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

Merge pull request #48 from MING-ZCH/main

Browse Source 
[DOC] Update docs of evaluation
This commit is contained in:
MING_X 2024-03-06 17:39:56 +08:00 committed by GitHub
commit 3ed7507e53
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 44 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
evaluate/General_evaluation.md
View File

@ -45,6 +45,6 @@ pip install torch transformers datasets nltk rouge jieba
| Model | ROUGE-1 | ROUGE-2 | ROUGE-L | BLEU-1 | BLEU-2 | BLEU-3 | BLEU-4 |
|----------|---------|---------|---------|---------|---------|---------|---------|
| Qwen1_5-0_5B-Chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| 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% |

6
evaluate/Professional_evaluation.md
View File

@ -14,7 +14,9 @@
## 评测结果
评测模型: [EmoLLM](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model)(InternLM2_7B_chat_qlora), 得分：
* 评测模型: [EmoLLM V1.0](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model)(InternLM2_7B_chat_qlora)
* 得分：
| Metric | Value |
|-------------------|------------|
| Comprehensiveness | 1.32 |
@ -24,7 +26,7 @@
## 比较
* [EmoLLM](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model) 在 InternLM2-7B-Chat 基础上提升较大；相比 Role-playing ChatGPT 在心理咨询任务上能力相近
* [EmoLLM V1.0](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model) 在 InternLM2_7B_Chat 基础上提升较大；相比 Role-playing ChatGPT 在心理咨询任务上能力相近
* 对比结果图片来源于论文《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》
![image](https://github.com/MING-ZCH/EmoLLM/assets/119648793/abc9f626-11bc-4ec8-84a4-427c4600a720)

32
evaluate/Professional_evaluation_EN.md Normal file
View File

@ -0,0 +1,32 @@
# EmoLLM's professional evaluation
## Introduction
This document describes a professional evaluation method and provides EmoLLM's scores on professional metrics.
## Evaluation
The evaluation method, metric, and dataset from the paper《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》.
* Metric: Comprehensiveness, Professionalism, Authenticity, Safety
* Method: Turn-Based Dialogue Evaluation
* Dataset: CPsyCounE
## Result
* Model: [EmoLLM V1.0](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model)(InternLM2_7B_chat_qlora)
* Score：
| Metric | Value |
|-------------------|------------|
| Comprehensiveness | 1.32 |
| Professionalism | 2.20 |
| Authenticity | 2.10 |
| Safety | 1.00 |
## Comparison
* [EmoLLM V1.0](https://openxlab.org.cn/models/detail/jujimeizuo/EmoLLM_Model) is greatly improved on InternLM2_7B_Chat; Performance on the counseling task was similar compared to ChatGPT(Role-playing)
* The comparison results are from the paper《CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling》
![image](https://github.com/MING-ZCH/EmoLLM/assets/119648793/abc9f626-11bc-4ec8-84a4-427c4600a720)

2
evaluate/README.md
View File

@ -6,7 +6,7 @@
| Model | ROUGE-1 | ROUGE-2 | ROUGE-L | BLEU-1 | BLEU-2 | BLEU-3 | BLEU-4 |
|----------|---------|---------|---------|---------|---------|---------|---------|
| Qwen1_5-0_5B-Chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| 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% |
## 专业指标评测

13
evaluate/README_EN.md
View File

@ -6,17 +6,14 @@
| Model | ROUGE-1 | ROUGE-2 | ROUGE-L | BLEU-1 | BLEU-2 | BLEU-3 | BLEU-4 |
|----------|---------|---------|---------|---------|---------|---------|---------|
| Qwen1_5-0_5B-Chat | 27.23% | 8.55% | 17.05% | 26.65% | 13.11% | 7.19% | 4.05% |
| InternLM2_7B_chat | 37.86% | 15.23% | 24.34% | 39.71% | 22.66% | 14.26% | 9.21% |
| 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% |
## Professional Metrics Evaluation
* For specific metrics and methods, see [Professional_evaluation_EN.md](./Professional_evaluation_EN.md)
| Metric | Value |
|-------------------|------------|
| Comprehensiveness | 1.32 |
| Professionalism | 2.20 |
| Authenticity | 2.10 |
| Safety | 1.00 |
| Model | Comprehensiveness | rofessionalism | Authenticity | Safety |
|-------------------|-----------------------|-------------------|-----------------|---------|
| InternLM2_7B_chat_qlora | 1.32 | 2.20 | 2.10 | 1.00 |