@@ -50,6 +50,10 @@ This mode supports a number of command-line arguments, the details of which can
* `--wandb_args`: Tracks logging to Weights and Biases for evaluation runs and includes args passed to `wandb.init`, such as `project` and `job_type`. Full list (here.)[https://docs.wandb.ai/ref/python/init]. e.g., ```--wandb_args project=test-project,name=test-run```
* `--hf_hub_log_args`: To push results and samples to the Hugging Face Hub. First ensure an access token with write access is set in the `HF_TOKEN` environment variable. Then, use this flag to specify the organization, repository name, repository visibility, and whether to push results and samples to the Hub. e.g., ```--hf_hub_log_args hub_results_org=EleutherAI,hub_repo_name=lm-eval-results,public_repo=False,push_samples_to_hub=True```
## External Library Usage
We also support using the library's external API for use within model training loops or other scripts.
Title: `COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances`
Abstract: `https://arxiv.org/abs/2311.01012`
`COPAL-ID is an Indonesian causal commonsense reasoning dataset that captures local nuances. It provides a more natural portrayal of day-to-day causal reasoning within the Indonesian (especially Jakartan) cultural sphere. Professionally written and validatid from scratch by natives, COPAL-ID is more fluent and free from awkward phrases, unlike the translated XCOPA-ID.`
Homepage: `https://github.com/haryoa/copal-id`
### Citation
```
@article{wibowo2023copal,
title={COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances},
author={Wibowo, Haryo Akbarianto and Fuadi, Erland Hilman and Nityasya, Made Nindyatama and Prasojo, Radityo Eko and Aji, Alham Fikri},
journal={arXiv preprint arXiv:2311.01012},
year={2023}
}
```
### Groups and Tasks
#### Groups
*`copal_id`
#### Tasks
*`copal_id_standard`: `Standard version of COPAL dataset, use formal language and less local nuances`
*`copal_id_colloquial`: `Colloquial version of COPAL dataset, use informal language and more local nuances`
### Checklist
For adding novel benchmarks/datasets to the library:
* [x] Is the task an existing benchmark in the literature?
* [x] Have you referenced the original paper that introduced the task?
* [x] If yes, does the original paper provide a reference implementation? If so, have you checked against the reference implementation and documented how to run such a test?
If other tasks on this dataset are already supported:
* [ ] Is the "Main" variant of this task clearly denoted?
* [ ] Have you provided a short sentence in a README on what each new variant adds / evaluates?
* [ ] Have you noted which, if any, published evaluation setups are matched by this variant?
