metadata
language:
- mn
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Mongolian-distilbert-base-multilingual-cased-ner
results: []
Mongolian-distilbert-base-multilingual-cased-ner
This model is a fine-tuned version of distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1344
- Precision: 0.8878
- Recall: 0.9055
- F1: 0.8966
- Accuracy: 0.9739
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 |
|---|---|---|---|---|---|---|---|
| 0.2155 | 1.0 | 477 | 0.1297 | 0.8050 | 0.8476 | 0.8257 | 0.9584 |
| 0.1037 | 2.0 | 954 | 0.0951 | 0.8505 | 0.8882 | 0.8690 | 0.9699 |
| 0.0687 | 3.0 | 1431 | 0.0978 | 0.8686 | 0.8924 | 0.8803 | 0.9711 |
| 0.05 | 4.0 | 1908 | 0.1087 | 0.8764 | 0.8955 | 0.8858 | 0.9719 |
| 0.0343 | 5.0 | 2385 | 0.1109 | 0.8781 | 0.8992 | 0.8885 | 0.9729 |
| 0.0264 | 6.0 | 2862 | 0.1169 | 0.8798 | 0.9011 | 0.8903 | 0.9729 |
| 0.0182 | 7.0 | 3339 | 0.1221 | 0.8871 | 0.9051 | 0.8960 | 0.9744 |
| 0.0146 | 8.0 | 3816 | 0.1286 | 0.8846 | 0.9036 | 0.8940 | 0.9735 |
| 0.0109 | 9.0 | 4293 | 0.1347 | 0.8880 | 0.9046 | 0.8962 | 0.9737 |
| 0.0095 | 10.0 | 4770 | 0.1344 | 0.8878 | 0.9055 | 0.8966 | 0.9739 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3