---
base_model: ai-forever/ruT5-base
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: rugec_RuReCl8
  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. -->

# rugec_RuReCl8

This model is a fine-tuned version of [ai-forever/ruT5-base](https://huggingface.co/ai-forever/ruT5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2950
- Bleu: 59.8321
- Gen Len: 16.2616

## 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: 3.83229e-05
- train_batch_size: 64
- eval_batch_size: 64
- 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 | Bleu    | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| 0.7072        | 1.0   | 853  | 0.3031          | 59.7005 | 16.2684 |
| 0.2571        | 2.0   | 1706 | 0.2950          | 59.8321 | 16.2616 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1