---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: tokipona_model_v0.3
  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. -->

# tokipona_model_v0.3

This model is a fine-tuned version of [plgrm720/tokipona_model_v0.2](https://huggingface.co/plgrm720/tokipona_model_v0.2) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4449
- Bleu: 0.5716
- Gen Len: 19.0

## 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: 0.02
- 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: 6
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log        | 1.0   | 55   | 1.7209          | 0.1079 | 19.0    |
| No log        | 2.0   | 110  | 1.5868          | 0.1863 | 19.0    |
| No log        | 3.0   | 165  | 1.6083          | 1.5625 | 17.7685 |
| No log        | 4.0   | 220  | 1.5498          | 0.1996 | 19.0    |
| No log        | 5.0   | 275  | 1.4770          | 0.4557 | 18.9557 |
| No log        | 6.0   | 330  | 1.4449          | 0.5716 | 19.0    |


### Framework versions

- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3