|
|
--- |
|
|
library_name: transformers |
|
|
tags: [] |
|
|
--- |
|
|
|
|
|
# Labor Augmenting Stated Aim Classifier |
|
|
|
|
|
This is a roberta-base model that is trained to classify whether a set of explicit stated aims extracted from a British [historical patent](https://huggingface.co/datasets/matthewleechen/300YearsOfBritishPatents) includes a labor-augmenting objective. |
|
|
|
|
|
Labels were manually generated and then checked with Gemini 2.0 Flash with the attached [prompt](https://huggingface.co/matthewleechen/labor-augmenting_stated_aim_classifier/blob/main/labor-augmenting_prompt.txt). |
|
|
|
|
|
Hyperparameters: |
|
|
lr = 7e-5 |
|
|
batch size = 128 |
|
|
|
|
|
Test set results: |
|
|
|
|
|
```text |
|
|
{'eval_loss': 0.2932845950126648, |
|
|
'eval_accuracy': 0.9, |
|
|
'eval_precision': 0.9, |
|
|
'eval_recall': 0.9, |
|
|
'eval_f1': 0.9, |
|
|
'eval_runtime': 0.3819, |
|
|
'eval_samples_per_second': 157.109, |
|
|
'eval_steps_per_second': 2.618} |
|
|
``` |
|
|
|
|
|
|
