<!-- 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. -->
ruBert-base_ner
This model is a fine-tuned version of ai-forever/ruBert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3164
- Precision: 0.6765
- Recall: 0.7667
- F1: 0.7188
- Accuracy: 0.9371
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: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 15 | 0.6490 | 0.3529 | 0.2 | 0.2553 | 0.7233 |
| No log | 2.0 | 30 | 0.3874 | 0.6286 | 0.7333 | 0.6769 | 0.9119 |
| No log | 3.0 | 45 | 0.3164 | 0.6765 | 0.7667 | 0.7188 | 0.9371 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
