---
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-squad
  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-squad

This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.8157
- Rouge1: 0.1335
- Rouge2: 0.0193
- Rougel: 0.1312
- Rougelsum: 0.1310

## 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: 1e-05
- 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: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
| No log        | 0.53  | 100  | 3.2422          | 0.1221 | 0.0171 | 0.1210 | 0.1209    |
| No log        | 1.06  | 200  | 2.9500          | 0.1248 | 0.0170 | 0.1224 | 0.1227    |
| No log        | 1.6   | 300  | 2.8945          | 0.1258 | 0.0173 | 0.1229 | 0.1231    |
| No log        | 2.13  | 400  | 2.8715          | 0.1295 | 0.0191 | 0.1270 | 0.1270    |
| 3.1266        | 2.66  | 500  | 2.8479          | 0.1299 | 0.0200 | 0.1275 | 0.1275    |
| 3.1266        | 3.19  | 600  | 2.8316          | 0.1307 | 0.0203 | 0.1285 | 0.1286    |
| 3.1266        | 3.72  | 700  | 2.8238          | 0.1324 | 0.0204 | 0.1301 | 0.1302    |
| 3.1266        | 4.26  | 800  | 2.8180          | 0.1339 | 0.0193 | 0.1316 | 0.1315    |
| 3.1266        | 4.79  | 900  | 2.8157          | 0.1335 | 0.0193 | 0.1312 | 0.1310    |


### Framework versions

- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3