",
|
14 |
+
"1": "positive"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"negative": 0,
|
20 |
+
"positive": 1
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.26.0",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 30522
|
35 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.9128440366972477,
|
3 |
+
"eval_loss": 0.38576310873031616,
|
4 |
+
"eval_runtime": 6.8627,
|
5 |
+
"eval_samples_per_second": 127.064,
|
6 |
+
"eval_steps_per_second": 4.08
|
7 |
+
}
|
8 |
+
|
nncf_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"algorithm": "quantization",
|
4 |
+
"preset": "mixed",
|
5 |
+
"overflow_fix": "disable",
|
6 |
+
"initializer": {
|
7 |
+
"range": {
|
8 |
+
"num_init_samples": 300,
|
9 |
+
"type": "mean_min_max"
|
10 |
+
},
|
11 |
+
"batchnorm_adaptation": {
|
12 |
+
"num_bn_adaptation_samples": 0
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"scope_overrides": {
|
16 |
+
"activations": {
|
17 |
+
"{re}.*matmul_0": {
|
18 |
+
"mode": "symmetric"
|
19 |
+
}
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"ignored_scopes": [
|
23 |
+
"{re}.*Embeddings.*",
|
24 |
+
"{re}.*__add___[0-1]",
|
25 |
+
"{re}.*layer_norm_0",
|
26 |
+
"{re}.*matmul_1",
|
27 |
+
"{re}.*__truediv__*"
|
28 |
+
]
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"algorithm": "magnitude_sparsity",
|
32 |
+
"ignored_scopes": [
|
33 |
+
"{re}.*NNCFEmbedding.*",
|
34 |
+
"{re}.*LayerNorm.*",
|
35 |
+
"{re}.*pooler.*",
|
36 |
+
"{re}.*classifier.*"
|
37 |
+
],
|
38 |
+
"sparsity_init": 0.0,
|
39 |
+
"params": {
|
40 |
+
"power": 3,
|
41 |
+
"schedule": "polynomial",
|
42 |
+
"sparsity_freeze_epoch": 10,
|
43 |
+
"sparsity_target": 0.8,
|
44 |
+
"sparsity_target_epoch": 9,
|
45 |
+
"steps_per_epoch": 2105,
|
46 |
+
"update_per_optimizer_step": true
|
47 |
+
}
|
48 |
+
}
|
49 |
+
]
|
nncf_output.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|
openvino_config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"compression": [
|
3 |
+
{
|
4 |
+
"algorithm": "quantization",
|
5 |
+
"export_to_onnx_standard_ops": false,
|
6 |
+
"ignored_scopes": [
|
7 |
+
"{re}.*Embeddings.*",
|
8 |
+
"{re}.*__add___[0-1]",
|
9 |
+
"{re}.*layer_norm_0",
|
10 |
+
"{re}.*matmul_1",
|
11 |
+
"{re}.*__truediv__*"
|
12 |
+
],
|
13 |
+
"initializer": {
|
14 |
+
"batchnorm_adaptation": {
|
15 |
+
"num_bn_adaptation_samples": 0
|
16 |
+
},
|
17 |
+
"range": {
|
18 |
+
"num_init_samples": 300,
|
19 |
+
"type": "mean_min_max"
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"overflow_fix": "disable",
|
23 |
+
"preset": "mixed",
|
24 |
+
"scope_overrides": {
|
25 |
+
"activations": {
|
26 |
+
"{re}.*matmul_0": {
|
27 |
+
"mode": "symmetric"
|
28 |
+
}
|
29 |
+
}
|
30 |
+
}
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"algorithm": "magnitude_sparsity",
|
34 |
+
"ignored_scopes": [
|
35 |
+
"{re}.*NNCFEmbedding.*",
|
36 |
+
"{re}.*LayerNorm.*",
|
37 |
+
"{re}.*pooler.*",
|
38 |
+
"{re}.*classifier.*"
|
39 |
+
],
|
40 |
+
"params": {
|
41 |
+
"power": 3,
|
42 |
+
"schedule": "polynomial",
|
43 |
+
"sparsity_freeze_epoch": 10,
|
44 |
+
"sparsity_target": 0.8,
|
45 |
+
"sparsity_target_epoch": 9,
|
46 |
+
"steps_per_epoch": 2105,
|
47 |
+
"update_per_optimizer_step": true
|
48 |
+
},
|
49 |
+
"sparsity_init": 0.0
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"input_info": [
|
53 |
+
{
|
54 |
+
"keyword": "input_ids",
|
55 |
+
"sample_size": [
|
56 |
+
32,
|
57 |
+
128
|
58 |
+
],
|
59 |
+
"type": "long"
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"keyword": "token_type_ids",
|
63 |
+
"sample_size": [
|
64 |
+
32,
|
65 |
+
128
|
66 |
+
],
|
67 |
+
"type": "long"
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"keyword": "attention_mask",
|
71 |
+
"sample_size": [
|
72 |
+
32,
|
73 |
+
128
|
74 |
+
],
|
75 |
+
"type": "long"
|
76 |
+
}
|
77 |
+
],
|
78 |
+
"log_dir": "/nvme2/yujiepan/workspace/jpqd-test/LOGS/optimum-magnitude/0209_jp0w_QMaP80_LR5e-05_COS11,6_EPO17_PerStp_INIT0.0_END9_BS32_LT0.95TMP2_SEED1_dgx1",
|
79 |
+
"optimum_version": "1.6.3",
|
80 |
+
"save_onnx_model": false,
|
81 |
+
"transformers_version": "4.26.0"
|
82 |
+
}
|
openvino_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bc46883c54fe9cf7d9ed6d172ee9622273d1c081c186aae0da2755d30bc0861
|
3 |
+
size 181696972
|
openvino_model.xml
ADDED
The diff for this file is too large to render.
