rubert-RuOpinionNe
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: 0.5722
- Accuracy: 0.7990
- Precision: 0.7832
- Recall: 0.7824
- F1 Macro: 0.7828
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: 32
- eval_batch_size: 32
- 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Macro |
---|---|---|---|---|---|---|---|
0.9542 | 1.0 | 56 | 0.8013 | 0.6484 | 0.7327 | 0.5959 | 0.5520 |
0.6766 | 2.0 | 112 | 0.6441 | 0.7188 | 0.7135 | 0.7053 | 0.7037 |
0.474 | 3.0 | 168 | 0.6089 | 0.7292 | 0.7271 | 0.7251 | 0.7217 |
0.3561 | 4.0 | 224 | 0.6353 | 0.7318 | 0.7247 | 0.7288 | 0.7257 |
0.282 | 5.0 | 280 | 0.6261 | 0.7604 | 0.7548 | 0.7512 | 0.7524 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for sverhmassivnaya/rubert-RuOpinionNe
Base model
DeepPavlov/rubert-base-cased