---
tags:
- generated_from_trainer
- not-for-all-audiences
model-index:
- name: TinySatirik-sm
  results: []
license: mit
datasets:
- igorktech/anekdots
language:
- ru
pipeline_tag: text-generation
---

<!-- 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. -->

# TinySatirik-sm

This model is a pre-trained version of really tiny LLama2 model on an [anekdots](https://huggingface.co/datasets/igorktech/anekdots) dataset.

Inspired by [TinyStories](https://arxiv.org/abs/2305.07759).

It achieves the following results on the evaluation set:
- Loss: 1.2643

## Tokenizer

To utilize the model, install the [special tokenizer](https://github.com/Koziev/character-tokenizer):

```bash
pip install git+https://github.com/Koziev/character-tokenizer
```

In addition to recognizing Cyrillic characters and punctuation, this tokenizer is aware of special tokens such as ```<s>```, ```</s>```, ```<pad>```, and ```<unk>```.

As this is a non-standard tokenizer for transformers, load it not via ```transformers.AutoTokenizer.from_pretrained```, but somewhat like this:

```python
import charactertokenizer

...
tokenizer = charactertokenizer.CharacterTokenizer.from_pretrained('igorktech/CharPicoSatirik-sm')
```

To observe tokenization, use this code snippet:

```python
prompt = '<s>Hello World\n'
encoded_prompt = tokenizer.encode(prompt, return_tensors='pt')
print('Tokenized prompt:', ' | '.join(tokenizer.decode([t]) for t in encoded_prompt[0]))
```

You will see a list of tokens separated by the ```|``` symbol:

```
Tokenized prompt: <s> | H | e | l | l | o |   | W | o | r | l | d | 
```

Tokenizer created by [Koziev](https://github.com/Koziev).

## Model description

Llama2 architecture based.
## 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: 0.0005
- train_batch_size: 32
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 250
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.3401        | 1.81  | 2000 | 1.3465          |
| 1.2323        | 3.62  | 4000 | 1.2643          |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0