Hugging Face's logo

ymcki
/
gemma-2-2b-jpn-it-abliterated-17-ORPO

Text Generation
Transformers
Safetensors
multilingual
gemma2
nlp
code
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
ymcki commited on
Commit
df03492
·
1 Parent(s): 8e597a2

fix README again

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -43,9 +43,8 @@ I also created another layer 18 and 24 abliterated model for comparison.
43
  ORPO fine tuning was performed for eight epoches. Lowest eval_loss at 7.48 epoch.
44
  Checkpoint at 7.48 epoch was chosen to generate this model.
45
 
46
- | ----- | ---- | --------- | eval | eval |
47
- | Epoch | loss | eval_loss | logps/rejected | logps/chosen |
48
- | ----- | ---- | --------- | -------------- | ------------ |
49
  | 1.00 | 1.2015 | 1.0501 | -1.0451 | -0.7449 |
50
  | 2.00 | 1.2576 | 1.0145 | -1.1346 | -0.7248 |
51
  | 3.00 | 0.9310 | 0.9958 | -1.2629 | -0.7332 |
 
43
  ORPO fine tuning was performed for eight epoches. Lowest eval_loss at 7.48 epoch.
44
  Checkpoint at 7.48 epoch was chosen to generate this model.
45
 
46
+ | Epoch | loss | eval_loss | eval_logps/rejected | eval_logps/chosen |
47
+ | ----- | ---- | --------- | ------------------- | ----------------- |
 
48
  | 1.00 | 1.2015 | 1.0501 | -1.0451 | -0.7449 |
49
  | 2.00 | 1.2576 | 1.0145 | -1.1346 | -0.7248 |
50
  | 3.00 | 0.9310 | 0.9958 | -1.2629 | -0.7332 |