<!-- 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. -->
war-tiny-bert
This model is a fine-tuned version of cointegrated/rubert-tiny2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3438
- F1: 0.6929
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 21
- 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 | F1 |
|---|---|---|---|---|
| 0.3216 | 1.0 | 2500 | 0.2645 | 0.5988 |
| 0.2388 | 2.0 | 5000 | 0.2379 | 0.6496 |
| 0.2067 | 3.0 | 7500 | 0.2375 | 0.6696 |
| 0.1822 | 4.0 | 10000 | 0.2553 | 0.6740 |
| 0.1661 | 5.0 | 12500 | 0.2770 | 0.6725 |
| 0.1509 | 6.0 | 15000 | 0.2853 | 0.6965 |
| 0.1423 | 7.0 | 17500 | 0.3187 | 0.6765 |
| 0.1322 | 8.0 | 20000 | 0.3277 | 0.6958 |
| 0.1256 | 9.0 | 22500 | 0.3411 | 0.6909 |
| 0.1224 | 10.0 | 25000 | 0.3438 | 0.6929 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
