bert_uncased_L-4_H-512_A-8-finetuned-legal-definitions-longer
This model is a fine-tuned version of google/bert_uncased_L-4_H-512_A-8 on the legal-definitions dataset. It achieves the following results on the evaluation set:
- Loss: 1.3701
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4867 | 1.0 | 801 | 1.4951 |
| 1.429 | 2.0 | 1602 | 1.4872 |
| 1.4055 | 3.0 | 2403 | 1.4147 |
| 1.3703 | 4.0 | 3204 | 1.4231 |
| 1.3414 | 5.0 | 4005 | 1.4094 |
| 1.3254 | 6.0 | 4806 | 1.3913 |
| 1.3064 | 7.0 | 5607 | 1.3827 |
| 1.2967 | 8.0 | 6408 | 1.3905 |
| 1.2961 | 9.0 | 7209 | 1.3719 |
| 1.2824 | 10.0 | 8010 | 1.3701 |
Framework versions
- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1