Hugging Face's logo

allenai
/
Llama-3.1-8B-Instruct-RM-RB2

Text Classification
Transformers
PyTorch
English
llama
text-generation-inference
Model card Files
xet
Community
3
saumyamalik commited on
Commit
bb097d9
·
verified ·
1 Parent(s): 1013efd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -19
README.md CHANGED
@@ -22,26 +22,27 @@ library_name: transformers
22
  ### Model Description
23
 
24
  --------------------------------------------------
25
- | Revision | Training Data | Learning Rate | Num Epochs | RewardBench 2 Score | Factuality | Precise IF | Math | Safety | Focus | Ties |
 
26
  |----------|---------------|---------------|------------|---------------------|------------|------------|------|--------|-------|------|
27
- | main | Combined | 3e-6 | 1 | 0.7285 | 0.7432 | 0.4437 | 0.6175 | 0.8956 | 0.9071 | 0.7638 |
28
- | 1 | Combined | 4e-6 | 1 | 0.7266 | 0.7347 | 0.4313 | 0.6339 | 0.8933 | 0.8970 | 0.7697 |
29
- | 2 | Combined | 1e-6 | 2 | 0.7241 | 0.7305 | 0.4000 | 0.6667 | 0.9422 | 0.9414 | 0.6635 |
30
- | 3 | Combined | 3e-6 | 2 | 0.7209 | 0.7116 | 0.3875 | 0.6612 | 0.9067 | 0.9172 | 0.7414 |
31
- | 4 | Combined | 2e-6 | 1 | 0.7190 | 0.7263 | 0.3875 | 0.6393 | 0.8956 | 0.9273 | 0.7380 |
32
- | 5 | Combined | 3e-6 | 1 | 0.7189 | 0.7305 | 0.3937 | 0.6066 | 0.8978 | 0.9374 | 0.7475 |
33
- | 6 | Combined | 3e-6 | 1 | 0.7172 | 0.7242 | 0.4313 | 0.6175 | 0.8778 | 0.8970 | 0.7555 |
34
- | 7 | Skywork | 3e-6 | 1 | 0.7045 | 0.6253 | 0.3812 | 0.6667 | 0.9200 | 0.9232 | 0.7109 |
35
- | 8 | Combined | 1e-6 | 1 | 0.7038 | 0.6947 | 0.3937 | 0.6557 | 0.8867 | 0.8586 | 0.7331 |
36
- | 9 | Tulu | 3e-6 | 1 | 0.6938 | 0.7537 | 0.4500 | 0.6393 | 0.8667 | 0.7616 | 0.6913 |
37
- | 10 | Tulu | 3e-6 | 2 | 0.6813 | 0.7137 | 0.4437 | 0.6284 | 0.8644 | 0.7596 | 0.6781 |
38
- | 11 | Tulu | 1e-6 | 2 | 0.6754 | 0.6716 | 0.4000 | 0.6339 | 0.8756 | 0.7737 | 0.6976 |
39
- | 12 | Tulu | 3e-6 | 1 | 0.6754 | 0.7242 | 0.4062 | 0.6284 | 0.8422 | 0.7535 | 0.6976 |
40
- | 13 | Combined | 2e-5 | 1 | 0.6716 | 0.6632 | 0.3688 | 0.6284 | 0.8200 | 0.8303 | 0.7190 |
41
- | 14 | Skywork | 1e-6 | 1 | 0.6665 | 0.5979 | 0.3688 | 0.6339 | 0.8956 | 0.8606 | 0.6422 |
42
- | 15 | Tulu | 1e-6 | 1 | 0.6637 | 0.6947 | 0.4062 | 0.6284 | 0.8422 | 0.7273 | 0.6834 |
43
- | 16 | Tulu | 3e-6 | 1 | 0.6572 | 0.7305 | 0.3688 | 0.6284 | 0.8289 | 0.7030 | 0.6837 |
44
- | 17 | Combined | 2e-5 | 2 | 0.6207 | 0.6358 | 0.3750 | 0.5902 | 0.8267 | 0.8020 | 0.4948 |
45
 
46
 
47
  - **Developed by:** [More Information Needed]
 
22
  ### Model Description
23
 
24
  --------------------------------------------------
25
+ | Revision | Training Data | Learning Rate | Num Epochs | RewardBench 2 | Factuality | Precise IF | Math | Safety | Focus | Ties |
26
+ | | | | | Score | | | | | | |
27
  |----------|---------------|---------------|------------|---------------------|------------|------------|------|--------|-------|------|
28
+ | main | Combined | 3e-6 | 1 | 72.8 | 74.3 | 44.4 | 61.7 | 89.6 | 90.7 | 76.4 |
29
+ | 1 | Combined | 4e-6 | 1 | 72.7 | 73.5 | 43.1 | 63.4 | 89.3 | 89.7 | 77.0 |
30
+ | 2 | Combined | 1e-6 | 2 | 72.4 | 73.1 | 40.0 | 66.7 | 94.2 | 94.1 | 66.4 |
31
+ | 3 | Combined | 3e-6 | 2 | 72.1 | 71.2 | 38.8 | 66.1 | 90.7 | 91.7 | 74.1 |
32
+ | 4 | Combined | 2e-6 | 1 | 71.9 | 72.6 | 38.8 | 63.9 | 89.6 | 92.7 | 73.8 |
33
+ | 5 | Combined | 3e-6 | 1 | 71.9 | 73.1 | 39.4 | 60.7 | 89.8 | 93.7 | 74.7 |
34
+ | 6 | Combined | 3e-6 | 1 | 71.7 | 72.4 | 43.1 | 61.7 | 87.8 | 89.7 | 75.6 |
35
+ | 7 | Skywork | 3e-6 | 1 | 70.5 | 62.5 | 38.1 | 66.7 | 92.0 | 92.3 | 71.1 |
36
+ | 8 | Combined | 1e-6 | 1 | 70.4 | 69.5 | 39.4 | 65.6 | 88.7 | 85.9 | 73.3 |
37
+ | 9 | Tulu | 3e-6 | 1 | 69.4 | 75.4 | 45.0 | 63.9 | 86.7 | 76.2 | 69.1 |
38
+ | 10 | Tulu | 3e-6 | 2 | 68.1 | 71.4 | 44.4 | 62.8 | 86.4 | 76.0 | 67.8 |
39
+ | 11 | Tulu | 1e-6 | 2 | 67.5 | 67.2 | 40.0 | 63.4 | 87.6 | 77.4 | 69.8 |
40
+ | 12 | Tulu | 3e-6 | 1 | 67.5 | 72.4 | 40.6 | 62.8 | 84.2 | 75.4 | 69.8 |
41
+ | 13 | Combined | 2e-5 | 1 | 67.2 | 66.3 | 36.9 | 62.8 | 82.0 | 83.0 | 71.9 |
42
+ | 14 | Skywork | 1e-6 | 1 | 66.6 | 59.8 | 36.9 | 63.4 | 89.6 | 86.1 | 64.2 |
43
+ | 15 | Tulu | 1e-6 | 1 | 66.4 | 69.5 | 40.6 | 62.8 | 84.2 | 72.7 | 68.3 |
44
+ | 16 | Tulu | 3e-6 | 1 | 65.7 | 73.1 | 36.9 | 62.8 | 82.9 | 70.3 | 68.4 |
45
+ | 17 | Combined | 2e-5 | 2 | 62.1 | 63.6 | 37.5 | 59.0 | 82.7 | 80.2 | 49.5 |
46
 
47
 
48
  - **Developed by:** [More Information Needed]