---
library_name: transformers
license: apache-2.0
base_model: Goshective/kazparc_ru_en_model_1
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: kazparc_en_ru_model_1
  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. -->

# kazparc_en_ru_model_1

This model is a fine-tuned version of [Goshective/kazparc_ru_en_model_1](https://huggingface.co/Goshective/kazparc_ru_en_model_1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8554
- Bleu: 0.5951
- Gen Len: 18.1181

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Bleu   | Gen Len |
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|
| 2.2576        | 1.0   | 8482  | 2.0346          | 0.2351 | 18.1501 |
| 2.1164        | 2.0   | 16964 | 1.8959          | 0.5118 | 18.1236 |
| 2.0784        | 3.0   | 25446 | 1.8554          | 0.5951 | 18.1181 |


### Framework versions

- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3