lgaalves commited on
Commit
4801150
1 Parent(s): b49cb54

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -7
README.md CHANGED
@@ -18,13 +18,11 @@ pipeline_tag: text-generation
18
 
19
  | Metric | GPT-2-Open-Platypus | GPT-2 (base) |
20
  |-----------------------|-------|-------|
21
- | Avg. | - | 29.9 |
22
- | ARC (25-shot) | - | 21.84 |
23
- | HellaSwag (10-shot) | - | 31.6 |
24
- | MMLU (5-shot) | - | 25.86 |
25
- | TruthfulQA (0-shot) | - | 40.67 |
26
-
27
-
28
 
29
  We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
30
 
 
18
 
19
  | Metric | GPT-2-Open-Platypus | GPT-2 (base) |
20
  |-----------------------|-------|-------|
21
+ | Avg. | **30.01** | 29.9 |
22
+ | ARC (25-shot) | **22.18** | 21.84 |
23
+ | HellaSwag (10-shot) | 31.29 | **31.6** |
24
+ | MMLU (5-shot) | **26.19** | 25.86 |
25
+ | TruthfulQA (0-shot) | **40.35** | 40.67 |
 
 
26
 
27
  We use state-of-the-art [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
28