<!-- 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. -->
bert-large-cased-sigir-support-refute-no-label-40-2nd-test-LR100-40
This model is a fine-tuned version of jojoUla/bert-large-cased-sigir-support-refute-no-label-40 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4444
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: 4e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1928 | 1.0 | 1 | 5.0343 |
| 3.8865 | 2.0 | 2 | 4.7751 |
| 4.0526 | 3.0 | 3 | 2.2212 |
| 2.3444 | 4.0 | 4 | 1.6810 |
| 1.596 | 5.0 | 5 | 1.3135 |
| 1.6805 | 6.0 | 6 | 1.2568 |
| 1.1736 | 7.0 | 7 | 1.5288 |
| 1.2663 | 8.0 | 8 | 1.4556 |
| 1.3703 | 9.0 | 9 | 1.1139 |
| 0.9768 | 10.0 | 10 | 1.0658 |
| 1.0132 | 11.0 | 11 | 1.2556 |
| 0.9896 | 12.0 | 12 | 1.1046 |
| 1.1184 | 13.0 | 13 | 1.0522 |
| 0.8142 | 14.0 | 14 | 1.3122 |
| 0.706 | 15.0 | 15 | 1.0713 |
| 0.7227 | 16.0 | 16 | 1.4111 |
| 0.7169 | 17.0 | 17 | 0.5603 |
| 0.7922 | 18.0 | 18 | 1.0911 |
| 0.7763 | 19.0 | 19 | 0.6882 |
| 0.5832 | 20.0 | 20 | 1.4459 |
| 0.7265 | 21.0 | 21 | 1.5459 |
| 0.7249 | 22.0 | 22 | 0.9200 |
| 0.5397 | 23.0 | 23 | 1.0976 |
| 0.5063 | 24.0 | 24 | 1.1201 |
| 0.6569 | 25.0 | 25 | 1.0701 |
| 0.472 | 26.0 | 26 | 1.7735 |
| 0.6124 | 27.0 | 27 | 1.3597 |
| 0.6042 | 28.0 | 28 | 0.9292 |
| 0.5232 | 29.0 | 29 | 1.4994 |
| 0.4961 | 30.0 | 30 | 1.2059 |
| 0.371 | 31.0 | 31 | 1.2648 |
| 0.4746 | 32.0 | 32 | 1.0907 |
| 0.4901 | 33.0 | 33 | 1.2564 |
| 0.5066 | 34.0 | 34 | 1.9231 |
| 0.6352 | 35.0 | 35 | 1.0160 |
| 0.5672 | 36.0 | 36 | 1.2958 |
| 0.5139 | 37.0 | 37 | 0.9384 |
| 0.5583 | 38.0 | 38 | 1.9518 |
| 0.5443 | 39.0 | 39 | 1.4243 |
| 0.5935 | 40.0 | 40 | 1.3882 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
