<!-- 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-no-label-40-sigir-tune2nd-LR10-labelled-40
This model is a fine-tuned version of jojoUla/bert-large-cased-sigir-support-no-label-40 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4091
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: 30
- eval_batch_size: 30
- 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 |
---|---|---|---|
3.0728 | 1.0 | 1 | 3.3883 |
3.6431 | 2.0 | 2 | 4.0303 |
3.4087 | 3.0 | 3 | 2.1767 |
2.522 | 4.0 | 4 | 2.3348 |
1.8187 | 5.0 | 5 | 0.7921 |
1.5562 | 6.0 | 6 | 1.6986 |
1.505 | 7.0 | 7 | 1.7494 |
1.4673 | 8.0 | 8 | 1.5797 |
1.22 | 9.0 | 9 | 1.7811 |
1.5497 | 10.0 | 10 | 2.0455 |
0.8699 | 11.0 | 11 | 2.7731 |
1.6008 | 12.0 | 12 | 2.3984 |
0.9909 | 13.0 | 13 | 1.7870 |
1.4982 | 14.0 | 14 | 1.5336 |
0.88 | 15.0 | 15 | 0.5394 |
0.5231 | 16.0 | 16 | 0.5391 |
1.1294 | 17.0 | 17 | 1.2333 |
1.5638 | 18.0 | 18 | 1.4246 |
1.5274 | 19.0 | 19 | 0.7396 |
1.1525 | 20.0 | 20 | 0.7160 |
0.7708 | 21.0 | 21 | 3.9853 |
0.6681 | 22.0 | 22 | 1.8747 |
0.6073 | 23.0 | 23 | 1.0765 |
0.64 | 24.0 | 24 | 0.7888 |
1.3657 | 25.0 | 25 | 1.0972 |
1.1772 | 26.0 | 26 | 0.6801 |
1.6493 | 27.0 | 27 | 0.8378 |
0.8971 | 28.0 | 28 | 0.5728 |
1.3524 | 29.0 | 29 | 1.7829 |
0.7754 | 30.0 | 30 | 1.8142 |
1.1628 | 31.0 | 31 | 0.7712 |
0.4534 | 32.0 | 32 | 1.3779 |
0.6799 | 33.0 | 33 | 1.0512 |
1.2813 | 34.0 | 34 | 0.5455 |
0.6709 | 35.0 | 35 | 1.8824 |
0.4398 | 36.0 | 36 | 2.1419 |
0.1491 | 37.0 | 37 | 1.2215 |
0.7378 | 38.0 | 38 | 1.7122 |
0.657 | 39.0 | 39 | 1.4764 |
0.9551 | 40.0 | 40 | 0.5116 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2