---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
model-index:
- name: flant5-base-finetuning
  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. -->

# flant5-base-finetuning

This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0746

## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.1109        | 0.64  | 500  | 0.0801          |
| 0.0919        | 1.28  | 1000 | 0.0772          |
| 0.088         | 1.93  | 1500 | 0.0766          |
| 0.085         | 2.57  | 2000 | 0.0758          |
| 0.0828        | 3.21  | 2500 | 0.0754          |
| 0.0809        | 3.85  | 3000 | 0.0750          |
| 0.0793        | 4.49  | 3500 | 0.0749          |
| 0.0788        | 5.14  | 4000 | 0.0746          |
| 0.0776        | 5.78  | 4500 | 0.0746          |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.15.2