Update README.md

README.md

@@ -97,8 +97,8 @@ Pile-T5 can be loaded using the `AutoModelForSeq2SeqLM` functionality:
 ```python
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pile-t5-base")
-model = AutoModelForSeq2SeqLM.from_pretrained("EleutherAI/pile-t5-base")
+tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pile-t5-xl")
+model = AutoModelForSeq2SeqLM.from_pretrained("EleutherAI/pile-t5-xl")
 ```
 
 ### Training
@@ -132,6 +132,8 @@ There are in total 200 checkpoints that are spaced 10,000 steps. For T5x-native
 checkpoints that can be used for finetuning with the T5x library, refer to [here](https://huggingface.co/lintang/pile-t5-base-t5x/tree/main)
 
 
+The training loss (in tfevent format) and validation perplexity (in jsonl) can be found [here](https://huggingface.co/EleutherAI/pile-t5-xl/blob/main/xl.zip).
+
 ### Evaluations
 
 Pile-T5 XL was evaluated on SuperGLUE, CodeXGLUE. A Flan-finetuned version was evaluated on Flan Held In tasks, MMLU and BBH.