<!-- 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-20-sigir-tune2nd-LR10-labelled-30
This model is a fine-tuned version of jojoUla/bert-large-cased-sigir-support-no-label-20 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3995
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 |
---|---|---|---|
2.1303 | 1.0 | 1 | 3.2415 |
2.3107 | 2.0 | 2 | 2.1225 |
1.2824 | 3.0 | 3 | 2.2623 |
1.0548 | 4.0 | 4 | 0.5449 |
1.1366 | 5.0 | 5 | 1.1446 |
0.5947 | 6.0 | 6 | 0.3811 |
0.4889 | 7.0 | 7 | 1.6445 |
1.2689 | 8.0 | 8 | 1.7214 |
0.8074 | 9.0 | 9 | 2.3152 |
0.7084 | 10.0 | 10 | 0.9325 |
1.0307 | 11.0 | 11 | 2.4217 |
0.7119 | 12.0 | 12 | 2.6455 |
1.0052 | 13.0 | 13 | 1.1594 |
0.7125 | 14.0 | 14 | 1.2795 |
0.4732 | 15.0 | 15 | 0.1245 |
0.8829 | 16.0 | 16 | 1.8585 |
0.7079 | 17.0 | 17 | 1.6644 |
0.6243 | 18.0 | 18 | 1.6117 |
1.2438 | 19.0 | 19 | 2.3044 |
1.0812 | 20.0 | 20 | 4.5037 |
0.7003 | 21.0 | 21 | 1.5862 |
0.867 | 22.0 | 22 | 2.1851 |
0.9098 | 23.0 | 23 | 1.6055 |
0.6214 | 24.0 | 24 | 2.6699 |
0.282 | 25.0 | 25 | 1.3515 |
0.1888 | 26.0 | 26 | 2.3864 |
0.6863 | 27.0 | 27 | 1.2444 |
0.8527 | 28.0 | 28 | 1.9603 |
0.9416 | 29.0 | 29 | 3.7045 |
0.8302 | 30.0 | 30 | 0.9336 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2