metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mbert-finnic-ner
results: []
mbert-finnic-ner
This model is a fine-tuned version of bert-base-multilingual-cased on the Finnish and Estonian parts of the "WikiANN" dataset. It achieves the following results on the evaluation set:
- Loss: 0.1427
- Precision: 0.9090
- Recall: 0.9156
- F1: 0.9123
- Accuracy: 0.9672
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 |
|---|---|---|---|---|---|---|---|
| 0.1636 | 1.0 | 2188 | 0.1385 | 0.8906 | 0.9000 | 0.8953 | 0.9601 |
| 0.0991 | 2.0 | 4376 | 0.1346 | 0.9099 | 0.9095 | 0.9097 | 0.9660 |
| 0.0596 | 3.0 | 6564 | 0.1427 | 0.9090 | 0.9156 | 0.9123 | 0.9672 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6