-
Notifications
You must be signed in to change notification settings - Fork 1
/
run_short_bioelectra_biolm.sh
133 lines (121 loc) · 3.71 KB
/
run_short_bioelectra_biolm.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
export TOKENIZERS_PARALLELISM=false
# n2c2 2006
export DATASET_NAME=n2c2_2006_smokers
# CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
# --model_name_or_path bio-lm \
# --dataset_name $DATASET_NAME \
# --do_train \
# --do_eval \
# --logging_steps 10 \
# --max_seq_length 512 \
# --per_device_train_batch_size 8 \
# --gradient_accumulation_steps 1 \
# --learning_rate 1e-5 \
# --num_train_epochs 50 \
# --evaluation_strategy epoch \
# --output_dir ./save/bio-lm-512-$DATASET_NAME/ \
# --overwrite_output_dir
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path kamalkraj/bioelectra-base-discriminator-pubmed \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 50 \
--evaluation_strategy epoch \
--output_dir ./save/bioelectra-512-$DATASET_NAME/ \
--overwrite_output_dir
# n2c2 2008 textual
export DATASET_NAME=n2c2_2008_textual
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path bio-lm \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 50 \
--evaluation_strategy epoch \
--output_dir ./save/bio-lm-512-$DATASET_NAME/ \
--overwrite_output_dir
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path kamalkraj/bioelectra-base-discriminator-pubmed \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 50 \
--evaluation_strategy epoch \
--output_dir ./save/bioelectra-512-$DATASET_NAME/ \
--overwrite_output_dir
# n2c2 2008 intuitive
export DATASET_NAME=n2c2_2008_intuitive
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path bio-lm \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 50 \
--evaluation_strategy epoch \
--output_dir ./save/bio-lm-512-$DATASET_NAME/ \
--overwrite_output_dir
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path kamalkraj/bioelectra-base-discriminator-pubmed \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 50 \
--evaluation_strategy epoch \
--output_dir ./save/bioelectra-512-$DATASET_NAME/ \
--overwrite_output_dir
# n2c2 2018
export DATASET_NAME=n2c2_2018_track1
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path bio-lm \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 80 \
--evaluation_strategy epoch \
--output_dir ./save/bio-lm-512-$DATASET_NAME/ \
--overwrite_output_dir
CUDA_VISIBLE_DEVICES=0 python run_nlu.py \
--model_name_or_path kamalkraj/bioelectra-base-discriminator-pubmed \
--dataset_name $DATASET_NAME \
--do_train \
--do_eval \
--logging_steps 10 \
--max_seq_length 512 \
--per_device_train_batch_size 8 \
--gradient_accumulation_steps 1 \
--learning_rate 1e-5 \
--num_train_epochs 80 \
--evaluation_strategy epoch \
--output_dir ./save/bioelectra-512-$DATASET_NAME/ \
--overwrite_output_dir