|
--- |
|
license: apache-2.0 |
|
base_model: ai-forever/ruBert-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: ruBert-base-finetuned-pos |
|
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. --> |
|
|
|
# ruBert-base-finetuned-pos |
|
|
|
This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co./ai-forever/ruBert-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1544 |
|
- Precision: 0.8561 |
|
- Recall: 0.8723 |
|
- F1: 0.8642 |
|
- Accuracy: 0.8822 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- 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 | 311 | 0.1686 | 0.8380 | 0.8440 | 0.8410 | 0.8565 | |
|
| 0.0464 | 2.0 | 622 | 0.1597 | 0.8462 | 0.8582 | 0.8521 | 0.8715 | |
|
| 0.0464 | 3.0 | 933 | 0.1544 | 0.8561 | 0.8723 | 0.8642 | 0.8822 | |
|
| 0.0046 | 4.0 | 1244 | 0.1564 | 0.8469 | 0.8629 | 0.8548 | 0.8737 | |
|
| 0.0029 | 5.0 | 1555 | 0.1556 | 0.8538 | 0.8700 | 0.8618 | 0.8801 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
