|
--- |
|
license: apache-2.0 |
|
base_model: ai-forever/ruBert-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- recall |
|
- precision |
|
- f1 |
|
model-index: |
|
- name: training_results |
|
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. --> |
|
|
|
# training_results |
|
|
|
This model is a fine-tuned version of [ai-forever/ruBert-base](https://huggingface.co/ai-forever/ruBert-base) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8438 |
|
- Accuracy: 0.7661 |
|
- Recall: 0.7479 |
|
- Precision: 0.7613 |
|
- F1: 0.7523 |
|
|
|
## 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: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| No log | 1.0 | 100 | 0.9047 | 0.7222 | 0.6078 | 0.6087 | 0.5979 | |
|
| No log | 2.0 | 200 | 0.7773 | 0.7427 | 0.6082 | 0.5795 | 0.5919 | |
|
| No log | 3.0 | 300 | 0.9403 | 0.7398 | 0.7074 | 0.7732 | 0.7198 | |
|
| No log | 4.0 | 400 | 1.1453 | 0.7135 | 0.6713 | 0.7322 | 0.6785 | |
|
| 0.505 | 5.0 | 500 | 1.3685 | 0.7310 | 0.7011 | 0.7616 | 0.7131 | |
|
| 0.505 | 6.0 | 600 | 1.3323 | 0.7310 | 0.7511 | 0.7179 | 0.7290 | |
|
| 0.505 | 7.0 | 700 | 1.3571 | 0.7544 | 0.7280 | 0.7483 | 0.7283 | |
|
| 0.505 | 8.0 | 800 | 1.4632 | 0.7368 | 0.7334 | 0.7298 | 0.7275 | |
|
| 0.505 | 9.0 | 900 | 1.5987 | 0.7515 | 0.7474 | 0.7494 | 0.7429 | |
|
| 0.0175 | 10.0 | 1000 | 1.5397 | 0.7778 | 0.7534 | 0.7902 | 0.7671 | |
|
| 0.0175 | 11.0 | 1100 | 1.6137 | 0.7749 | 0.7731 | 0.7927 | 0.7784 | |
|
| 0.0175 | 12.0 | 1200 | 1.6046 | 0.7778 | 0.7611 | 0.7916 | 0.7714 | |
|
| 0.0175 | 13.0 | 1300 | 1.5817 | 0.7778 | 0.7591 | 0.7894 | 0.7706 | |
|
| 0.0175 | 14.0 | 1400 | 1.6229 | 0.7865 | 0.7642 | 0.7965 | 0.7766 | |
|
| 0.0035 | 15.0 | 1500 | 1.5925 | 0.7836 | 0.7620 | 0.7910 | 0.7733 | |
|
| 0.0035 | 16.0 | 1600 | 1.6239 | 0.7836 | 0.7640 | 0.7922 | 0.7747 | |
|
| 0.0035 | 17.0 | 1700 | 1.6805 | 0.7778 | 0.7564 | 0.7769 | 0.7643 | |
|
| 0.0035 | 18.0 | 1800 | 1.7244 | 0.7719 | 0.7528 | 0.7622 | 0.7560 | |
|
| 0.0035 | 19.0 | 1900 | 1.7410 | 0.7719 | 0.7561 | 0.7619 | 0.7576 | |
|
| 0.0028 | 20.0 | 2000 | 1.7693 | 0.7690 | 0.7617 | 0.7579 | 0.7569 | |
|
| 0.0028 | 21.0 | 2100 | 1.7823 | 0.7690 | 0.7520 | 0.7623 | 0.7542 | |
|
| 0.0028 | 22.0 | 2200 | 1.7821 | 0.7719 | 0.7524 | 0.7652 | 0.7560 | |
|
| 0.0028 | 23.0 | 2300 | 1.7932 | 0.7690 | 0.7510 | 0.7634 | 0.7546 | |
|
| 0.0028 | 24.0 | 2400 | 1.8111 | 0.7690 | 0.7510 | 0.7703 | 0.7584 | |
|
| 0.0017 | 25.0 | 2500 | 1.8289 | 0.7690 | 0.7494 | 0.7707 | 0.7580 | |
|
| 0.0017 | 26.0 | 2600 | 1.8438 | 0.7661 | 0.7479 | 0.7613 | 0.7523 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|