---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-small-finetuned-English-to-BASH
  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-small-finetuned-English-to-BASH

This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on a more balanced iteration of the [NL2BASH](https://github.com/TellinaTool/nl2bash/tree/master/data) dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4817
- Bleu: 19.6535
- Gen Len: 14.4432

## 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: 0.0001
- 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: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
| No log        | 1.0   | 387  | 2.2188          | 13.8458 | 15.1085 |
| 2.8603        | 2.0   | 774  | 1.9373          | 15.1492 | 14.1602 |
| 2.1898        | 3.0   | 1161 | 1.7808          | 16.4009 | 13.907  |
| 1.9486        | 4.0   | 1548 | 1.6841          | 18.1435 | 14.8282 |
| 1.9486        | 5.0   | 1935 | 1.6103          | 17.5652 | 14.1279 |
| 1.8078        | 6.0   | 2322 | 1.5607          | 19.0694 | 14.6602 |
| 1.7078        | 7.0   | 2709 | 1.5267          | 18.4997 | 14.407  |
| 1.6613        | 8.0   | 3096 | 1.5003          | 18.7652 | 14.2726 |
| 1.6613        | 9.0   | 3483 | 1.4867          | 19.009  | 14.4742 |
| 1.6075        | 10.0  | 3870 | 1.4817          | 19.6535 | 14.4432 |


### Framework versions

- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2