<!-- 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. -->
bert_model
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3693
- Precision: 0.8462
- Recall: 0.9167
- F1: 0.8800
- Accuracy: 0.9545
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: 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 1 | 1.0725 | 0.85 | 0.7083 | 0.7727 | 0.7955 |
No log | 2.0 | 2 | 0.8541 | 0.7692 | 0.8333 | 0.8 | 0.9091 |
No log | 3.0 | 3 | 0.7265 | 0.7143 | 0.8333 | 0.7692 | 0.9091 |
No log | 4.0 | 4 | 0.6288 | 0.7143 | 0.8333 | 0.7692 | 0.9091 |
No log | 5.0 | 5 | 0.5448 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
No log | 6.0 | 6 | 0.4874 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
No log | 7.0 | 7 | 0.4398 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
No log | 8.0 | 8 | 0.4043 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
No log | 9.0 | 9 | 0.3810 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
No log | 10.0 | 10 | 0.3693 | 0.8462 | 0.9167 | 0.8800 | 0.9545 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1
- Datasets 2.13.0
- Tokenizers 0.13.3