!python finetune.py \
    --train_path "./data/train.txt" \
    --dev_path "./data/dev.txt" \
    --save_dir "./checkpoint" \
    --learning_rate 5e-6  \
    --batch_size 16 \
    --max_seq_len 512 \
    --num_epochs 10 \
    --model "uie-base" \
    --seed 1000 \
    --logging_steps 10 \
    --valid_steps 50 \
    --device "gpu"

[2022-09-08 17:26:55,701] [    INFO] - Evaluation precision: 0.69375, recall: 0.69811, F1: 0.69592
[2022-09-08 17:27:01,145] [    INFO] - global step 260, epoch: 9, loss: 0.00172, speed: 1.84 step/s
[2022-09-08 17:27:06,448] [    INFO] - global step 270, epoch: 9, loss: 0.00168, speed: 1.89 step/s
[2022-09-08 17:27:12,102] [    INFO] - global step 280, epoch: 10, loss: 0.00165, speed: 1.77 step/s
[2022-09-08 17:27:17,607] [    INFO] - global step 290, epoch: 10, loss: 0.00162, speed: 1.82 step/s
[2022-09-08 17:27:22,899] [    INFO] - global step 300, epoch: 10, loss: 0.00159, speed: 1.89 step/s
[2022-09-08 17:27:26,577] [    INFO] - Evaluation precision: 0.69277, recall: 0.72327, F1: 0.70769
[2022-09-08 17:27:26,577] [    INFO] - best F1 performence has been updated: 0.69841 --> 0.70769

%cd /home/aistudio/data_distill
!python data_distill.py \
    --data_path /home/aistudio/data \
    --save_dir student_data \
    --task_type relation_extraction \
    --synthetic_ratio 10 \
    --model_path /home/aistudio/checkpoint/model_best

 parser.add_argument("--data_path", default="../data", type=str, help="The directory for labeled data with doccano format and the large scale unlabeled data.")
    parser.add_argument("--model_path", type=str, default="../checkpoint/model_best", help="The path of saved model that you want to load.")
    parser.add_argument("--save_dir", default="./distill_task", type=str, help="The path of data that you wanna save.")
    parser.add_argument("--synthetic_ratio", default=10, type=int, help="The ratio of labeled and synthetic samples.")
    parser.add_argument("--task_type", choices=['relation_extraction', 'event_extraction', 'entity_extraction', 'opinion_extraction'], default="entity_extraction", type=str, help="Select the training task type.")
    parser.add_argument("--seed", type=int, default=1000, help="Random seed for initialization")

parser.add_argument("--model_path", type=str, default=None, help="The path of saved model that you want to load.")
    parser.add_argument("--test_path", type=str, default=None, help="The path of test set.")
    parser.add_argument("--encoder", default="ernie-3.0-base-zh", type=str, help="Select the pretrained encoder model for GP.")
    parser.add_argument("--label_maps_path", default="./ner_data/label_maps.json", type=str, help="The file path of the labels dictionary.")
    parser.add_argument("--batch_size", type=int, default=16, help="Batch size per GPU/CPU for training.")
    parser.add_argument("--max_seq_len", type=int, default=128, help="The maximum total input sequence length after tokenization.")
    parser.add_argument("--task_type", choices=['relation_extraction', 'event_extraction', 'entity_extraction', 'opinion_extraction'], default="entity_extraction",

!python train.py \
    --task_type relation_extraction \
    --train_path student_data/train_data.json \
    --dev_path student_data/dev_data.json \
    --label_maps_path student_data/label_maps.json \
    --num_epochs 200 \
    --encoder ernie-3.0-mini-zh

# %cd /home/aistudio/data_distill
!python train.py \
    --task_type relation_extraction \
    --train_path student_data/train_data.json \
    --dev_path student_data/dev_data.json \
    --label_maps_path student_data/label_maps.json \
    --num_epochs 100 \
    --encoder ernie-3.0-mini-zh\
    --device "gpu"\
    --valid_steps 100\
    --logging_steps 10\
    --save_dir './checkpoint2'\
    --batch_size 16

from pprint import pprint
from paddlenlp import Taskflow

ie = Taskflow("information_extraction", model="uie-data-distill-gp", task_path="checkpoint2/model_best/") # Schema 在闭域信息抽取中是固定的
pprint(ie("登革热@结果 升高 ### 血清白蛋白水平 检查 结果 检查 在资源匮乏地区和富足地区，对有症状患者均应早期检测。"))

