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: 0.1205
- Precision: 0.9307
- Recall: 0.9389
- F1: 0.9348
- Accuracy: 0.9816
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
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3889 | 1.0 | 477 | 0.0832 | 0.8808 | 0.8987 | 0.8897 | 0.9743 |
| 0.0736 | 2.0 | 954 | 0.0703 | 0.9170 | 0.9226 | 0.9198 | 0.9796 |
| 0.0361 | 3.0 | 1431 | 0.0784 | 0.9227 | 0.9321 | 0.9274 | 0.9801 |
| 0.0216 | 4.0 | 1908 | 0.0863 | 0.9235 | 0.9328 | 0.9281 | 0.9801 |
| 0.0116 | 5.0 | 2385 | 0.0977 | 0.9292 | 0.9371 | 0.9332 | 0.9809 |
| 0.007 | 6.0 | 2862 | 0.1071 | 0.9270 | 0.9356 | 0.9313 | 0.9808 |
| 0.0046 | 7.0 | 3339 | 0.1123 | 0.9322 | 0.9378 | 0.9350 | 0.9818 |
| 0.0029 | 8.0 | 3816 | 0.1179 | 0.9310 | 0.9371 | 0.9340 | 0.9814 |
| 0.0021 | 9.0 | 4293 | 0.1187 | 0.9293 | 0.9375 | 0.9334 | 0.9812 |
| 0.0013 | 10.0 | 4770 | 0.1205 | 0.9307 | 0.9389 | 0.9348 | 0.9816 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2