<!-- 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. -->
AkeyLegalBert_inScotus_and_Ledgar_14epoch
This model is a fine-tuned version of hatemestinbejaia/AkeyLegalBert_inScotus_and_Ledgar on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.3286
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
- num_epochs: 7.0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
3.3388 | 1.0 | 9878 | 3.5630 |
3.2344 | 2.0 | 19756 | 3.5443 |
3.2459 | 3.0 | 29634 | 3.4798 |
3.2394 | 4.0 | 39512 | 3.4407 |
3.2801 | 5.0 | 49390 | 3.4104 |
3.2772 | 6.0 | 59268 | 3.3571 |
3.3636 | 7.0 | 69146 | 3.3350 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1