Hugging Face's logo

shisa-ai
/
shisa-v1-llama3-8b

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
leonardlin commited on
Commit
d09c2a1
•
1 Parent(s): 9777a00

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -21,8 +21,8 @@ I ran the tests for 2 runs just to try to lower variance. These are all using te
21
  |-----------------------------|-----------|----------|-------------|--------|-------------|-----------|
22
  | shisa-v1-llama3-8b.lr-2e4 | 3.97 | 4.60 | 4.54 | 3.33 | 3.42 | 92.42% |
23
  | shisa-v1-llama3-8b.lr-5e5 | 5.73 | 6.28 | 6.45 | 5.37 | 4.81 | 90.93% |
24
- | shisa-v1-llama3-8b (2e5 avg)| 6.33 | 6.51 | 6.66 | 6.68 | 5.48 | 91.51% |
25
- | shisa-v1-llama3-8b.8e6 | 6.59 | 6.67 | 6.95 | 7.05 | 5.68 | 91.30% |
26
  | shisa-v1-llama3-8b.5e6 | 6.42 | 6.33 | 6.76 | 7.15 | 5.45 | 91.56% |
27
  | shisa-v1-llama3-8b.2e6 | 6.31 | 6.26 | 6.88 | 6.73 | 5.38 | 92.00% |
28
  * The 2e-4 and 5e-5 are definitely overtrained and perform significantly worse.
 
21
  |-----------------------------|-----------|----------|-------------|--------|-------------|-----------|
22
  | shisa-v1-llama3-8b.lr-2e4 | 3.97 | 4.60 | 4.54 | 3.33 | 3.42 | 92.42% |
23
  | shisa-v1-llama3-8b.lr-5e5 | 5.73 | 6.28 | 6.45 | 5.37 | 4.81 | 90.93% |
24
+ | shisa-v1-llama3-8b.2e5 | 6.33 | 6.51 | 6.66 | 6.68 | 5.48 | 91.51% |
25
+ | shisa-v1-llama3-8b (8-e6) | 6.59 | 6.67 | 6.95 | 7.05 | 5.68 | 91.30% |
26
  | shisa-v1-llama3-8b.5e6 | 6.42 | 6.33 | 6.76 | 7.15 | 5.45 | 91.56% |
27
  | shisa-v1-llama3-8b.2e6 | 6.31 | 6.26 | 6.88 | 6.73 | 5.38 | 92.00% |
28
  * The 2e-4 and 5e-5 are definitely overtrained and perform significantly worse.