<!-- 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-LR100-0-cased-20
This model is a fine-tuned version of bert-large-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5289
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: 2e-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: 20.0
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
7.0635 | 1.0 | 1 | 6.6184 |
7.131 | 2.0 | 2 | 7.0072 |
7.0969 | 3.0 | 3 | 5.8833 |
6.087 | 4.0 | 4 | 5.2094 |
5.8314 | 5.0 | 5 | 5.3317 |
5.1807 | 6.0 | 6 | 5.0294 |
5.0853 | 7.0 | 7 | 4.3234 |
4.5785 | 8.0 | 8 | 4.0070 |
4.0047 | 9.0 | 9 | 3.5287 |
3.5236 | 10.0 | 10 | 4.0761 |
4.2192 | 11.0 | 11 | 3.2353 |
3.6715 | 12.0 | 12 | 3.6203 |
3.4242 | 13.0 | 13 | 2.7801 |
3.1152 | 14.0 | 14 | 3.6127 |
2.9266 | 15.0 | 15 | 2.2571 |
3.4507 | 16.0 | 16 | 2.8120 |
3.0439 | 17.0 | 17 | 3.1393 |
2.6443 | 18.0 | 18 | 3.4350 |
2.8907 | 19.0 | 19 | 1.0329 |
2.8591 | 20.0 | 20 | 2.0586 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2