Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
panhb
bert_tensorflow
Commits
f9044b4b
Commit
f9044b4b
authored
Jul 12, 2023
by
hepj987
Browse files
补充精度数据
parent
dbb44794
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
12 additions
and
5 deletions
+12
-5
README.md
README.md
+8
-1
bert_class.sh
bert_class.sh
+1
-1
bert_class_gpus.sh
bert_class_gpus.sh
+2
-2
bert_squad_gpus.sh
bert_squad_gpus.sh
+1
-1
No files found.
README.md
View file @
f9044b4b
...
...
@@ -192,7 +192,14 @@ sh bert_squad_gpus.sh
## 模型精度
待完善...
使用单张Z100收敛性如下所示:
| 模型任务 | 训练精度 |
| :----------------: | :------------------: |
| MNLI-class(单卡) | val_accuracy: 0.7387 |
| squad1.1(单卡) | F1-score:0.916378 |
# 源码仓库及问题反馈
...
...
bert_class.sh
View file @
f9044b4b
...
...
@@ -8,7 +8,7 @@ python3 run_classifier.py \
--init_checkpoint
/public/home/hepj/model_source/bert-base-TF2/bert_model.ckpt
\
--train_batch_size
320
\
--eval_batch_size
32
\
--steps_per_loop
10
00
\
--steps_per_loop
10
\
--learning_rate
2e-5
\
--num_train_epochs
3
\
--num_gpus
1
\
...
...
bert_class_gpus.sh
View file @
f9044b4b
...
...
@@ -6,9 +6,9 @@ python3 run_classifier.py \
--eval_data_path
/public/home/hepj/MNLI/eval.tf_record
\
--bert_config_file
/public/home/hepj/model_source/uncased_L-12_H-768_A-12/bert_config.json
\
--init_checkpoint
/public/home/hepj/model_source/bert-base-TF2/bert_model.ckpt
\
--train_batch_size
32
0
\
--train_batch_size
128
0
\
--eval_batch_size
32
\
--steps_per_loop
10
00
\
--steps_per_loop
10
\
--learning_rate
2e-5
\
--num_train_epochs
3
\
--num_gpus
4
\
...
...
bert_squad_gpus.sh
View file @
f9044b4b
...
...
@@ -7,7 +7,7 @@ python3 run_squad_xuan.py \
--train_data_path
/public/home/hepj/model/tf2.7.0_Bert/squad1.1/train.tf_record
\
--predict_file
/public/home/hepj/model/model_source/sq1.1/dev-v1.1.json
\
--init_checkpoint
/public/home/hepj/model_source/bert-large-TF2/bert_model.ckpt
\
--train_batch_size
4
\
--train_batch_size
16
\
--predict_batch_size
4
\
--learning_rate
2e-5
\
--log_steps
1
\
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment