metadata
license: apache-2.0
base_model: ai-forever/ruBert-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: opd_bert_spam_ru
results: []
opd_bert_spam_ru
This model is a fine-tuned version of ai-forever/ruBert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1034
- F1: 0.9872
- Accuracy: 0.9872
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 70
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
|---|---|---|---|---|---|
| 0.1094 | 0.5102 | 100 | 0.2559 | 0.9587 | 0.9591 |
| 0.1566 | 1.0204 | 200 | 0.0769 | 0.9847 | 0.9847 |
| 0.0352 | 1.5306 | 300 | 0.0860 | 0.9821 | 0.9821 |
| 0.0571 | 2.0408 | 400 | 0.0908 | 0.9846 | 0.9847 |
| 0.0256 | 2.5510 | 500 | 0.1034 | 0.9872 | 0.9872 |
| 0.0178 | 3.0612 | 600 | 0.1416 | 0.9770 | 0.9770 |
| 0.0098 | 3.5714 | 700 | 0.1461 | 0.9821 | 0.9821 |
| 0.0097 | 4.0816 | 800 | 0.1618 | 0.9770 | 0.9770 |
| 0.0003 | 4.5918 | 900 | 0.1651 | 0.9795 | 0.9795 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1