|
--- |
|
base_model: DeepPavlov/rubert-base-cased-conversational |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: my_model |
|
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. --> |
|
|
|
# my_model |
|
|
|
This model is a fine-tuned version of [DeepPavlov/rubert-base-cased-conversational](https://huggingface.co/DeepPavlov/rubert-base-cased-conversational) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1517 |
|
- Accuracy: 0.9568 |
|
|
|
## 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: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7699 | 1.0 | 881 | 0.2688 | 0.9057 | |
|
| 0.268 | 2.0 | 1762 | 0.1825 | 0.9412 | |
|
| 0.1903 | 3.0 | 2643 | 0.1592 | 0.9497 | |
|
| 0.1528 | 4.0 | 3524 | 0.1506 | 0.9526 | |
|
| 0.133 | 5.0 | 4405 | 0.1448 | 0.9551 | |
|
| 0.1104 | 6.0 | 5286 | 0.1410 | 0.9579 | |
|
| 0.0965 | 7.0 | 6167 | 0.1517 | 0.9568 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
