weqweasdas commited on
Commit
1bedbf1
1 Parent(s): 465c80f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -14,14 +14,15 @@ The model is trained from [meta-llama/Meta-Llama-3-8B](https://huggingface.co/me
14
 
15
  ## Academic Benchmarks
16
 
 
 
17
  | **Model** | **Size** | **Method** | **LC AlpacaEval** | **MT-Bench** | **GSM-8K** | **MMLU** | **HumanEval** | **TruthfulQA** | **ARC** | **MBPP** |
18
  |----------------------------|----------|-----------------|------------|------------|------------|----------|---------------|----------------|---------|----------|
19
  | LLaMA-3-8B-it | 8B | RS+DPO+PPO |22.9|8.16| 79.6 | 66.0 | 61.6 | 43.9 | 59.5 | 61.1 |
20
- | Ours (SFT baseline) | 8B | SFT |10.2|7.69| 74.2 | 64.7 | 65.2 | 53.4 | 61.4 | 62.3 |
21
  | Ours (Iterative RLHF) | 8B | Iterative DPO |37.2|8.46| 80.7 | 65.3 | 64.6 | 60.4 | 64.3 | 60.8 |
22
 
23
 
24
-
25
  ## Citation
26
  Please cite our techical report if you find our model is useful for your research or product.
27
  ```
 
14
 
15
  ## Academic Benchmarks
16
 
17
+ We use ToRA script to evaluate GSM8K and MATH, Evalplut for HumanEval, and lm-evaluation-harness for other benchmarks. The model is evaluated in zero-shot setting so the results here may be slightly different from that reported in the technical report.
18
+
19
  | **Model** | **Size** | **Method** | **LC AlpacaEval** | **MT-Bench** | **GSM-8K** | **MMLU** | **HumanEval** | **TruthfulQA** | **ARC** | **MBPP** |
20
  |----------------------------|----------|-----------------|------------|------------|------------|----------|---------------|----------------|---------|----------|
21
  | LLaMA-3-8B-it | 8B | RS+DPO+PPO |22.9|8.16| 79.6 | 66.0 | 61.6 | 43.9 | 59.5 | 61.1 |
22
+ | Ours (SFT baseline) | 8B | SFT |10.2|7.69| 74.2 | 30.0 | 64.6 | 63.4 | 53.5 | 58.6 |
23
  | Ours (Iterative RLHF) | 8B | Iterative DPO |37.2|8.46| 80.7 | 65.3 | 64.6 | 60.4 | 64.3 | 60.8 |
24
 
25
 
 
26
  ## Citation
27
  Please cite our techical report if you find our model is useful for your research or product.
28
  ```