Update README.md

README.md

@@ -6,6 +6,9 @@ datasets:
 ## LoRA Info:
 Please note that this is a highly experimental LoRA model. It may do some good stuff, it may be bad, it may do nothing and not work. Hopefully after training is fully done, it'll be good!
 
-Current upload: checkpoint of epoch 0.8 (run crashed, was gonna upload at epoch 1 xP).
+Current upload: checkpoint of epoch 1.0 (of 3)
 
-The alpaca-lora repo by tloen doesn't *seem* to create a working adapter/peft model until the training is finalized, but I attempted to turn a checkpoint into one, I hope it works for y'all ^~^ I'd test but the resources are currently being used to continue training!
+The alpaca-lora repo by tloen doesn't *seem* to create an immediately working adapter/peft model until the training is finalized, but I attempted to turn a checkpoint into one.
+I hope it works for y'all ^~^ Thanks to MetaIX for initial seemingly successful testing of the first uploaded checkpoint (epoch 0.8).
+
+**Wikitext2 eval benchmark for epoch 0.8 upload:** 4.548329830169678 (Thanks to Metal/MetaIX)