|
--- |
|
license: mit |
|
base_model: coppercitylabs/uzbert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: uzpostagger-cyrillic-3 |
|
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. --> |
|
|
|
# uzpostagger-cyrillic-3 |
|
|
|
This model is a fine-tuned version of [coppercitylabs/uzbert-base-uncased](https://huggingface.co/coppercitylabs/uzbert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2715 |
|
- Precision: 0.8763 |
|
- Recall: 0.8699 |
|
- F1: 0.8731 |
|
- Accuracy: 0.9219 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 25 | 0.8765 | 0.6558 | 0.5477 | 0.5969 | 0.7485 | |
|
| No log | 2.0 | 50 | 0.4086 | 0.8496 | 0.8237 | 0.8364 | 0.9004 | |
|
| No log | 3.0 | 75 | 0.3133 | 0.8615 | 0.8552 | 0.8583 | 0.9142 | |
|
| No log | 4.0 | 100 | 0.2806 | 0.8730 | 0.8657 | 0.8693 | 0.9193 | |
|
| No log | 5.0 | 125 | 0.2715 | 0.8763 | 0.8699 | 0.8731 | 0.9219 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.2.0 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.13.3 |
|
|
