metadata
library_name: transformers
license: mit
base_model: cointegrated/rubert-tiny2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ruBertTiny_multiclassv1
results: []
ruBertTiny_multiclassv1
This model is a fine-tuned version of cointegrated/rubert-tiny2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2674
- Accuracy: 0.8889
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8043 | 0.2739 | 10000 | 0.5419 | 0.7051 |
| 0.5404 | 0.5478 | 20000 | 0.4947 | 0.7692 |
| 0.5161 | 0.8217 | 30000 | 0.4281 | 0.8291 |
| 0.4866 | 1.0956 | 40000 | 0.3883 | 0.8162 |
| 0.4536 | 1.3695 | 50000 | 0.3552 | 0.8462 |
| 0.4339 | 1.6434 | 60000 | 0.3569 | 0.8248 |
| 0.4225 | 1.9173 | 70000 | 0.3502 | 0.8462 |
| 0.4029 | 2.1912 | 80000 | 0.3187 | 0.8547 |
| 0.3924 | 2.4651 | 90000 | 0.3197 | 0.8718 |
| 0.385 | 2.7391 | 100000 | 0.3036 | 0.8761 |
| 0.3794 | 3.0130 | 110000 | 0.2773 | 0.8803 |
| 0.3627 | 3.2869 | 120000 | 0.2852 | 0.8803 |
| 0.3607 | 3.5608 | 130000 | 0.2744 | 0.8803 |
| 0.3583 | 3.8347 | 140000 | 0.2707 | 0.8803 |
| 0.3526 | 4.1086 | 150000 | 0.2647 | 0.8889 |
| 0.3477 | 4.3825 | 160000 | 0.2654 | 0.8846 |
| 0.3472 | 4.6564 | 170000 | 0.2676 | 0.8889 |
| 0.3478 | 4.9303 | 180000 | 0.2674 | 0.8889 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.0.1+cu118
- Datasets 2.21.0
- Tokenizers 0.19.1