legalbert-adept
This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6927
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 70.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
5.4774 | 1.0 | 907 | 4.6352 |
4.5985 | 2.0 | 1814 | 4.2252 |
4.2598 | 3.0 | 2721 | 3.9970 |
4.0564 | 4.0 | 3628 | 3.8458 |
3.852 | 5.0 | 4535 | 3.6996 |
3.7954 | 6.0 | 5442 | 3.5729 |
3.6572 | 7.0 | 6349 | 3.4669 |
3.5174 | 8.0 | 7256 | 3.3176 |
3.3779 | 9.0 | 8163 | 3.1742 |
3.2451 | 10.0 | 9070 | 3.1204 |
3.1785 | 11.0 | 9977 | 3.0070 |
3.0627 | 12.0 | 10884 | 2.9171 |
2.9859 | 13.0 | 11791 | 2.8068 |
2.8921 | 14.0 | 12698 | 2.7104 |
2.7894 | 15.0 | 13605 | 2.6986 |
2.754 | 16.0 | 14512 | 2.6349 |
2.6242 | 17.0 | 15419 | 2.5321 |
2.6069 | 18.0 | 16326 | 2.5110 |
2.5147 | 19.0 | 17233 | 2.4618 |
2.4694 | 20.0 | 18140 | 2.3947 |
2.4267 | 21.0 | 19047 | 2.3827 |
2.3936 | 22.0 | 19954 | 2.3171 |
2.3613 | 23.0 | 20861 | 2.2848 |
2.2855 | 24.0 | 21768 | 2.2050 |
2.2256 | 25.0 | 22675 | 2.1967 |
2.2242 | 26.0 | 23582 | 2.1683 |
2.1924 | 27.0 | 24489 | 2.1475 |
2.136 | 28.0 | 25396 | 2.1203 |
2.0947 | 29.0 | 26303 | 2.0854 |
2.1093 | 30.0 | 27210 | 2.0813 |
2.0255 | 31.0 | 28117 | 2.0102 |
1.9977 | 32.0 | 29024 | 2.0168 |
1.9815 | 33.0 | 29931 | 2.0015 |
1.9804 | 34.0 | 30838 | 1.9795 |
1.9459 | 35.0 | 31745 | 1.9581 |
1.9032 | 36.0 | 32652 | 1.9227 |
1.8959 | 37.0 | 33559 | 1.9146 |
1.9449 | 38.0 | 34466 | 1.8836 |
1.8673 | 39.0 | 35373 | 1.9147 |
1.8379 | 40.0 | 36280 | 1.9020 |
1.8424 | 41.0 | 37187 | 1.8786 |
1.8173 | 42.0 | 38094 | 1.8736 |
1.8092 | 43.0 | 39001 | 1.8398 |
1.7937 | 44.0 | 39908 | 1.8393 |
1.7844 | 45.0 | 40815 | 1.7940 |
1.7868 | 46.0 | 41722 | 1.8064 |
1.7554 | 47.0 | 42629 | 1.7834 |
1.7161 | 48.0 | 43536 | 1.7966 |
1.7715 | 49.0 | 44443 | 1.8080 |
1.7177 | 50.0 | 45350 | 1.7561 |
1.6985 | 51.0 | 46257 | 1.7451 |
1.7119 | 52.0 | 47164 | 1.7476 |
1.6712 | 53.0 | 48071 | 1.7359 |
1.6765 | 54.0 | 48978 | 1.7663 |
1.6749 | 55.0 | 49885 | 1.7227 |
1.6639 | 56.0 | 50792 | 1.7032 |
1.6363 | 57.0 | 51699 | 1.7090 |
1.6378 | 58.0 | 52606 | 1.7037 |
1.6237 | 59.0 | 53513 | 1.7047 |
1.6311 | 60.0 | 54420 | 1.7031 |
1.592 | 61.0 | 55327 | 1.7099 |
1.6111 | 62.0 | 56234 | 1.6824 |
1.6026 | 63.0 | 57141 | 1.6669 |
1.6252 | 64.0 | 58048 | 1.6886 |
1.6184 | 65.0 | 58955 | 1.6742 |
1.6088 | 66.0 | 59862 | 1.7186 |
1.6246 | 67.0 | 60769 | 1.6937 |
1.5948 | 68.0 | 61676 | 1.6868 |
1.5951 | 69.0 | 62583 | 1.7186 |
1.5775 | 70.0 | 63490 | 1.6775 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Downloads last month
- 11
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.