|
--- |
|
language: |
|
- mn |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: mongolian-gpt2-ner-finetuning |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# mongolian-gpt2-ner-finetuning |
|
|
|
This model is a fine-tuned version of [bayartsogt/mongolian-gpt2](https://huggingface.co/bayartsogt/mongolian-gpt2) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3230 |
|
- Precision: 0.0989 |
|
- Recall: 0.2277 |
|
- F1: 0.1380 |
|
- Accuracy: 0.9078 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.5225 | 1.0 | 477 | 0.3650 | 0.0743 | 0.1674 | 0.1030 | 0.8821 | |
|
| 0.322 | 2.0 | 954 | 0.3129 | 0.0853 | 0.1903 | 0.1178 | 0.8966 | |
|
| 0.2681 | 3.0 | 1431 | 0.3008 | 0.0915 | 0.2034 | 0.1262 | 0.9022 | |
|
| 0.232 | 4.0 | 1908 | 0.2963 | 0.0914 | 0.2070 | 0.1269 | 0.9053 | |
|
| 0.2029 | 5.0 | 2385 | 0.2974 | 0.0933 | 0.2120 | 0.1295 | 0.9071 | |
|
| 0.1791 | 6.0 | 2862 | 0.3038 | 0.0949 | 0.2140 | 0.1315 | 0.9076 | |
|
| 0.1603 | 7.0 | 3339 | 0.3100 | 0.0958 | 0.2186 | 0.1332 | 0.9079 | |
|
| 0.146 | 8.0 | 3816 | 0.3174 | 0.0950 | 0.2156 | 0.1319 | 0.9079 | |
|
| 0.1355 | 9.0 | 4293 | 0.3233 | 0.1001 | 0.2274 | 0.1390 | 0.9080 | |
|
| 0.1291 | 10.0 | 4770 | 0.3230 | 0.0989 | 0.2277 | 0.1380 | 0.9078 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.1 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
