metadata
language:
- mn
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-ner-demo
results: []
xlm-roberta-base-ner-demo
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0988
- Precision: 0.9333
- Recall: 0.9387
- F1: 0.9360
- Accuracy: 0.9803
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 |
|---|---|---|---|---|---|---|---|
| 0.178 | 1.0 | 572 | 0.0840 | 0.8985 | 0.9121 | 0.9052 | 0.9751 |
| 0.0801 | 2.0 | 1144 | 0.0744 | 0.9095 | 0.9262 | 0.9178 | 0.9780 |
| 0.0566 | 3.0 | 1716 | 0.0797 | 0.9230 | 0.9312 | 0.9271 | 0.9787 |
| 0.0436 | 4.0 | 2288 | 0.0734 | 0.9157 | 0.9302 | 0.9229 | 0.9795 |
| 0.0333 | 5.0 | 2860 | 0.0871 | 0.9152 | 0.9270 | 0.9210 | 0.9772 |
| 0.0254 | 6.0 | 3432 | 0.0848 | 0.9216 | 0.9307 | 0.9261 | 0.9792 |
| 0.0186 | 7.0 | 4004 | 0.0992 | 0.9302 | 0.9367 | 0.9334 | 0.9806 |
| 0.0142 | 8.0 | 4576 | 0.0989 | 0.9288 | 0.9357 | 0.9322 | 0.9801 |
| 0.0119 | 9.0 | 5148 | 0.0965 | 0.9331 | 0.9387 | 0.9359 | 0.9807 |
| 0.0103 | 10.0 | 5720 | 0.0988 | 0.9333 | 0.9387 | 0.9360 | 0.9803 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3