metadata
language:
- mn
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: canine-s-mongolian-ner
results: []
canine-s-mongolian-ner
This model is a fine-tuned version of facebook/xlm-v-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3588
- Precision: 0.5262
- Recall: 0.5383
- F1: 0.5322
- Accuracy: 0.9073
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 |
|---|---|---|---|---|---|---|---|
| 0.6287 | 1.0 | 477 | 0.5233 | 0.2908 | 0.1814 | 0.2234 | 0.8471 |
| 0.4898 | 2.0 | 954 | 0.4404 | 0.3727 | 0.2993 | 0.3320 | 0.8677 |
| 0.403 | 3.0 | 1431 | 0.3939 | 0.4498 | 0.3922 | 0.4191 | 0.8832 |
| 0.3416 | 4.0 | 1908 | 0.3720 | 0.4734 | 0.4606 | 0.4669 | 0.8934 |
| 0.2986 | 5.0 | 2385 | 0.3640 | 0.5093 | 0.4745 | 0.4913 | 0.8987 |
| 0.2693 | 6.0 | 2862 | 0.3599 | 0.5126 | 0.5039 | 0.5082 | 0.9012 |
| 0.243 | 7.0 | 3339 | 0.3534 | 0.5009 | 0.5241 | 0.5123 | 0.9026 |
| 0.2262 | 8.0 | 3816 | 0.3582 | 0.5103 | 0.5315 | 0.5207 | 0.9048 |
| 0.213 | 9.0 | 4293 | 0.3534 | 0.5195 | 0.5327 | 0.5260 | 0.9059 |
| 0.2064 | 10.0 | 4770 | 0.3588 | 0.5262 | 0.5383 | 0.5322 | 0.9073 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3