See raw diff
|
|
original_graph.dot
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pip-requirements.txt
ADDED
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
addict==2.4.0
|
2 |
+
aiofiles==22.1.0
|
3 |
+
aiohttp==3.8.3
|
4 |
+
aiosignal==1.3.1
|
5 |
+
aiosqlite==0.18.0
|
6 |
+
alembic==1.9.2
|
7 |
+
anyio==3.6.2
|
8 |
+
appdirs==1.4.4
|
9 |
+
argon2-cffi==21.3.0
|
10 |
+
argon2-cffi-bindings==21.2.0
|
11 |
+
arrow==1.2.3
|
12 |
+
astroid==1.6.6
|
13 |
+
asttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1670263926556/work
|
14 |
+
async-timeout==4.0.2
|
15 |
+
attrs==22.1.0
|
16 |
+
audioread==3.0.0
|
17 |
+
autoflake==2.0.0
|
18 |
+
autograd==1.5
|
19 |
+
autopep8==2.0.1
|
20 |
+
Babel==2.11.0
|
21 |
+
backcall @ file:///home/conda/feedstock_root/build_artifacts/backcall_1592338393461/work
|
22 |
+
backports.functools-lru-cache @ file:///home/conda/feedstock_root/build_artifacts/backports.functools_lru_cache_1618230623929/work
|
23 |
+
beautifulsoup4==4.11.2
|
24 |
+
black==22.12.0
|
25 |
+
bleach==6.0.0
|
26 |
+
blessings==1.7
|
27 |
+
certifi==2022.12.7
|
28 |
+
cffi==1.15.1
|
29 |
+
charset-normalizer==2.1.1
|
30 |
+
click==8.1.3
|
31 |
+
cma==2.7.0
|
32 |
+
cmaes==0.9.1
|
33 |
+
coloredlogs==15.0.1
|
34 |
+
colorlog==6.7.0
|
35 |
+
comm @ file:///home/conda/feedstock_root/build_artifacts/comm_1670575068857/work
|
36 |
+
cycler==0.11.0
|
37 |
+
datasets==2.8.0
|
38 |
+
debugpy==1.6.4
|
39 |
+
decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
|
40 |
+
defusedxml==0.7.1
|
41 |
+
dill==0.3.6
|
42 |
+
docker-pycreds==0.4.0
|
43 |
+
entrypoints @ file:///home/conda/feedstock_root/build_artifacts/entrypoints_1643888246732/work
|
44 |
+
et-xmlfile==1.1.0
|
45 |
+
evaluate==0.4.0
|
46 |
+
executing @ file:///home/conda/feedstock_root/build_artifacts/executing_1667317341051/work
|
47 |
+
fastjsonschema==2.16.2
|
48 |
+
filelock==3.8.2
|
49 |
+
flake8==6.0.0
|
50 |
+
fonttools==4.38.0
|
51 |
+
fqdn==1.5.1
|
52 |
+
frozenlist==1.3.3
|
53 |
+
fsspec==2022.11.0
|
54 |
+
future==0.18.2
|
55 |
+
gitdb==4.0.10
|
56 |
+
GitPython==3.1.29
|
57 |
+
gpustat==0.6.0
|
58 |
+
greenlet==2.0.2
|
59 |
+
huggingface-hub==0.11.1
|
60 |
+
humanfriendly==10.0
|
61 |
+
idna==3.4
|
62 |
+
importlib-metadata==5.2.0
|
63 |
+
importlib-resources==5.10.2
|
64 |
+
iniconfig==1.1.1
|
65 |
+
ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1673894597753/work
|
66 |
+
ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1674911957283/work
|
67 |
+
ipython-genutils==0.2.0
|
68 |
+
ipywidgets==8.0.4
|
69 |
+
isoduration==20.11.0
|
70 |
+
isort==5.10.1
|
71 |
+
jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1669134318875/work
|
72 |
+
Jinja2==3.1.2
|
73 |
+
joblib==1.2.0
|
74 |
+
json5==0.9.11
|
75 |
+
jsonpointer==2.3
|
76 |
+
jsonschema==4.17.3
|
77 |
+
jstyleson==0.0.2
|
78 |
+
jupyter-events==0.5.0
|
79 |
+
jupyter-ydoc==0.2.2
|
80 |
+
jupyter_client==8.0.2
|
81 |
+
jupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1674601164834/work
|
82 |
+
jupyter_server==2.2.1
|
83 |
+
jupyter_server_fileid==0.6.0
|
84 |
+
jupyter_server_terminals==0.4.4
|
85 |
+
jupyter_server_ydoc==0.6.1
|
86 |
+
jupyterlab==3.6.1
|
87 |
+
jupyterlab-pygments==0.2.2
|
88 |
+
jupyterlab-widgets==3.0.5
|
89 |
+
jupyterlab_server==2.19.0
|
90 |
+
kiwisolver==1.4.4
|
91 |
+
lazy-object-proxy==1.7.1
|
92 |
+
librosa==0.9.2
|
93 |
+
llvmlite==0.39.1
|
94 |
+
Mako==1.2.4
|
95 |
+
MarkupSafe==2.1.2
|
96 |
+
matplotlib==3.5.3
|
97 |
+
matplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1660814786464/work
|
98 |
+
mccabe==0.7.0
|
99 |
+
mistune==2.0.5
|
100 |
+
mpmath==1.2.1
|
101 |
+
multidict==6.0.3
|
102 |
+
multiprocess==0.70.14
|
103 |
+
mypy-extensions==0.4.3
|
104 |
+
natsort==8.2.0
|
105 |
+
nbclassic==0.5.1
|
106 |
+
nbclient==0.7.2
|
107 |
+
nbconvert==7.2.9
|
108 |
+
nbformat==5.7.3
|
109 |
+
nest-asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1664684991461/work
|
110 |
+
networkx==2.8.8
|
111 |
+
ninja==1.10.2.4
|
112 |
+
nncf @ git+https://github.com/openvinotoolkit/nncf@c02f9f3bc0d77677b8cacbeedf102bb8ca93c0ac
|
113 |
+
notebook==6.5.2
|
114 |
+
notebook_shim==0.2.2
|
115 |
+
ntplib==0.4.0
|
116 |
+
numba==0.56.4
|
117 |
+
numpy==1.23.4
|
118 |
+
nvidia-ml-py3==7.352.0
|
119 |
+
onnx==1.13.0
|
120 |
+
opencv-python==4.7.0.68
|
121 |
+
openpyxl==3.0.10
|
122 |
+
openvino==2023.0.0.dev20230119
|
123 |
+
openvino-dev==2023.0.0.dev20230119
|
124 |
+
openvino-telemetry==2022.3.0
|
125 |
+
optimum==1.6.3
|
126 |
+
-e git+https://github.com/yujiepan-work/optimum-intel.git@01927af543eaea8678671bf8f4eb78fdb29f8930#egg=optimum_intel
|
127 |
+
optuna==3.1.0
|
128 |
+
packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1673482170163/work
|
129 |
+
pandas==1.3.5
|
130 |
+
pandocfilters==1.5.0
|
131 |
+
parameterized==0.8.1
|
132 |
+
parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1638334955874/work
|
133 |
+
pathspec==0.10.3
|
134 |
+
pathtools==0.1.2
|
135 |
+
pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1667297516076/work
|
136 |
+
pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work
|
137 |
+
Pillow==9.4.0
|
138 |
+
pkgutil_resolve_name==1.3.10
|
139 |
+
platformdirs @ file:///home/conda/feedstock_root/build_artifacts/platformdirs_1672264874562/work
|
140 |
+
pooch==1.6.0
|
141 |
+
prometheus-client==0.16.0
|
142 |
+
promise==2.3
|
143 |
+
prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1670414775770/work
|
144 |
+
protobuf==3.20.2
|
145 |
+
psutil==5.9.1
|
146 |
+
ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
|
147 |
+
pure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work
|
148 |
+
py==1.11.0
|
149 |
+
pyarrow==10.0.1
|
150 |
+
pycodestyle==2.10.0
|
151 |
+
pycparser==2.21
|
152 |
+
pydot==1.4.2
|
153 |
+
pyflakes==3.0.1
|
154 |
+
Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1672682006896/work
