README.md

---
base_model: bert-base-multilingual-uncased
datasets:
- nguha/legalbench
license: apache-2.0
tags:
- embedding_space_map
- BaseLM:bert-base-multilingual-uncased
---

# ESM nguha/legalbench

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

ESM

- **Developed by:** David Schulte
- **Model type:** ESM
- **Base Model:** bert-base-multilingual-uncased
- **Intermediate Task:** nguha/legalbench
- **ESM architecture:** linear
- **Language(s) (NLP):** [More Information Needed]
- **License:** Apache-2.0 license

## Training Details

### Intermediate Task
- **Task ID:** nguha/legalbench
- **Subset [optional]:** supply_chain_disclosure_disclosed_audits
- **Text Column:** text
- **Label Column:** answer
- **Dataset Split:**  train
- **Sample size [optional]:** 8
- **Sample seed [optional]:** 

### Training Procedure [optional]

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Language Model Training Hyperparameters [optional]
- **Epochs:** 3
- **Batch size:** 32
- **Learning rate:** 2e-05
- **Weight Decay:** 0.01
- **Optimizer**: AdamW

### ESM Training Hyperparameters [optional]
- **Epochs:** 10
- **Batch size:** 32
- **Learning rate:** 0.001
- **Weight Decay:** 0.01
- **Optimizer**: AdamW


### Additional trainiung details [optional]


## Model evaluation

### Evaluation of fine-tuned language model [optional]


### Evaluation of ESM [optional]
MSE: 

### Additional evaluation details [optional]



## What are Embedding Space Maps?

<!-- This section describes the evaluation protocols and provides the results. -->
Embedding Space Maps (ESMs) are neural networks that approximate the effect of fine-tuning a language model on a task. They can be used to quickly transform embeddings from a base model to approximate how a fine-tuned model would embed the the input text.
ESMs can be used for intermediate task selection with the ESM-LogME workflow.

## How can I use Embedding Space Maps for Intermediate Task Selection?
[![PyPI version](https://img.shields.io/pypi/v/hf-dataset-selector.svg)](https://pypi.org/project/hf-dataset-selector)

We release **hf-dataset-selector**, a Python package for intermediate task selection using Embedding Space Maps.

**hf-dataset-selector** fetches ESMs for a given language model and uses it to find the best dataset for applying intermediate training to the target task. ESMs are found by their tags on the Huggingface Hub.

```python
from hfselect import Dataset, compute_task_ranking

# Load target dataset from the Hugging Face Hub
dataset = Dataset.from_hugging_face(
    name="stanfordnlp/imdb",
    split="train",
    text_col="text",
    label_col="label",
    is_regression=False,
    num_examples=1000,
    seed=42
)

# Fetch ESMs and rank tasks
task_ranking = compute_task_ranking(
    dataset=dataset,
    model_name="bert-base-multilingual-uncased"
)

# Display top 5 recommendations
print(task_ranking[:5])
```

For more information on how to use ESMs please have a look at the [official Github repository](https://github.com/davidschulte/hf-dataset-selector).

## Citation


<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
If you are using this Embedding Space Maps, please cite our [paper](https://arxiv.org/abs/2410.15148).

**BibTeX:**


```
@misc{schulte2024moreparameterefficientselectionintermediate,
      title={Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning}, 
      author={David Schulte and Felix Hamborg and Alan Akbik},
      year={2024},
      eprint={2410.15148},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2410.15148}, 
}
```


**APA:**

```
Schulte, D., Hamborg, F., & Akbik, A. (2024). Less is More: Parameter-Efficient Selection of Intermediate Tasks for Transfer Learning. arXiv preprint arXiv:2410.15148.
```

## Additional Information