jina-embeddings-v2-base-en-finetuned-legalcorpus
This model is a fine-tuned version of jinaai/jina-embeddings-v2-base-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.5728
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 |
|---|---|---|---|
| No log | 1.0 | 79 | 5.4931 |
| No log | 2.0 | 158 | 5.2537 |
| No log | 3.0 | 237 | 5.1049 |
| No log | 4.0 | 316 | 4.9755 |
| No log | 5.0 | 395 | 4.8611 |
| No log | 6.0 | 474 | 4.7611 |
| 5.1847 | 7.0 | 553 | 4.6757 |
| 5.1847 | 8.0 | 632 | 4.6213 |
| 5.1847 | 9.0 | 711 | 4.5839 |
| 5.1847 | 10.0 | 790 | 4.5728 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0