|
155 |
+
pylint==1.9.4
|
156 |
+
pymoo==0.5.0
|
157 |
+
pyparsing==2.4.7
|
158 |
+
pyrsistent==0.19.2
|
159 |
+
python-dateutil==2.8.2
|
160 |
+
python-json-logger==2.0.4
|
161 |
+
pytz==2022.7.1
|
162 |
+
PyYAML==6.0
|
163 |
+
pyzmq==25.0.0
|
164 |
+
regex==2022.10.31
|
165 |
+
requests==2.28.2
|
166 |
+
resampy==0.4.2
|
167 |
+
responses==0.18.0
|
168 |
+
rfc3339-validator==0.1.4
|
169 |
+
rfc3986-validator==0.1.1
|
170 |
+
scikit-learn==1.2.0
|
171 |
+
scipy==1.10.0
|
172 |
+
seaborn==0.12.0
|
173 |
+
Send2Trash==1.8.0
|
174 |
+
sentencepiece==0.1.97
|
175 |
+
sentry-sdk==1.12.1
|
176 |
+
setproctitle==1.3.2
|
177 |
+
shortuuid==1.0.11
|
178 |
+
six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
|
179 |
+
smmap==5.0.0
|
180 |
+
sniffio==1.3.0
|
181 |
+
soundfile==0.11.0
|
182 |
+
soupsieve==2.3.2.post1
|
183 |
+
SQLAlchemy==2.0.1
|
184 |
+
stack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work
|
185 |
+
sympy==1.11.1
|
186 |
+
terminado==0.17.1
|
187 |
+
texttable==1.6.7
|
188 |
+
threadpoolctl==3.1.0
|
189 |
+
tinycss2==1.2.1
|
190 |
+
tokenizers==0.13.2
|
191 |
+
tomli==2.0.1
|
192 |
+
torch==1.13.1+cu116
|
193 |
+
torchaudio==0.13.1+cu116
|
194 |
+
torchvision==0.14.1+cu116
|
195 |
+
tornado==6.2
|
196 |
+
tqdm==4.64.1
|
197 |
+
traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1673359992537/work
|
198 |
+
transformers==4.26.0
|
199 |
+
typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1665144421445/work
|
200 |
+
uri-template==1.2.0
|
201 |
+
urllib3==1.26.14
|
202 |
+
wandb==0.13.7
|
203 |
+
wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1673864653149/work
|
204 |
+
webcolors==1.12
|
205 |
+
webencodings==0.5.1
|
206 |
+
websocket-client==1.5.1
|
207 |
+
widgetsnbextension==4.0.5
|
208 |
+
wrapt==1.14.1
|
209 |
+
xxhash==3.1.0
|
210 |
+
y-py==0.5.5
|
211 |
+
yarl==1.8.2
|
212 |
+
ypy-websocket==0.8.2
|
213 |
+
zipp==3.11.0
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db74623dddd1b4b137050000513cf9aca5b7a07131693df439c5b3d0c2b3236d
|
3 |
+
size 778415781
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"name_or_path": "textattack/bert-base-uncased-SST-2",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": "/home/yujiepan/.cache/huggingface/hub/models--textattack--bert-base-uncased-SST-2/snapshots/95f0f6f859b35c8ff0863ae3cd4e2dbc702c0ae2/special_tokens_map.json",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 17.0,
|
3 |
+
"train_loss": 0.06787751242209697,
|
4 |
+
"train_runtime": 20398.7052,
|
5 |
+
"train_samples": 67349,
|
6 |
+
"train_samples_per_second": 56.128,
|
7 |
+
"train_steps_per_second": 1.754
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7224e8ad3cd262826caf3cd7f3d73b6abdefaa2008e8fc0bc14c4995c6af1961
|
3 |
+
size 17898144
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aec332d02c9c5ad9062f278fc7bcfa773a8024c1e0626e6b2f7f7e7b9077300e
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|