<!-- 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. -->
roberta-base-ner-demo-copy
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1618
- Precision: 0.9013
- Recall: 0.9119
- F1: 0.9065
- Accuracy: 0.9725
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: 32
- 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 |
---|---|---|---|---|---|---|---|
0.1721 | 1.0 | 477 | 0.1083 | 0.8538 | 0.8813 | 0.8673 | 0.9666 |
0.0843 | 2.0 | 954 | 0.0957 | 0.8820 | 0.8974 | 0.8896 | 0.9709 |
0.0579 | 3.0 | 1431 | 0.1049 | 0.8912 | 0.9049 | 0.8980 | 0.9721 |
0.0386 | 4.0 | 1908 | 0.1172 | 0.8986 | 0.9095 | 0.9040 | 0.9734 |
0.0278 | 5.0 | 2385 | 0.1200 | 0.8909 | 0.9072 | 0.8990 | 0.9714 |
0.0193 | 6.0 | 2862 | 0.1328 | 0.8946 | 0.9080 | 0.9012 | 0.9725 |
0.0141 | 7.0 | 3339 | 0.1426 | 0.8990 | 0.9079 | 0.9035 | 0.9727 |
0.0092 | 8.0 | 3816 | 0.1532 | 0.9007 | 0.9103 | 0.9055 | 0.9728 |
0.0071 | 9.0 | 4293 | 0.1619 | 0.8984 | 0.9101 | 0.9042 | 0.9721 |
0.0052 | 10.0 | 4770 | 0.1618 | 0.9013 | 0.9119 | 0.9065 | 0.9725 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3