---
base_model: ai-forever/ruT5-base
tags:
- generated_from_trainer
model-index:
- name: res
  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. -->

# t5-caser

This model is a fine-tuned version of [ai-forever/ruT5-base](https://huggingface.co/ai-forever/ruT5-base) on an ru_syntagrus dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0431

## Model description

The model aim is to paraphrase sentence made of lemmas into sentence with correct cases (in Russian)

## 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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.0997        | 1.0   | 2441 | 0.0468          |
| 0.0778        | 2.0   | 4882 | 0.0431          |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2