Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.0116	0.26	100	0.0941	0.9742	0.9598	0.9824	0.9382
0.0017	0.52	200	0.0769	0.9834	0.9749	0.9669	0.9831
0.0015	0.78	300	0.0606	0.9834	0.9744	0.9884	0.9607
0.0007	1.04	400	0.0996	0.9853	0.9779	0.9620	0.9944
0.0002	1.3	500	0.0377	0.9926	0.9888	0.9833	0.9944
0.0001	1.56	600	0.0521	0.9890	0.9831	0.9831	0.9831
0.0001	1.82	700	0.0678	0.9908	0.9861	0.9779	0.9944
0.0001	2.08	800	0.0603	0.9908	0.9858	0.9943	0.9775
0.0001	2.34	900	0.0425	0.9945	0.9915	0.9944	0.9888
0.0	2.6	1000	0.0438	0.9945	0.9915	0.9944	0.9888
0.0	2.86	1100	0.0410	0.9963	0.9944	0.9944	0.9944
0.0	3.12	1200	0.1029	0.9871	0.9806	0.9672	0.9944
0.0	3.38	1300	0.0315	0.9963	0.9944	0.9944	0.9944
0.0	3.64	1400	0.0316	0.9963	0.9944	0.9944	0.9944
0.0	3.9	1500	0.0316	0.9963	0.9944	0.9944	0.9944
0.0	4.16	1600	0.0317	0.9963	0.9944	0.9944	0.9944
0.0	4.42	1700	0.0316	0.9963	0.9944	0.9944	0.9944
0.0	4.68	1800	0.0316	0.9963	0.9944	0.9944	0.9944
0.0	4.94	1900	0.0316	0.9963	0.9944	0.9944	0.9944

Framework versions

Transformers 4.23.1
Pytorch 1.13.0+cu117
Datasets 2.6.1
Tokenizers 0.13.1

Public release information

This model is released by the SCALES Open Knowledge Network under the GNU General Public License v3.0. It is derived from scales-okn/docket-language-model and is intended for research and development involving legal-document classification or information extraction. It is not legal advice.

The organization has reviewed the release decision and confirmed that the model's training data and resulting weights are legally and ethically releasable. Users are responsible for evaluating accuracy, bias, privacy, and fitness for their own use.

The repository includes PyTorch .bin artifacts. Hugging Face's server-side security scan reported no file issues before publication. As with any serialized model artifact, load it only with maintained libraries and in an appropriately isolated environment.

scales-okn/ontology-motion-for-summary-judgment

ontology-motion-for-summary-judgment

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Public release information

scales-okn/
ontology-motion-for-summary-judgment