BERT-multilingual-finetuned-CEFR_ner-3000news
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5691
- Accuracy: 0.4044
- Precision: 0.4949
- Recall: 0.6593
- F1: 0.4688
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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
No log | 1.0 | 132 | 0.5657 | 0.3739 | 0.5044 | 0.5333 | 0.4050 |
No log | 2.0 | 264 | 0.5076 | 0.3859 | 0.5011 | 0.5712 | 0.4225 |
No log | 3.0 | 396 | 0.4845 | 0.3925 | 0.4690 | 0.6167 | 0.4351 |
0.4009 | 4.0 | 528 | 0.4981 | 0.3985 | 0.4956 | 0.6180 | 0.4514 |
0.4009 | 5.0 | 660 | 0.5136 | 0.3976 | 0.4913 | 0.6348 | 0.4570 |
0.4009 | 6.0 | 792 | 0.5092 | 0.4019 | 0.5004 | 0.6434 | 0.4655 |
0.4009 | 7.0 | 924 | 0.5235 | 0.4012 | 0.4837 | 0.6434 | 0.4555 |
0.1848 | 8.0 | 1056 | 0.5327 | 0.4033 | 0.4948 | 0.6519 | 0.4662 |
0.1848 | 9.0 | 1188 | 0.5640 | 0.4033 | 0.4920 | 0.6536 | 0.4638 |
0.1848 | 10.0 | 1320 | 0.5717 | 0.4031 | 0.4962 | 0.6547 | 0.4677 |
0.1848 | 11.0 | 1452 | 0.5667 | 0.4043 | 0.4910 | 0.6609 | 0.4666 |
0.1096 | 12.0 | 1584 | 0.5691 | 0.4044 | 0.4949 | 0.6593 | 0.4688 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1