LegalLMs
Collection
XLM-RoBERTa models with continued pretraining on the MultiLegalPile
•
37 items
•
Updated
•
2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7922 | 18.01 | 50000 | 0.5792 |
0.7107 | 37.01 | 100000 | 0.5011 |
0.6712 | 56.01 | 150000 | 0.4763 |
0.6598 | 75.01 | 200000 | 0.4611 |