metadata
language:
- mn
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bloom-mongolian-ner-demo
results: []
bloom-mongolian-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: 0.1048
- Precision: 0.9267
- Recall: 0.9354
- F1: 0.9310
- Accuracy: 0.9796
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 |
|---|---|---|---|---|---|---|---|
| 0.195 | 1.0 | 477 | 0.0947 | 0.8845 | 0.8994 | 0.8919 | 0.9707 |
| 0.0848 | 2.0 | 954 | 0.0761 | 0.9095 | 0.9235 | 0.9164 | 0.9774 |
| 0.0614 | 3.0 | 1431 | 0.0724 | 0.9218 | 0.9317 | 0.9267 | 0.9797 |
| 0.0452 | 4.0 | 1908 | 0.0756 | 0.9283 | 0.9350 | 0.9316 | 0.9806 |
| 0.035 | 5.0 | 2385 | 0.0824 | 0.9221 | 0.9337 | 0.9279 | 0.9796 |
| 0.0263 | 6.0 | 2862 | 0.0895 | 0.9191 | 0.9319 | 0.9254 | 0.9787 |
| 0.02 | 7.0 | 3339 | 0.0991 | 0.9238 | 0.9335 | 0.9286 | 0.9789 |
| 0.0148 | 8.0 | 3816 | 0.1005 | 0.9277 | 0.9358 | 0.9317 | 0.9798 |
| 0.0124 | 9.0 | 4293 | 0.1014 | 0.9254 | 0.9356 | 0.9305 | 0.9801 |
| 0.01 | 10.0 | 4770 | 0.1048 | 0.9267 | 0.9354 | 0.9310 | 0.9796 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3