Text Generation
Transformers
PyTorch
Safetensors
English
gpt2
alignment
instruction tuned
text generation
conversation
assistant
dpo
text-generation-inference
Inference Endpoints
nicholasKluge commited on
Commit
6ce8837
1 Parent(s): 061e6e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -0
README.md CHANGED
@@ -53,6 +53,23 @@ extra_args:
53
  beta: 0.8
54
  ```
55
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  ## Eval
57
 
58
  | Task |Version| Metric |Value | |Stderr|
 
53
  beta: 0.8
54
  ```
55
 
56
+ ## Logs
57
+
58
+ | Key | Value |
59
+ |-----------------------|---------------------------------|
60
+ | loss | 0.2274 |
61
+ | learning_rate | 4.976714865090827e-05 |
62
+ | rewards/chosen | -33.849693298339844 |
63
+ | rewards/rejected | -114.72045135498047 |
64
+ | rewards/accuracies | 0.9768750071525574 |
65
+ | rewards/margins | 80.87075805664062 |
66
+ | logps/rejected | -404.8834228515625 |
67
+ | logps/chosen | -383.7469482421875 |
68
+ | logits/rejected | -67.6454086303711 |
69
+ | logits/chosen | -30.543472290039062 |
70
+ | epoch | 0.05 |
71
+
72
+
73
  ## Eval
74
 
75
  | Task |Version| Metric |Value | |Stderr|