docs: update README

README.md

@@ -55,8 +55,14 @@ See [WandB logs](https://wandb.ai/d0rj/summarization/runs/5mmyskgi).
 
 See report at **REPORT WIP**.
 
+## Notes
+
+> Scheduler, optimizer and trainer states are saved into this repo, so you can use that to continue finetune with your own data with existing gradients.
+
 ## Usage
 
+### Summarization pipeline
+
 ```python
 from transformers import pipeline
 
@@ -65,6 +71,8 @@ pipe = pipeline('summarization', model='d0rj/rut5-base-summ')
 pipe(text)
 ```
 
+### Text-to-text generation
+
 ```python
 from transformers import T5Tokenizer, T5ForConditionalGeneration