Downloads · 30 days
20
24% of all-time downloads
roberta-base-legal-multi-downstream-build_rr
MHGanainy/roberta-base-legal-multi-downstream-build_rr
roberta-base-legal-multi-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. --
All-time downloads
82
Public
Parameters
138M
17.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors554 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Aug 25, 2024
- Updated
- Aug 25, 2024
- SHA
- 6f910f9b
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
roberta-base-legal-multi-downstream-build_rr
This model is a fine-tuned version of MHGanainy/roberta-base-legal-multi on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8987
- Precision-macro: 0.6721
- Recall-macro: 0.5833
- Macro-f1: 0.6019
- Precision-micro: 0.7864
- Recall-micro: 0.7864
- Micro-f1: 0.7864
- Accuracy: 0.7864
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision-macro | Recall-macro | Macro-f1 | Precision-micro | Recall-micro | Micro-f1 | Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 0.8509 | 0.5354 | 0.4685 | 0.4732 | 0.7520 | 0.7520 | 0.7520 | 0.7520 |
| No log | 2.0 | 248 | 0.8284 | 0.5216 | 0.5460 | 0.5157 | 0.7117 | 0.7117 | 0.7117 | 0.7117 |
| No log | 3.0 | 372 | 0.7703 | 0.5761 | 0.5531 | 0.5450 | 0.7600 | 0.7600 | 0.7600 | 0.7600 |
| No log | 4.0 | 496 | 0.7000 | 0.6454 | 0.5316 | 0.5460 | 0.7801 | 0.7801 | 0.7801 | 0.7801 |
| 0.9835 | 5.0 | 620 | 0.7343 | 0.6004 | 0.5919 | 0.5832 | 0.7694 | 0.7694 | 0.7694 | 0.7694 |
| 0.9835 | 6.0 | 744 | 0.7321 | 0.6138 | 0.5588 | 0.5662 | 0.7787 | 0.7787 | 0.7787 | 0.7787 |
| 0.9835 | 7.0 | 868 | 0.7456 | 0.6322 | 0.5782 | 0.5897 | 0.7815 | 0.7815 | 0.7815 | 0.7815 |
| 0.9835 | 8.0 | 992 | 0.7454 | 0.6145 | 0.5999 | 0.6008 | 0.7864 | 0.7864 | 0.7864 | 0.7864 |
| 0.5025 | 9.0 | 1116 | 0.8391 | 0.6037 | 0.5996 | 0.5978 | 0.7753 | 0.7753 | 0.7753 | 0.7753 |
| 0.5025 | 10.0 | 1240 | 0.8464 | 0.6166 | 0.5677 | 0.5832 | 0.7798 | 0.7798 | 0.7798 | 0.7798 |
| 0.5025 | 11.0 | 1364 | 0.8987 | 0.6721 | 0.5833 | 0.6019 | 0.7864 | 0.7864 | 0.7864 | 0.7864 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- Created
- Aug 25, 2024
- Updated
- Aug 25, 2024