|
--- |
|
base_model: ai-forever/ruBert-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: ruBert-large_ner |
|
results: [] |
|
--- |
|
|
|
<!-- 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-large_ner |
|
|
|
This model is a fine-tuned version of [ai-forever/ruBert-large](https://huggingface.co/ai-forever/ruBert-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5158 |
|
- Precision: 0.8832 |
|
- Recall: 0.9014 |
|
- F1: 0.8912 |
|
- Accuracy: 0.9234 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 438 | 0.3216 | 0.8700 | 0.8309 | 0.8448 | 0.8941 | |
|
| 0.3915 | 2.0 | 876 | 0.3379 | 0.8596 | 0.8790 | 0.8672 | 0.9089 | |
|
| 0.175 | 3.0 | 1314 | 0.3441 | 0.8656 | 0.8833 | 0.8737 | 0.9092 | |
|
| 0.0942 | 4.0 | 1752 | 0.3751 | 0.8651 | 0.8856 | 0.8729 | 0.9104 | |
|
| 0.0597 | 5.0 | 2190 | 0.3919 | 0.8881 | 0.9002 | 0.8935 | 0.9236 | |
|
| 0.0309 | 6.0 | 2628 | 0.4360 | 0.8730 | 0.8958 | 0.8821 | 0.9171 | |
|
| 0.0154 | 7.0 | 3066 | 0.4564 | 0.8848 | 0.8985 | 0.8907 | 0.9234 | |
|
| 0.0064 | 8.0 | 3504 | 0.4809 | 0.8797 | 0.9036 | 0.8904 | 0.9236 | |
|
| 0.0064 | 9.0 | 3942 | 0.5027 | 0.8832 | 0.9024 | 0.8917 | 0.9232 | |
|
| 0.0024 | 10.0 | 4380 | 0.5158 | 0.8832 | 0.9014 | 0.8912 | 0.9234 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
