|
---
|
|
library_name: transformers
|
|
license: mit
|
|
base_model: cointegrated/rubert-tiny2
|
|
tags:
|
|
- generated_from_trainer
|
|
metrics:
|
|
- f1
|
|
model-index:
|
|
- name: spb_city_prob_class
|
|
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. -->
|
|
|
|
# spb_city_prob_class
|
|
|
|
This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on an unknown dataset.
|
|
It achieves the following results on the evaluation set:
|
|
- Loss: 0.8037
|
|
- F1: 0.7589
|
|
|
|
## 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: 8
|
|
- eval_batch_size: 4
|
|
- seed: 42
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: linear
|
|
- num_epochs: 3
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
|
| 0.8437 | 1.0 | 2200 | 0.8193 | 0.7403 |
|
|
| 0.6405 | 2.0 | 4400 | 0.7884 | 0.7535 |
|
|
| 0.5648 | 3.0 | 6600 | 0.8037 | 0.7589 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.48.1
|
|
- Pytorch 2.5.1+cu124
|
|
- Datasets 3.2.0
|
|
- Tokenizers 0.21.0
|
|
|
