FuryAssassin commited on
Commit
f2a6ea5
·
verified ·
1 Parent(s): 4b3c52c

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -18,8 +18,6 @@ library_name: transformers
18
  </a>
19
  </div>
20
 
21
- Best checkpoint: step_1000
22
-
23
  ## 1. Introduction
24
 
25
  The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models.
@@ -34,27 +32,29 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
34
 
35
  ## 2. Evaluation Results
36
 
 
 
37
  ### Comprehensive Benchmark Results
38
 
39
  <div align="center">
40
 
41
  | | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
42
  |---|---|---|---|---|---|
43
- | **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.903 |
44
- | | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.891 |
45
- | | Common Sense | 0.716 | 0.702 | 0.725 | 0.807 |
46
- | **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.831 |
47
- | | Question Answering | 0.582 | 0.599 | 0.601 | 0.843 |
48
- | | Text Classification | 0.803 | 0.811 | 0.820 | 0.867 |
49
- | | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.819 |
50
- | **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.879 |
51
- | | Creative Writing | 0.588 | 0.579 | 0.601 | 0.795 |
52
- | | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.831 |
53
- | | Summarization | 0.745 | 0.755 | 0.760 | 0.855 |
54
- | **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.843 |
55
- | | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.807 |
56
- | | Instruction Following | 0.733 | 0.749 | 0.751 | 0.867 |
57
- | | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.819 |
58
 
59
  </div>
60
 
@@ -124,4 +124,4 @@ This code repository is licensed under the [MIT License](LICENSE). The use of My
124
 
125
  ## 6. Contact
126
  If you have any questions, please raise an issue on our GitHub repository or contact us at contact@MyAwesomeModel.ai.
127
- ```
 
18
  </a>
19
  </div>
20
 
 
 
21
  ## 1. Introduction
22
 
23
  The MyAwesomeModel has undergone a significant version upgrade. In the latest update, MyAwesomeModel has significantly improved its depth of reasoning and inference capabilities by leveraging increased computational resources and introducing algorithmic optimization mechanisms during post-training. The model has demonstrated outstanding performance across various benchmark evaluations, including mathematics, programming, and general logic. Its overall performance is now approaching that of other leading models.
 
32
 
33
  ## 2. Evaluation Results
34
 
35
+ Best checkpoint: step_400
36
+
37
  ### Comprehensive Benchmark Results
38
 
39
  <div align="center">
40
 
41
  | | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
42
  |---|---|---|---|---|---|
43
+ | **Core Reasoning Tasks** | Math Reasoning | 0.510 | 0.535 | 0.521 | 0.659894 |
44
+ | | Logical Reasoning | 0.789 | 0.801 | 0.810 | 0.740000 |
45
+ | | Common Sense | 0.716 | 0.702 | 0.725 | 0.705000 |
46
+ | **Language Understanding** | Reading Comprehension | 0.671 | 0.685 | 0.690 | 0.680000 |
47
+ | | Question Answering | 0.582 | 0.599 | 0.601 | 0.602000 |
48
+ | | Text Classification | 0.803 | 0.811 | 0.820 | 0.826000 |
49
+ | | Sentiment Analysis | 0.777 | 0.781 | 0.790 | 0.788000 |
50
+ | **Generation Tasks** | Code Generation | 0.615 | 0.631 | 0.640 | 0.649000 |
51
+ | | Creative Writing | 0.588 | 0.579 | 0.601 | 0.589000 |
52
+ | | Dialogue Generation | 0.621 | 0.635 | 0.639 | 0.642000 |
53
+ | | Summarization | 0.745 | 0.755 | 0.760 | 0.756000 |
54
+ | **Specialized Capabilities**| Translation | 0.782 | 0.799 | 0.801 | 0.802000 |
55
+ | | Knowledge Retrieval | 0.651 | 0.668 | 0.670 | 0.669000 |
56
+ | | Instruction Following | 0.733 | 0.749 | 0.751 | 0.745000 |
57
+ | | Safety Evaluation | 0.718 | 0.701 | 0.725 | 0.727000 |
58
 
59
  </div>
60
 
 
124
 
125
  ## 6. Contact
126
  If you have any questions, please raise an issue on our GitHub repository or contact us at contact@MyAwesomeModel.ai.
127
+ ```