<!-- 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. -->
ner-distillbert-ner-tags
This model is a fine-tuned version of harvinder676/ner-distillbert-ner-tags on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1387
- Precision: 0.8521
- Recall: 0.8574
- F1: 0.8547
- Accuracy: 0.9710
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: 0.0001
- 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 | 13 | 0.1262 | 0.8023 | 0.8589 | 0.8296 | 0.9666 |
| No log | 2.0 | 26 | 0.1178 | 0.8262 | 0.8313 | 0.8287 | 0.9673 |
| No log | 3.0 | 39 | 0.1244 | 0.8165 | 0.8328 | 0.8246 | 0.9671 |
| No log | 4.0 | 52 | 0.1280 | 0.8275 | 0.8313 | 0.8294 | 0.9683 |
| No log | 5.0 | 65 | 0.1338 | 0.8410 | 0.8436 | 0.8423 | 0.9685 |
| No log | 6.0 | 78 | 0.1378 | 0.8346 | 0.8589 | 0.8466 | 0.9688 |
| No log | 7.0 | 91 | 0.1359 | 0.8452 | 0.8543 | 0.8497 | 0.9706 |
| No log | 8.0 | 104 | 0.1336 | 0.8416 | 0.8635 | 0.8524 | 0.9707 |
| No log | 9.0 | 117 | 0.1376 | 0.8472 | 0.8589 | 0.8530 | 0.9709 |
| No log | 10.0 | 130 | 0.1387 | 0.8521 | 0.8574 | 0.8547 | 0.9710 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
