Update README.md

README.md

@@ -21,7 +21,9 @@ This lora was trained on 250k post and response pairs from 43 different fincial,
 
 ## Training Details
 
-1 note worthy change I will mention now, is this was trained with casualLM rather than seq2seq like a number of the other instruct models have been. I can't explain why they used seq2seq for data collators, other than that's what alpaca lora originally used. Llama as a generative model was trained for casualLM so to me it makes sense to use that when fine tuning.
+* Training took ~30hrs on 5x3090s and used almost 23gb of vram on each. DDP was used for pytorch parallelism. 
+
+* 1 note worthy change I will mention now, is this was trained with casualLM rather than seq2seq like a number of the other instruct models have been. I can't explain why they used seq2seq for data collators, other than that's what alpaca lora originally used. Llama as a generative model was trained for casualLM so to me it makes sense to use that when fine tuning.
 
 * More coming soon.