xlm-roberta-base-finetuned-ner-geocorpus
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1081
- Precision: 0.8117
- Recall: 0.8791
- F1: 0.8440
- Accuracy: 0.9765
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 276 | 0.2364 | 0.5253 | 0.4795 | 0.5014 | 0.9411 |
0.3373 | 2.0 | 552 | 0.1581 | 0.7023 | 0.7592 | 0.7297 | 0.9616 |
0.3373 | 3.0 | 828 | 0.1280 | 0.8232 | 0.7245 | 0.7707 | 0.9672 |
0.1133 | 4.0 | 1104 | 0.1229 | 0.7239 | 0.8601 | 0.7862 | 0.9667 |
0.1133 | 5.0 | 1380 | 0.1100 | 0.7764 | 0.8801 | 0.8250 | 0.9722 |
0.0635 | 6.0 | 1656 | 0.0978 | 0.8065 | 0.8896 | 0.846 | 0.9772 |
0.0635 | 7.0 | 1932 | 0.0942 | 0.8189 | 0.8749 | 0.8460 | 0.9774 |
0.0416 | 8.0 | 2208 | 0.1083 | 0.8097 | 0.8591 | 0.8337 | 0.9756 |
0.0416 | 9.0 | 2484 | 0.1062 | 0.8027 | 0.8896 | 0.8439 | 0.9767 |
0.0292 | 10.0 | 2760 | 0.1081 | 0.8117 | 0.8791 | 0.8440 | 0.9765 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 6