harishnair04 commited on
Commit
3311fff
·
verified ·
1 Parent(s): ebb3d13

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -31,11 +31,9 @@ This model is a fine-tuned variant of `Gemma-2-2b`, optimized for medical transc
31
 
32
  ### Training Details
33
 
34
- - **Training Loss:** Final training loss at step 10: 1.4791
35
  - **Training Configuration:**
36
  - LoRA with `r=8`, targeting specific transformer modules for adaptation.
37
  - 4-bit quantization using `nf4` quantization type and `bfloat16` compute precision.
38
- - **Training Runtime:** 20.85 seconds, with approximately 1.92 samples processed per second.
39
 
40
  ## How to Use
41
 
 
31
 
32
  ### Training Details
33
 
 
34
  - **Training Configuration:**
35
  - LoRA with `r=8`, targeting specific transformer modules for adaptation.
36
  - 4-bit quantization using `nf4` quantization type and `bfloat16` compute precision.
 
37
 
38
  ## How to Use
39