[{'疾病': [{'end': 3,
          'probability': 0.9995957,
          'relations': {'实验室检查': [{'end': 21,
                                   'probability': 0.99892455,
                                   'relations': {},
                                   'start': 14,
                                   'text': '血清白蛋白水平'}],
                        '影像学检查': [{'end': 21,
                                   'probability': 0.99832386,
                                   'relations': {},
                                   'start': 14,
                                   'text': '血清白蛋白水平'}]},
          'start': 0,
          'text': '登革热'}]}]

from pprint import pprint
import json
from paddlenlp.taskflow import Taskflow
import pandas as pd
#运行时间
import time


def openreadtxt(file_name):
    data = []
    file = open(file_name,'r',encoding='UTF-8')  #打开文件
    file_data = file.readlines() #读取所有行
    for row in file_data:
        data.append(row) #将每行数据插入data中     
    return data

# 时间1
old_time = time.time()
data_input=openreadtxt('/home/aistudio/数据集/unlabeled_data.txt')


few_ie = Taskflow("information_extraction", model="uie-data-distill-gp", task_path="/home/aistudio/data_distill/checkpoint2/model_best",batch_size=32) # Schema 在闭域信息抽取中是固定的


# 时间1
current_time = time.time()
print("数据模型载入运行时间为" + str(current_time - old_time) + "s")

#时间2
old_time1 = time.time()
results=few_ie(data_input)
current_time1 = time.time()
print("模型计算运行时间为" + str(current_time1 - old_time1) + "s")
#时间2

#时间三
old_time3 = time.time()
test = pd.DataFrame(data=results)
test.to_csv('/home/aistudio/output/reslut.txt', sep='\t', index=False,header=False) #本地

# with open("/home/aistudio/output/reslut.txt", "w+",encoding='UTF-8') as f:    #a :   写入文件，若文件不存在则会先创建再写入，但不会覆盖原文件，而是追加在文件末尾
#     for result in results:
#         line = json.dumps(result, ensure_ascii=False)  #对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
#         f.write(line + "\n")
current_time3 = time.time()
print("数据导出运行时间为" + str(current_time3 - old_time3) + "s")

# for idx, text in enumerate(data):
#     print('Data: {} \t Lable: {}'.format(text[0], results[idx]))
print("数据结果已导出")

**mini运行时间：**

数据模型载入运行时间为0.8430757522583008s

模型计算运行时间为6.839258909225464s

数据导出运行时间为0.008304595947265625s

**nano运行时间：**
数据模型载入运行时间为0.5164840221405029s

模型计算运行时间为6.6231770515441895s

数据导出运行时间为0.023623943328857422s

**micro运行时间：**

数据模型载入运行时间为0.5323500633239746s

模型计算运行时间为6.77699007987976s

数据导出运行时间为0.04320549964904785s

0:"手术治疗"
1:"实验室检查"
2:"影像学检查"

from pprint import pprint
import json
from paddlenlp import Taskflow
import pandas as pd
#运行时间
import time


def openreadtxt(file_name):
    data = []
    file = open(file_name,'r',encoding='UTF-8')  #打开文件
    file_data = file.readlines() #读取所有行
    for row in file_data:
        data.append(row) #将每行数据插入data中     
    return data

# 时间1
old_time = time.time()
data_input=openreadtxt('/home/aistudio/数据集/unlabeled_data.txt')

schema = {'疾病': ['手术治疗', '实验室检查', '影像学检查']}
# few_ie = Taskflow('information_extraction', schema=schema, batch_size=32,task_path='/home/aistudio/checkpoint_mini/model_best') #自行切换
few_ie = Taskflow('information_extraction', schema=schema, batch_size=32,task_path='/home/aistudio/checkpoint_micro/model_best')
# 时间1
current_time = time.time()
print("数据模型载入运行时间为" + str(current_time - old_time) + "s")

