This is a roberta-base model that is trained to classify whether a set of explicit stated aims extracted from a British
historical patent includes a labor-augmenting objective.
Labels were manually generated and then checked with Gemini 2.0 Flash with the attached
prompt.
1{'eval_loss': 0.2932845950126648,
2 'eval_accuracy': 0.9,
3 'eval_precision': 0.9,
4 'eval_recall': 0.9,
5 'eval_f1': 0.9,
6 'eval_runtime': 0.3819,
7 'eval_samples_per_second': 157.109,
8 'eval_steps_per_second': 2.618}
