Hugging Face's logo

Blackroot
/
Llama-2-13B-Storywriter-LORA

Model card Files Community
3
Blackroot commited on
Commit
14eb78b
•
1 Parent(s): 9d47835

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -40,4 +40,4 @@ The following `bitsandbytes` quantization config was used during training:
40
  - bnb_4bit_use_double_quant: False
41
  - bnb_4bit_compute_dtype: float32
42
 
43
- This ran on for 3500 -- 3 epochs on an in testing storywriting dataset. Training took 14 hours on a 3090 Ti.
 
40
  - bnb_4bit_use_double_quant: False
41
  - bnb_4bit_compute_dtype: float32
42
 
43
+ This ran on for 3500 steps -- 3 epochs on an in testing storywriting dataset. Training took 14 hours on a 3090 Ti.