#时间2
old_time1 = time.time()
results=few_ie(data_input)
current_time1 = time.time()
print("模型计算运行时间为" + str(current_time1 - old_time1) + "s")
#时间2

#时间三
old_time3 = time.time()
test = pd.DataFrame(data=results)
test.to_csv('/home/aistudio/output/reslut.txt', sep='\t', index=False,header=False) #本地

# with open("/home/aistudio/output/reslut.txt", "w+",encoding='UTF-8') as f:    #a :   写入文件，若文件不存在则会先创建再写入，但不会覆盖原文件，而是追加在文件末尾
#     for result in results:
#         line = json.dumps(result, ensure_ascii=False)  #对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
#         f.write(line + "\n")
current_time3 = time.time()
print("数据导出运行时间为" + str(current_time3 - old_time3) + "s")

# for idx, text in enumerate(data):
#     print('Data: {} \t Lable: {}'.format(text[0], results[idx]))
print("数据结果已导出")

通过上述程序自行切换：加载对应模型

记录推理时间：
**uie-nano**
数据模型载入运行时间为0.3770780563354492s
模型计算运行时间为24.893776178359985s
数据导出运行时间为0.01157689094543457s

**uie-micro**
数据模型载入运行时间为0.39632749557495117s
模型计算运行时间为26.367019176483154s
数据导出运行时间为0.012260198593139648s

**uie-mini**

数据模型载入运行时间为0.5642790794372559s

模型计算运行时间为28.93251943588257s

数据导出运行时间为0.01435089111328125s

**uie-base**

数据模型载入运行时间为1.4756040573120117s

模型计算运行时间为68.61049008369446s

数据导出运行时间为0.02205801010131836s

from pprint import pprint
import json
from paddlenlp.taskflow import Taskflow
import pandas as pd
#运行时间
import time


def openreadtxt(file_name):
    data = []
    file = open(file_name,'r',encoding='UTF-8')  #打开文件
    file_data = file.readlines() #读取所有行
    for row in file_data:
        data.append(row) #将每行数据插入data中     
    return data

# 时间1
old_time = time.time()
data_input=openreadtxt('/home/aistudio/数据集/unlabeled_data-Copy1.txt')

few_ie = Taskflow("information_extraction", model="uie-data-distill-gp", task_path="/home/aistudio/data_distill/checkpoint2/model_best",use_faster=True,batch_size=32) # Schema 在闭域信息抽取中是固定的
# few_ie = Taskflow("information_extraction", model="uie-data-distill-gp", task_path="/home/aistudio/data_distill/checkpoint2/model_best",batch_size=32) # Schema 在闭域信息抽取中是固定的

# schema = {'疾病': ['手术治疗', '实验室检查', '影像学检查']}
# few_ie = Taskflow('information_extraction', schema=schema, batch_size=32,use_faster=True,task_path='/home/aistudio/checkpoint/model_best')
# few_ie = Taskflow('information_extraction', schema=schema, batch_size=32,task_path='/home/aistudio/checkpoint/model_best')

# 时间1
current_time = time.time()
print("数据模型载入运行时间为" + str(current_time - old_time) + "s")

#时间2
old_time1 = time.time()
results=few_ie(data_input)
current_time1 = time.time()
print("模型计算运行时间为" + str(current_time1 - old_time1) + "s")
#时间2

#时间三
old_time3 = time.time()
test = pd.DataFrame(data=results)
test.to_csv('/home/aistudio/output/reslut.txt', sep='\t', index=False,header=False) #本地

# with open("/home/aistudio/output/reslut.txt", "w+",encoding='UTF-8') as f:    #a :   写入文件，若文件不存在则会先创建再写入，但不会覆盖原文件，而是追加在文件末尾
#     for result in results:
#         line = json.dumps(result, ensure_ascii=False)  #对中文默认使用的ascii编码.想输出真正的中文需要指定ensure_ascii=False
#         f.write(line + "\n")
current_time3 = time.time()
print("数据导出运行时间为" + str(current_time3 - old_time3) + "s")

# for idx, text in enumerate(data):
#     print('Data: {} \t Lable: {}'.format(text[0], results[idx]))
print("数据结果已导出")