metadata
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-multilingual-cased-finetuned-conll2003-ner
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: 0.0635
- Precision: 0.9269
- Recall: 0.9337
- F1: 0.9303
- Accuracy: 0.9835
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 |
---|---|---|---|---|---|---|---|
0.2338 | 1.0 | 878 | 0.0753 | 0.9188 | 0.9089 | 0.9138 | 0.9795 |
0.0541 | 2.0 | 1756 | 0.0681 | 0.9362 | 0.9278 | 0.9320 | 0.9830 |
0.031 | 3.0 | 2634 | 0.0635 | 0.9269 | 0.9337 | 0.9303 | 0.9835 |
Framework versions
- Transformers 4.6.1
- Pytorch 1.8.1+cu101
- Datasets 1.6.2
- Tokenizers 0.10.2