---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: flan-t5-xl-finetuned-unnatural-instructions
  results: []

widget:
- text: "You will be provided with a short text that you should read. After reading the text, answer the question 'Who is telling the story in first person?'\nText: I went to the store and bought some milk.\nThe output should be one of the two options: 'I' or 'Not I'.\nOutput:"
- text: "You are given the title and opening paragraph of an article. Your task is to find the main idea of the article using context clues from the text.\nText: The first confirmed case of Zika in Africa has been found in Uganda, health officials said on Tuesday, more than 4,000 miles away from Brazil where a major outbreak began last year.\nAblood test carried out at a private hospital showed that a five-year-old girl who had returned from Mozambique three weeks ago had contracted Zika, which can cause birth defects in babies born to infected mothers.\nOutput:"
- text: "We have given you a list of sentences. Your task is to go through this list and find all the unique words used in these sentences and store them in a dictionary.\nThis is an example sentence., That is another example sentence., Here is an interesting sentence!\nThe output should be a Python dictionary with keys as the unique words and values as the number of times that word occurs in the text.\nOutput:\n"
- text: "You will given a set of two or more words. Output the shortest word in the set. If there is a tie for the shortest word, output all tied words in alphabetical order, separated by space.\nWords: defenestrate, circumambulate, excommunication.\nThe input will be lowercase and only contain alphanumeric characters and spaces.\nOutput:\n"

inference:
  parameters:
    max_length: 150
---

<!-- 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. -->

# flan-t5-xl-finetuned-unnatural-instructions

This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1224

## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 5000

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.1345        | 0.02  | 1000 | 0.1386          |
| 0.14          | 0.03  | 2000 | 0.1336          |
| 0.1402        | 0.05  | 3000 | 0.1282          |
| 0.129         | 0.07  | 4000 | 0.1235          |
| 0.1356        | 0.08  | 5000 | 0.1224          |


### Framework versions

- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2