<!-- 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-LR10-40-0-prompt
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: 0.1867
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: 20.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.4282 | 1.0 | 1 | 6.2572 |
5.1897 | 2.0 | 2 | 0.8887 |
5.3182 | 3.0 | 3 | 0.5006 |
3.5777 | 4.0 | 4 | 4.5763 |
2.8563 | 5.0 | 5 | 1.1608 |
2.9237 | 6.0 | 6 | 0.1457 |
2.6571 | 7.0 | 7 | 1.3326 |
2.0324 | 8.0 | 8 | 0.8740 |
1.953 | 9.0 | 9 | 0.1867 |
1.5396 | 10.0 | 10 | 2.7574 |
1.4795 | 11.0 | 11 | 0.6534 |
1.0338 | 12.0 | 12 | 0.7555 |
1.2048 | 13.0 | 13 | 0.4882 |
1.1804 | 14.0 | 14 | 3.7854 |
1.1336 | 15.0 | 15 | 2.1575 |
0.8142 | 16.0 | 16 | 0.7917 |
0.6188 | 17.0 | 17 | 0.6608 |
0.6794 | 18.0 | 18 | 3.5129 |
1.0154 | 19.0 | 19 | 0.1962 |
0.4131 | 20.0 | 20 | 1.5695 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2