Update README.md

README.md

@@ -5,14 +5,14 @@ license: llama2
 
 ## THIS IS A PLACEHOLDER, MODEL COMMING SOON
 
-CyberBase 13b 8k *base model* - (llama-2-13b - lmsys/vicuna-13b-v1.5-16k)
+CyberBase is an experimental *base model* for cybersecurity. (llama-2-13b -> lmsys/vicuna-13b-v1.5-16k -> CyberBase)
 
 ## Test run 1 (less context, more trainable params):
 - sequence_len: 4096
 - max_packed_sequence_len: 4096
 - lora_r: 256
 - lora_alpha: 128
-- num_epochs: 2
+- num_epochs: 3
 - trainable params: 1,001,390,080 || all params: 14,017,264,640 || trainable%: 7.143976415643959
 
 # Base cybersecurity model for future fine-tuning, it is not recomended to use on it's own.