Update README.md

README.md

@@ -68,7 +68,7 @@ inference:
 
 - **Use cases:** long narrative summarization (think stories - as the dataset intended), article/paper/textbook/other summarization, technical:simple summarization. 
   - Models trained on this dataset tend to also _explain_ what they are summarizing, which IMO is awesome.
-- This is an 'upgraded' version of [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum), it was trained for an additional epoch with a max summary length of 1024 tokens (original was trained with 512) as a small portion of the summaries are between 512-1024 tokens long.
+- This is an 'upgraded' version of [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum), it has trained for a total of six more epochs with the parameters adjusted for _very_ fine-tuning type training (super low LR, etc)
   - all the parameters for generation on the API are the same for easy comparison between versions.
 - works well on lots of text, can hand 16384 tokens/batch.
   
@@ -76,7 +76,7 @@ inference:
 
 - See [led-large-book-summary](https://huggingface.co/pszemraj/led-large-book-summary) for LED-large trained on the same dataset.
 - A version of bigbird-pegasus trained on booksum is [here](https://huggingface.co/pszemraj/bigbird-pegasus-large-K-booksum)
-
+- original baseline checkpoint [`pszemraj/led-base-16384-finetuned-booksum`](https://huggingface.co/pszemraj/led-base-16384-finetuned-booksum)
 ---
 
 # Usage - Basics