metadata
language:
- mn
tags:
- generated_from_trainer
base_model: bayartsogt/mongolian-roberta-base
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-base-ner-test
results: []
roberta-base-ner-test
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: 0.1051
- Precision: 0.9154
- Recall: 0.9295
- F1: 0.9224
- Accuracy: 0.9778
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: 128
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|---|---|---|
| 0.4118 | 1.0 | 60 | 0.1230 | 0.7683 | 0.8344 | 0.8000 | 0.9584 |
| 0.1013 | 2.0 | 120 | 0.0996 | 0.8134 | 0.8677 | 0.8397 | 0.9649 |
| 0.0694 | 3.0 | 180 | 0.0961 | 0.8295 | 0.8783 | 0.8532 | 0.9676 |
| 0.0523 | 4.0 | 240 | 0.0861 | 0.9030 | 0.9198 | 0.9113 | 0.9762 |
| 0.0309 | 5.0 | 300 | 0.0847 | 0.9088 | 0.9239 | 0.9163 | 0.9775 |
| 0.0236 | 6.0 | 360 | 0.0950 | 0.9103 | 0.9253 | 0.9177 | 0.9772 |
| 0.019 | 7.0 | 420 | 0.0974 | 0.9158 | 0.9277 | 0.9217 | 0.9775 |
| 0.0153 | 8.0 | 480 | 0.0996 | 0.9139 | 0.9278 | 0.9208 | 0.9781 |
| 0.0122 | 9.0 | 540 | 0.1029 | 0.9143 | 0.9284 | 0.9213 | 0.9781 |
| 0.0104 | 10.0 | 600 | 0.1051 | 0.9154 | 0.9295 | 0.9224 | 0.9778 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2