roberta-base-russian-v0-finetuned-ner
This model is a fine-tuned version of blinoff/roberta-base-russian-v0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0284
- Precision: 0.9483
- Recall: 0.9658
- F1: 0.9570
- Accuracy: 0.9923
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: 16
- eval_batch_size: 16
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0523 | 1.0 | 1321 | 0.0423 | 0.9090 | 0.9398 | 0.9241 | 0.9865 |
| 0.0199 | 2.0 | 2642 | 0.0317 | 0.9321 | 0.9582 | 0.9450 | 0.9907 |
| 0.0076 | 3.0 | 3963 | 0.0284 | 0.9483 | 0.9658 | 0.9570 | 0.9923 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0