Downloads · 30 days
10
15% of all-time downloads
MHGanainy/roberta-base-legal-indian-courts-downstream-build_rr
roberta-base-legal-indian-courts-downstream-build_rr is a token classification model from MHGanainy. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
15% of all-time downloads
All-time downloads
67
Public
Parameters
138M
10 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors554 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of MHGanainy/roberta-base-legal-indian-courts 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 | Precision-macro | Recall-macro | Macro-f1 | Precision-micro | Recall-micro | Micro-f1 | Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 1.0334 | 0.5138 | 0.3194 | 0.3077 | 0.6985 | 0.6985 | 0.6985 | 0.6985 |
| No log | 2.0 | 248 | 0.8527 | 0.5498 | 0.4996 | 0.4955 | 0.7100 | 0.7100 | 0.7100 | 0.7100 |
| No log | 3.0 | 372 | 0.8072 | 0.5793 | 0.5436 | 0.5415 | 0.7516 | 0.7516 | 0.7516 | 0.7516 |
| No log | 4.0 | 496 | 0.7080 | 0.6448 | 0.5081 | 0.5108 | 0.7687 | 0.7687 | 0.7687 | 0.7687 |
| 1.0492 | 5.0 | 620 | 0.7448 | 0.5787 | 0.6034 | 0.5802 | 0.7600 | 0.7600 | 0.7600 | 0.7600 |
| 1.0492 | 6.0 | 744 | 0.7185 | 0.6264 | 0.5507 | 0.5596 | 0.7746 | 0.7746 | 0.7746 | 0.7746 |
| 1.0492 | 7.0 | 868 | 0.7547 | 0.6543 | 0.5620 | 0.5752 | 0.7853 | 0.7853 | 0.7853 | 0.7853 |
| 1.0492 | 8.0 | 992 | 0.7287 | 0.6138 | 0.5746 | 0.5852 | 0.7833 | 0.7833 | 0.7833 | 0.7833 |
| 0.5459 | 9.0 | 1116 | 0.8288 | 0.5778 | 0.6135 | 0.5885 | 0.7631 | 0.7631 | 0.7631 | 0.7631 |
| 0.5459 | 10.0 | 1240 | 0.8364 | 0.6167 | 0.5943 | 0.5987 | 0.7763 | 0.7763 | 0.7763 | 0.7763 |