|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mt5-small-gigatrue-slovak |
|
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. --> |
|
|
|
# mt5-small-gigatrue-slovak |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1758 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 128 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch 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 | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 3.5063 | 0.1015 | 3000 | 2.3075 | |
|
| 2.998 | 0.2030 | 6000 | 2.2417 | |
|
| 2.9368 | 0.3044 | 9000 | 2.2237 | |
|
| 2.9102 | 0.4059 | 12000 | 2.2064 | |
|
| 2.8894 | 0.5074 | 15000 | 2.2052 | |
|
| 2.8837 | 0.6089 | 18000 | 2.1945 | |
|
| 2.8756 | 0.7104 | 21000 | 2.1984 | |
|
| 2.8718 | 0.8119 | 24000 | 2.1881 | |
|
| 2.868 | 0.9133 | 27000 | 2.1868 | |
|
| 2.8644 | 1.0148 | 30000 | 2.1816 | |
|
| 2.8644 | 1.1163 | 33000 | 2.1815 | |
|
| 2.8566 | 1.2178 | 36000 | 2.1785 | |
|
| 2.858 | 1.3193 | 39000 | 2.1745 | |
|
| 2.8558 | 1.4207 | 42000 | 2.1784 | |
|
| 2.8559 | 1.5222 | 45000 | 2.1775 | |
|
| 2.85 | 1.6237 | 48000 | 2.1783 | |
|
| 2.8521 | 1.7252 | 51000 | 2.1777 | |
|
| 2.8488 | 1.8267 | 54000 | 2.1782 | |
|
| 2.8501 | 1.9282 | 57000 | 2.1760 | |
|
| 2.8521 | 2.0296 | 60000 | 2.1773 | |
|
| 2.8526 | 2.1311 | 63000 | 2.1764 | |
|
| 2.8494 | 2.2326 | 66000 | 2.1774 | |
|
| 2.8501 | 2.3341 | 69000 | 2.1765 | |
|
| 2.8489 | 2.4356 | 72000 | 2.1771 | |
|
| 2.8501 | 2.5370 | 75000 | 2.1763 | |
|
| 2.8506 | 2.6385 | 78000 | 2.1762 | |
|
| 2.8472 | 2.7400 | 81000 | 2.1762 | |
|
| 2.8512 | 2.8415 | 84000 | 2.1758 | |
|
| 2.8494 | 2.9430 | 87000 | 2.1758 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.48.0.dev0 |
|
- Pytorch 2.5.1 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.21.0 |
|
|
