# Can't load exist dataset for evaluation

**URL:** <https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622>\
**Category:** 🤗Datasets\
**Created:** [May 7, 2024, 11:53am UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622 "2024-05-07T11:53:13Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![IsmaelMousa](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ismaelmousa/32/26723_2.png) [@IsmaelMousa](https://discuss.huggingface.co/u/IsmaelMousa)\
**Post date:** [May 7, 2024, 11:53am UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622/1 "2024-05-07T11:53:13Z")

</div>

Hi, I used `dair-ai/emotion` to fine-tune the `bert-base-cased` model to use it for text-classification task.

The dataset is loaded when I load it in this script, so there is no problem up to here:

```python
from datasets import load_dataset

dataset = load_dataset("dair-ai/emotion")

```

But in the evaluation script here:

```python

import numpy as np
import evaluate

predictions = trainer.predict(eval_dataset)

preds = np.argmax(predictions.predictions, axis=-1)

metric = evaluate.load("dair-ai/emotion")

metric.compute(predictions=preds, references=predictions.label_ids)

```

I got: **FileNotFoundError** : Couldn’t find a module script at /content/dair-ai/emotion/emotion.py. **Module ‘dair-ai/emotion’ doesn’t exist on the Hugging Face Hub either.**

I tried to find out the reason but did not find the solution.

---

<div class="post-metadata">

**Author:** ![IsmaelMousa](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ismaelmousa/32/26723_2.png) [@IsmaelMousa](https://discuss.huggingface.co/u/IsmaelMousa)\
**Post date:** [May 13, 2024, 4:34pm UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622/2 "2024-05-13T16:34:47Z")

</div>

Hellllo :))

---

<div class="post-metadata">

**Author:** ![jerome-white](https://avatars.discourse-cdn.com/v4/letter/j/a587f6/32.png) [@jerome-white](https://discuss.huggingface.co/u/jerome-white)\
**Post date:** [May 14, 2024, 8:16am UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622/3 "2024-05-14T08:16:15Z")

</div>

Does the issue I recently filed ([DataFilesNotFoundError for datasets in the open-llm-leaderboard](https://github.com/huggingface/datasets/issues/6866)) sound like what you’re experiencing? There was no resolution, but perhaps you’re at least not alone

---

<div class="post-metadata">

**Author:** ![IsmaelMousa](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ismaelmousa/32/26723_2.png) [@IsmaelMousa](https://discuss.huggingface.co/u/IsmaelMousa)\
**Post date:** [May 14, 2024, 4:57pm UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622/4 "2024-05-14T16:57:56Z")

</div>

No, it is not the same. All that matters is that the dataset already exists on the Hub and I used it in the data preparation phase, but at the evaluation phase there is an error saying that the dataset does not exist on the Hub.

I think the problem is from the `evaluate` lib,  
And I have already opened an Issue on GitHub, but on `evaluate` repo.

[issue link](https://github.com/huggingface/evaluate/issues/589)

---

<div class="post-metadata">

**Author:** ![ullaimlu](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/ullaimlu/32/47610_2.png) [@ullaimlu](https://discuss.huggingface.co/u/ullaimlu)\
**Post date:** [May 15, 2025, 8:15pm UTC](https://discuss.huggingface.co/t/cant-load-exist-dataset-for-evaluation/85622/5 "2025-05-15T20:15:38Z")

</div>

i solve it with

```auto
import os
os.chdir(os.path.expanduser("~"))

```