metadata
base_model: DeepPavlov/rubert-base-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: rubert-finetuned-ner
results: []
rubert-finetuned-ner
This model is a fine-tuned version of DeepPavlov/rubert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2633
- Precision: 0.7560
- Recall: 0.8032
- F1: 0.7789
- Accuracy: 0.9251
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4805 | 0.4 | 500 | 0.4017 | 0.6644 | 0.7072 | 0.6852 | 0.8788 |
| 0.3281 | 0.8 | 1000 | 0.2818 | 0.7416 | 0.7886 | 0.7644 | 0.9203 |
| 0.165 | 1.2 | 1500 | 0.2653 | 0.7573 | 0.8023 | 0.7792 | 0.9244 |
| 0.2539 | 1.6 | 2000 | 0.2633 | 0.7571 | 0.8040 | 0.7799 | 0.9252 |
| 0.252 | 2.0 | 2500 | 0.2633 | 0.7560 | 0.8032 | 0.7789 | 0.9251 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1