:art:

README.md

@@ -67,7 +67,7 @@ inference:
 # long-t5-tglobal-base-16384-booksum
 
 - summarize long text and get a SparkNotes-esque summary of arbitrary topics!
-- generalizes fairly well to academic & narrative text. 
+- generalizes reasonably well to academic & narrative text. 
 
 ## Cheeky Proof-of-Concept
 
@@ -80,9 +80,9 @@ A summary of the [infamous navy seals copypasta](https://knowyourmeme.com/memes/
 
 A fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on the `kmfoda/booksum` dataset:
 
-- between different checkpoints, about 20 epochs in total
-- all training was done at 16384 token input / 1024 max output
-- early checkpoints of this model were trained on a "smaller" subsection of the dataset as it was filtered for summaries of **1024 characters**. This was subsequently caught and adjusted to **1024 tokens**, and then trained further for at least five epochs. 
+- 20+ epochs of fine-tuning from the base model on V100/A100 GPUs
+- all training used 16384 token input / 1024 max output
+- early checkpoints of this model were trained on a "smaller" subsection of the dataset as it was filtered for summaries of **1024 characters**. This was subsequently caught and adjusted to **1024 tokens**and then trained further for at least five epochs. 
 
 ## Intended uses & limitations
 
@@ -92,7 +92,7 @@ A fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/goo
 
 ## Training and evaluation data
 
-`kmfoda/booksum` dataset. Summaries longer than 1024 LongT5 tokens were filtered out to prevent the model from learning to generate "partial" summaries.
+`kmfoda/booksum` dataset. Summaries longer than 1024 LongT5 tokens were filtered out with the intent of preventing the model from learning to generate "partial" summaries.
 
 ## Training procedure
 
@@ -111,7 +111,7 @@ The following hyperparameters were used during the **final** training round\*:
 - lr_scheduler_warmup_ratio: 0.02
 - num_epochs: 2
 
-\*_Prior training sessions used roughly similar parameters, multiple sessions were required as this takes eons to train_
+\*_Prior training sessions used roughly similar parameters; multiple sessions were required as this takes eons to train_
 
 ### Training results