Skip to content

Conversation

@mattflock
Copy link

No description provided.

@nickcom007 nickcom007 self-requested a review April 29, 2024 16:33
```bash
conda create -n llm-loss-validator python==3.10.12
conda activate llm-loss-validator
pip install -r requirements.txt
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggest to navigate to https://github.com/FLock-io/llm-loss-validator first otherwise it could be confusing

--max_seq_length 128 \
--assignment_id <assignment-id> \
--validation_args_file <validation_config.json.example OR validation_config_cpu.json.example>
```
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ran it myself, i think the command should be the following instead:

FLOCK_API_KEY=<YOUR_FLOCK_API_KEY> python validate.py \ --model_name_or_path <MODEL_NAME> \ --eval_file <FILE_PATH> \ --assignment_id 10 \ --validation_args_file validation_config_cpu.json.example \ --base_model <BASE_MODEL> \ --context_length 128


4. Replace `<base_model>` with the corresponding value from the response body in Step 3

5. Replace `<eval_file>` with the `validation_set_url` value from the response body in Step 3
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggest to add a reminder that user needs to download the json file from this link, and also add that the link will expire in an hour

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants