<!-- 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. -->
UmoreskiAI
This model is a fine-tuned version of DeepPavlov/rubert-base-cased-sentence on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0956
- Roc auc: 0.8014
- Maxf1: 0.4348
- Best Threshold: 0.1332
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: 8
- eval_batch_size: 8
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Roc auc | Maxf1 | Best Threshold |
|---|---|---|---|---|---|---|
| 0.1013 | 1.0 | 993 | 0.0932 | 0.7972 | 0.4358 | 0.1875 |
| 0.0876 | 2.0 | 1986 | 0.0956 | 0.8014 | 0.4348 | 0.1332 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.12.1
