| | --- |
| | inference: |
| | parameters: |
| | function_to_apply: "none" |
| | widget: |
| | - text: "I cuddled with my dog today." |
| | --- |
| | |
| | # Utilitarian Roberta 01 |
| |
|
| | ## Model description |
| |
|
| | This is a [Roberta model](https://huggingface.co/roberta-large) fine-tuned on for computing utility estimates of experiences, represented in first-person sentences. It was trained from human-annotated pairwise utility comparisons, from the [ETHICS dataset](https://arxiv.org/abs/2008.02275). |
| |
|
| | ## Intended use |
| |
|
| | The main use case is the computation of utility estimates of first-person text scenarios. |
| |
|
| | ## Limitations |
| |
|
| | The model was only trained on a limited number of scenarios, and only on first-person sentences. It does not have the capability of interpreting highly complex or unusual scenarios, and it does not have hard guarantees on its domain of accuracy. |
| |
|
| | ## How to use |
| |
|
| | The model receives a sentence describing a scenario in first-person, and outputs a scalar representing a utility estimate. |
| |
|
| | ## Training data |
| |
|
| | The training data is the train split from the Utilitarianism part of the [ETHICS dataset](https://arxiv.org/abs/2008.02275). |
| |
|
| | ## Training procedure |
| |
|
| | Training can be reproduced by executing the training procedure from [`tune.py`](https://github.com/hendrycks/ethics/blob/3e4c09259a1b4022607da093e9452383fc1bb7e3/utilitarianism/tune.py) as follows: |
| |
|
| | ``` |
| | python tune.py --ngpus 1 --model roberta-large --learning_rate 1e-5 --batch_size 16 --nepochs 2 |
| | ``` |
| |
|
| | ## Evaluation results |
| |
|
| | The model achieves 90.8% accuracy on [The Moral Uncertainty Research Competition](https://moraluncertainty.mlsafety.org/), which consists of a subset of the ETHICS dataset. |
