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

# flan-t5-base

This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1442

## 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: 0.001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 10.7012       | 1.0   | 18   | 0.2887          |
| 0.2143        | 2.0   | 36   | 0.1380          |
| 0.087         | 3.0   | 54   | 0.1287          |
| 0.0641        | 4.0   | 72   | 0.0977          |
| 0.0281        | 5.0   | 90   | 0.1312          |
| 0.0125        | 6.0   | 108  | 0.1415          |
| 0.015         | 7.0   | 126  | 0.1289          |
| 0.0075        | 8.0   | 144  | 0.1352          |
| 0.0055        | 9.0   | 162  | 0.1426          |
| 0.0043        | 10.0  | 180  | 0.1442          |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0