CS505-NerCOQE-xlm
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- F1: 1.0
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| No log | 1.0 | 53 | 0.1859 | 0.4629 |
| No log | 2.0 | 106 | 0.0866 | 0.6823 |
| No log | 3.0 | 159 | 0.0541 | 0.7984 |
| No log | 4.0 | 212 | 0.0316 | 0.8789 |
| No log | 5.0 | 265 | 0.0353 | 0.8742 |
| No log | 6.0 | 318 | 0.0189 | 0.9384 |
| No log | 7.0 | 371 | 0.0090 | 0.9634 |
| No log | 8.0 | 424 | 0.0092 | 0.9765 |
| No log | 9.0 | 477 | 0.0036 | 0.9878 |
| No log | 10.0 | 530 | 0.0038 | 0.9900 |
| No log | 11.0 | 583 | 0.0035 | 0.9864 |
| No log | 12.0 | 636 | 0.0012 | 0.9935 |
| No log | 13.0 | 689 | 0.0034 | 0.9907 |
| No log | 14.0 | 742 | 0.0021 | 0.9964 |
| No log | 15.0 | 795 | 0.0010 | 0.9978 |
| No log | 16.0 | 848 | 0.0004 | 0.9993 |
| No log | 17.0 | 901 | 0.0004 | 0.9971 |
| No log | 18.0 | 954 | 0.0005 | 0.9957 |
| No log | 19.0 | 1007 | 0.0003 | 1.0 |
| No log | 20.0 | 1060 | 0.0002 | 1.0 |
| No log | 21.0 | 1113 | 0.0002 | 0.9978 |
| No log | 22.0 | 1166 | 0.0002 | 0.9978 |
| No log | 23.0 | 1219 | 0.0002 | 0.9978 |
| No log | 24.0 | 1272 | 0.0001 | 1.0 |
| No log | 25.0 | 1325 | 0.0001 | 1.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2