<!-- 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. -->
Classfication_longformer
This model is a fine-tuned version of allenai/longformer-base-4096 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1012
- Accuracy: 0.65
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 37 | 0.9535 | 0.7895 |
| No log | 2.0 | 74 | 1.0426 | 0.4737 |
| No log | 3.0 | 111 | 0.4770 | 0.8947 |
| No log | 4.0 | 148 | 0.9353 | 0.6316 |
| No log | 5.0 | 185 | 0.8856 | 0.6842 |
| No log | 6.0 | 222 | 0.6509 | 0.8421 |
| No log | 7.0 | 259 | 1.7107 | 0.6842 |
| No log | 8.0 | 296 | 1.2910 | 0.7368 |
| No log | 9.0 | 333 | 2.6230 | 0.6316 |
| No log | 10.0 | 370 | 1.6727 | 0.6842 |
| No log | 11.0 | 407 | 2.1794 | 0.6842 |
| No log | 12.0 | 444 | 2.2832 | 0.6842 |
| No log | 13.0 | 481 | 1.5007 | 0.7368 |
| 0.3791 | 14.0 | 518 | 2.3911 | 0.6842 |
| 0.3791 | 15.0 | 555 | 2.2838 | 0.6842 |
| 0.3791 | 16.0 | 592 | 2.1564 | 0.6842 |
| 0.3791 | 17.0 | 629 | 2.2632 | 0.6842 |
| 0.3791 | 18.0 | 666 | 2.3907 | 0.6842 |
| 0.3791 | 19.0 | 703 | 2.3995 | 0.6842 |
| 0.3791 | 20.0 | 740 | 2.3958 | 0.6842 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
