<!-- 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. -->
sbert_large_nlu_ru_ner
This model is a fine-tuned version of DimasikKurd/sbert_large_nlu_ru_ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6319
- Precision: 0.4157
- Recall: 0.4992
- F1: 0.4536
- Accuracy: 0.9003
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 40 | 0.6395 | 0.3447 | 0.5235 | 0.4157 | 0.8793 |
No log | 2.0 | 80 | 0.5574 | 0.4352 | 0.4733 | 0.4534 | 0.9056 |
No log | 3.0 | 120 | 0.5839 | 0.3942 | 0.5041 | 0.4424 | 0.8929 |
No log | 4.0 | 160 | 0.6134 | 0.4267 | 0.4862 | 0.4545 | 0.9029 |
No log | 5.0 | 200 | 0.6319 | 0.4157 | 0.4992 | 0.4536 | 0.9003 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3