metadata
language:
- mn
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mongolian-facebook-xlm-v-base-ner
results: []
mongolian-facebook-xlm-v-base-ner
This model is a fine-tuned version of facebook/xlm-v-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1036
- Precision: 0.9263
- Recall: 0.9352
- F1: 0.9307
- Accuracy: 0.9792
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 |
|---|---|---|---|---|---|---|---|
| 0.3409 | 1.0 | 477 | 0.1186 | 0.8832 | 0.9019 | 0.8924 | 0.9691 |
| 0.0953 | 2.0 | 954 | 0.0883 | 0.9130 | 0.9235 | 0.9182 | 0.9770 |
| 0.066 | 3.0 | 1431 | 0.0837 | 0.9166 | 0.9264 | 0.9215 | 0.9768 |
| 0.0487 | 4.0 | 1908 | 0.0918 | 0.9244 | 0.9286 | 0.9265 | 0.9778 |
| 0.0388 | 5.0 | 2385 | 0.0902 | 0.9218 | 0.9317 | 0.9268 | 0.9787 |
| 0.0304 | 6.0 | 2862 | 0.0955 | 0.9202 | 0.9296 | 0.9249 | 0.9780 |
| 0.0226 | 7.0 | 3339 | 0.0992 | 0.9226 | 0.9311 | 0.9269 | 0.9781 |
| 0.0192 | 8.0 | 3816 | 0.0962 | 0.9256 | 0.9328 | 0.9292 | 0.9790 |
| 0.0153 | 9.0 | 4293 | 0.1025 | 0.9243 | 0.9347 | 0.9295 | 0.9791 |
| 0.0133 | 10.0 | 4770 | 0.1036 | 0.9263 | 0.9352 | 0.9307 | 0.9792 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3