<!-- 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-LR100-labelled-30
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: 0.6520
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: 30.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.8321 | 1.0 | 2 | 4.3250 |
3.383 | 2.0 | 4 | 2.4023 |
1.9548 | 3.0 | 6 | 1.2925 |
1.4856 | 4.0 | 8 | 1.5152 |
0.9588 | 5.0 | 10 | 1.7731 |
1.2668 | 6.0 | 12 | 1.3830 |
0.8441 | 7.0 | 14 | 1.9760 |
1.0173 | 8.0 | 16 | 1.2364 |
0.6814 | 9.0 | 18 | 1.1771 |
0.9044 | 10.0 | 20 | 1.4721 |
0.6889 | 11.0 | 22 | 0.8518 |
0.5845 | 12.0 | 24 | 0.6993 |
0.4068 | 13.0 | 26 | 1.1771 |
0.5957 | 14.0 | 28 | 0.5895 |
0.4277 | 15.0 | 30 | 0.5326 |
0.3736 | 16.0 | 32 | 1.0893 |
0.413 | 17.0 | 34 | 1.3267 |
0.5718 | 18.0 | 36 | 1.0331 |
0.3892 | 19.0 | 38 | 1.0793 |
0.3913 | 20.0 | 40 | 0.8742 |
0.4794 | 21.0 | 42 | 1.1264 |
0.4626 | 22.0 | 44 | 1.1857 |
0.2683 | 23.0 | 46 | 1.5181 |
0.3436 | 24.0 | 48 | 1.4419 |
0.3793 | 25.0 | 50 | 1.4198 |
0.356 | 26.0 | 52 | 1.1776 |
0.2189 | 27.0 | 54 | 0.7166 |
0.286 | 28.0 | 56 | 0.7601 |
0.3681 | 29.0 | 58 | 1.2592 |
0.5858 | 30.0 | 60 | 0.6520 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2