tg_comments_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: 0.0853
- Precision: 0.9687
- Recall: 0.9689
- F1: 0.9688
- Accuracy: 0.9703
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1502 | 0.2239 | 300 | 0.1232 | 0.9501 | 0.9510 | 0.9506 | 0.9530 |
0.118 | 0.4478 | 600 | 0.1065 | 0.9746 | 0.9422 | 0.9581 | 0.9609 |
0.1092 | 0.6716 | 900 | 0.0943 | 0.9709 | 0.9576 | 0.9642 | 0.9662 |
0.1081 | 0.8955 | 1200 | 0.0853 | 0.9687 | 0.9689 | 0.9688 | 0.9703 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 4