metadata
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
This model was trained from scratch on an unkown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0484
- Precision: 0.9340
- Recall: 0.9413
- F1: 0.9376
- Accuracy: 0.9875
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1931 | 1.0 | 878 | 0.0518 | 0.9146 | 0.9276 | 0.9210 | 0.9852 |
| 0.0389 | 2.0 | 1756 | 0.0470 | 0.9261 | 0.9389 | 0.9325 | 0.9870 |
| 0.0228 | 3.0 | 2634 | 0.0484 | 0.9340 | 0.9413 | 0.9376 | 0.9875 |
Framework versions
- Transformers 4.6.1
- Pytorch 1.8.1+cu101
- Datasets 1.6.2
- Tokenizers 0.10.2