|
--- |
|
base_model: DeepPavlov/rubert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
- medical |
|
- pharmacy |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: rubert-ner-drugname |
|
results: [] |
|
language: |
|
- ru |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# rubert-ner-drugname |
|
|
|
This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0365 |
|
- Precision: 0.7055 |
|
- Recall: 0.7658 |
|
- F1: 0.7344 |
|
- Accuracy: 0.9885 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- 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 | 61 | 0.0524 | 0.7588 | 0.5475 | 0.6360 | 0.9850 | |
|
| No log | 2.0 | 122 | 0.0485 | 0.56 | 0.7975 | 0.6580 | 0.9825 | |
|
| No log | 3.0 | 183 | 0.0361 | 0.7029 | 0.7563 | 0.7287 | 0.9884 | |
|
| No log | 4.0 | 244 | 0.0368 | 0.7591 | 0.7278 | 0.7431 | 0.9894 | |
|
| No log | 5.0 | 305 | 0.0365 | 0.7055 | 0.7658 | 0.7344 | 0.9885 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
