bakaEC/OliveSensorAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[ADD] add evaluation result of base model on 5/10 epochs

Browse Source
This commit is contained in:
Zeyu Ba 2024-03-28 15:38:37 +08:00
parent a24eb52342
commit 21e81298a3
7 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
evaluate/General_evaluation.md
View File

@ -48,3 +48,5 @@ pip install torch transformers datasets nltk rouge jieba
| Qwen1_5-0_5B-chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat_qlora | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| InternLM2_7B_chat_full | 32.45% | 10.82% | 20.17% | 30.48% | 15.67% | 8.84% | 5.02% |
| InternLM2_7B_base_qlora_5epoch | 41.94% | 20.21% | 29.67% | 42.98% | 27.07% | 19.33% | 14.62% |
| InternLM2_7B_base_qlora_10epoch | 43.47% | 22.06% | 31.4% | 44.81% | 29.15% | 21.44% | 16.72% |

2
evaluate/General_evaluation_EN.md
View File

@ -48,3 +48,5 @@ Test the data in data.json with the following results:
| Qwen1_5-0_5B-chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat_qlora | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| InternLM2_7B_chat_full | 32.45% | 10.82% | 20.17% | 30.48% | 15.67% | 8.84% | 5.02% |
| InternLM2_7B_base_qlora_5epoch | 41.94% | 20.21% | 29.67% | 42.98% | 27.07% | 19.33% | 14.62% |
| InternLM2_7B_base_qlora_10epoch | 43.47% | 22.06% | 31.4% | 44.81% | 29.15% | 21.44% | 16.72% |

2
evaluate/README.md
View File

@ -9,6 +9,8 @@
| Qwen1_5-0_5B-chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat_qlora | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| InternLM2_7B_chat_full | 32.45% | 10.82% | 20.17% | 30.48% | 15.67% | 8.84% | 5.02% |
| InternLM2_7B_base_qlora_5epoch | 41.94% | 20.21% | 29.67% | 42.98% | 27.07% | 19.33% | 14.62% |
| InternLM2_7B_base_qlora_10epoch | 43.47% | 22.06% | 31.4% | 44.81% | 29.15% | 21.44% | 16.72% |
## 专业指标评测

2
evaluate/README_EN.md
View File

@ -9,6 +9,8 @@
| Qwen1_5-0_5B-chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat_qlora | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| InternLM2_7B_chat_full | 32.45% | 10.82% | 20.17% | 30.48% | 15.67% | 8.84% | 5.02% |
| InternLM2_7B_base_qlora_5epoch | 41.94% | 20.21% | 29.67% | 42.98% | 27.07% | 19.33% | 14.62% |
| InternLM2_7B_base_qlora_10epoch | 43.47% | 22.06% | 31.4% | 44.81% | 29.15% | 21.44% | 16.72% |
## Professional Metrics Evaluation

2
scripts/qa_generation/QA_clean.py
View File

@ -101,7 +101,7 @@ def clean_qa(
future.result()
except Exception as exc:
logger.error("Thread generated an exception: %s" % (exc))
merge_sub_qa_generation(result_dir, storage_jsonl_path)

4
scripts/qa_generation/config/config.py
View File

@ -12,7 +12,7 @@ model_dir = os.path.join(base_dir, 'model') # mo
# data
data_dir = os.path.join(base_dir, 'data')
clean_dir = os.path.join(data_dir, 'cleaned')
judge_dir = os.path.join(data_dir, '数据整合')
judge_dir = os.path.join(data_dir, 'generated')
result_dir = os.path.join(data_dir, 'generated') # result
# log
@ -29,7 +29,7 @@ wash_prompt_file_path = os.path.join(base_dir, 'choose_prompt.md')
环境变量
"""
# api-keys
DASHSCOPE_API_KEY = ''
DASHSCOPE_API_KEY = 'sk-4295ec893e9c413abb0551b85e84f39f'
"""

16
scripts/qa_generation/util/data_loader.py
View File

@ -117,6 +117,20 @@ def save_to_file(storage_jsonl_path, storage_list):
for item in storage_list:
f.write(json.dumps(item, ensure_ascii=False) + '\n')
import time
import os
def safe_remove(file_path, max_attempts=5, delay=1):
for attempt in range(max_attempts):
try:
os.remove(file_path)
print(f"File {file_path} successfully deleted.")
break
except PermissionError as e:
print(f"Attempt {attempt+1}: Unable to delete {file_path} - {str(e)}")
time.sleep(delay)
else:
print(f"Failed to delete {file_path} after {max_attempts} attempts.")
"""
将并发产生的文件合并成为一个文件
@ -131,5 +145,5 @@ def merge_sub_qa_generation(directory, storage_jsonl_path):
with open(file_path, 'r', encoding='utf-8') as f:
for line in f:
file_contents.append(json.loads(line))
os.remove(file_path)
# safe_remove(file_path)
save_to_file(storage_jsonl_path, file_contents)