metadata
language:
- mn
base_model: bayartsogt/mongolian-roberta-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-base-ner-demo
results: []
roberta-base-ner-demo
This model is a fine-tuned version of bayartsogt/mongolian-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1304
- Precision: 0.9271
- Recall: 0.9357
- F1: 0.9314
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1666 | 1.0 | 477 | 0.0838 | 0.8642 | 0.9063 | 0.8847 | 0.9749 |
| 0.0532 | 2.0 | 954 | 0.0818 | 0.9114 | 0.9271 | 0.9192 | 0.9780 |
| 0.0272 | 3.0 | 1431 | 0.0847 | 0.9178 | 0.9318 | 0.9247 | 0.9798 |
| 0.0148 | 4.0 | 1908 | 0.0945 | 0.9151 | 0.9321 | 0.9235 | 0.9796 |
| 0.0082 | 5.0 | 2385 | 0.1051 | 0.9269 | 0.9364 | 0.9316 | 0.9807 |
| 0.0053 | 6.0 | 2862 | 0.1092 | 0.9240 | 0.9365 | 0.9302 | 0.9807 |
| 0.0031 | 7.0 | 3339 | 0.1259 | 0.9262 | 0.9364 | 0.9312 | 0.9801 |
| 0.002 | 8.0 | 3816 | 0.1262 | 0.9270 | 0.9359 | 0.9314 | 0.9803 |
| 0.0012 | 9.0 | 4293 | 0.1305 | 0.9275 | 0.9367 | 0.9320 | 0.9805 |
| 0.0013 | 10.0 | 4770 | 0.1304 | 0.9271 | 0.9357 | 0.9314 | 0.9803 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1