<!-- 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. -->
distilbert-base-uncased-WNUT-ner
This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3510
- Precision: 0.5362
- Recall: 0.3911
- F1: 0.4523
- Accuracy: 0.9465
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: 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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 213 | 0.2745 | 0.5099 | 0.2614 | 0.3456 | 0.9392 |
No log | 2.0 | 426 | 0.2729 | 0.6080 | 0.3105 | 0.4110 | 0.9436 |
0.1878 | 3.0 | 639 | 0.2826 | 0.5769 | 0.3373 | 0.4257 | 0.9456 |
0.1878 | 4.0 | 852 | 0.2840 | 0.5440 | 0.3726 | 0.4422 | 0.9461 |
0.0465 | 5.0 | 1065 | 0.3286 | 0.5914 | 0.3568 | 0.4451 | 0.9461 |
0.0465 | 6.0 | 1278 | 0.3273 | 0.5693 | 0.3577 | 0.4394 | 0.9466 |
0.0465 | 7.0 | 1491 | 0.3462 | 0.5621 | 0.3818 | 0.4547 | 0.9469 |
0.0195 | 8.0 | 1704 | 0.3576 | 0.5442 | 0.3707 | 0.4410 | 0.9461 |
0.0195 | 9.0 | 1917 | 0.3563 | 0.5306 | 0.3698 | 0.4358 | 0.9460 |
0.0111 | 10.0 | 2130 | 0.3510 | 0.5362 | 0.3911 | 0.4523 | 0.9465 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu117
- Datasets 2.9.0
- Tokenizers 0.13.2