---
library_name: transformers
license: cc-by-nc-sa-4.0
base_model: ufal/robeczech-base
tags:
- generated_from_trainer
datasets:
- generator
metrics:
- accuracy
model-index:
- name: Robeczech-CERED2
  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. -->

# Robeczech-CERED2

This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1300
- Accuracy: 0.8985
- Micro Precision: 0.8985
- Micro Recall: 0.8985
- Micro F1: 0.8985
- Macro Precision: 0.8711
- Macro Recall: 0.8608
- Macro F1: 0.8632

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1500
- num_epochs: 10
- label_smoothing_factor: 0.1

### Training results

| Training Loss | Epoch  | Step   | Validation Loss | Accuracy | Micro Precision | Micro Recall | Micro F1 | Macro Precision | Macro Recall | Macro F1 |
|:-------------:|:------:|:------:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|
| 1.1585        | 1.0000 | 11305  | 1.1208          | 0.8608   | 0.8608          | 0.8608       | 0.8608   | 0.8155          | 0.7878       | 0.7914   |
| 1.0617        | 2.0    | 22611  | 1.0567          | 0.8873   | 0.8873          | 0.8873       | 0.8873   | 0.8547          | 0.8428       | 0.8430   |
| 0.9804        | 3.0000 | 33916  | 1.0558          | 0.8900   | 0.8900          | 0.8900       | 0.8900   | 0.8546          | 0.8414       | 0.8438   |
| 0.9327        | 4.0    | 45222  | 1.0585          | 0.8920   | 0.8920          | 0.8920       | 0.8920   | 0.8557          | 0.8475       | 0.8483   |
| 0.8927        | 5.0000 | 56527  | 1.0820          | 0.8917   | 0.8917          | 0.8917       | 0.8917   | 0.8484          | 0.8499       | 0.8455   |
| 0.861         | 6.0    | 67833  | 1.0774          | 0.8982   | 0.8982          | 0.8982       | 0.8982   | 0.8596          | 0.8567       | 0.8545   |
| 0.8344        | 7.0000 | 79138  | 1.0987          | 0.8979   | 0.8979          | 0.8979       | 0.8979   | 0.8641          | 0.8558       | 0.8567   |
| 0.8222        | 8.0    | 90444  | 1.1113          | 0.8991   | 0.8991          | 0.8991       | 0.8991   | 0.8639          | 0.8544       | 0.8558   |
| 0.8096        | 9.0000 | 101749 | 1.1159          | 0.9001   | 0.9001          | 0.9001       | 0.9001   | 0.8584          | 0.8589       | 0.8552   |
| 0.8071        | 9.9996 | 113050 | 1.1176          | 0.8994   | 0.8994          | 0.8994       | 0.8994   | 0.8561          | 0.8577       | 0.8539   |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3