metadata
library_name: transformers
license: mit
base_model: cointegrated/rubert-tiny2
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: results_synt_data
results: []
results_synt_data
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: 0.1310
- Precision: 0.7870
- Recall: 0.8681
- F1: 0.8256
- Accuracy: 0.9644
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.061 | 1.0 | 2700 | 0.2892 | 0.4979 | 0.6620 | 0.5684 | 0.9082 |
| 0.0426 | 2.0 | 5400 | 0.1871 | 0.6795 | 0.7840 | 0.7280 | 0.9438 |
| 0.0321 | 3.0 | 8100 | 0.1526 | 0.7172 | 0.8293 | 0.7692 | 0.9519 |
| 0.0257 | 4.0 | 10800 | 0.1382 | 0.7414 | 0.8407 | 0.7880 | 0.9566 |
| 0.0211 | 5.0 | 13500 | 0.1359 | 0.7545 | 0.8477 | 0.7984 | 0.9587 |
| 0.0182 | 6.0 | 16200 | 0.1300 | 0.7738 | 0.8581 | 0.8138 | 0.9620 |
| 0.015 | 7.0 | 18900 | 0.1344 | 0.7811 | 0.8616 | 0.8194 | 0.9625 |
| 0.0135 | 8.0 | 21600 | 0.1309 | 0.7810 | 0.8681 | 0.8223 | 0.9628 |
| 0.0135 | 9.0 | 24300 | 0.1326 | 0.7881 | 0.8681 | 0.8261 | 0.9643 |
| 0.0121 | 10.0 | 27000 | 0.1310 | 0.7870 | 0.8681 | 0.8256 | 0.9644 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0
- Datasets 3.5.0
- Tokenizers 0.21.1