Issue Week 3 Lab3. Timeout error loading dataset

Course Q&A Generative AI with Large Language Models
1

When run this istructions:

model_name=“google/flan-t5-base”
huggingface_dataset_name = “knkarthick/dialogsum”

dataset_original = load_dataset(huggingface_dataset_name)

dataset_original

I´m getting timeout error when try to load dataset:

TimeoutError Traceback (most recent call last)
File , in HTTPConnectionPool._make_request(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)
466 try:
→ 467 self._validate_conn(conn)
468 except (SocketTimeout, BaseSSLError) as e:

…
ReadTimeout: (ReadTimeoutError(“HTTPSConnectionPool(h’, port=443): Read timed out. (read timeout=10)”), ‘(Request ID: fbcf779c-50af-463e-af3b-224580a35a7d)’)

Anybody might help me.

2

Hello there,

it seems to be an issue with Hugging Face servers, many learners are experiencing the same error.

Check here:

1 Like
3

Thank you Anna_Key, I manage to load datasets but same error apears when I run others commands like this one:

tokenizer = AutoTokenizer.from_pretrained(model_name, device_map=“auto”)

Do you know if I can do the lab again when this king of issues are fixed?

4

Yes you can do the lab again, you will have to open it the same way as you already did.

In case you encounter issues with the AWS budget, although I don’t think there will be any, you can fill a Lab issue report (GenAI with LLMs Lab Issue Report).

1 Like
5

I tried to do it twice today, but I always get the same error. I really wish they solve that soon.