---
license: apache-2.0
base_model: t5-base
tags:
- generated_from_trainer
metrics:
- rouge
- wer
model-index:
- name: t-5_base_extractive_512_750
  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. -->

# t-5_base_extractive_512_750

This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2627
- Rouge1: 0.6597
- Rouge2: 0.3836
- Rougel: 0.5954
- Rougelsum: 0.5953
- Wer: 0.5117

## 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: 2e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:------:|
| No log        | 0.13  | 250  | 1.3741          | 0.6424 | 0.3616 | 0.5756 | 0.5756    | 0.5348 |
| 1.8339        | 0.27  | 500  | 1.3204          | 0.6501 | 0.371  | 0.5847 | 0.5847    | 0.5245 |
| 1.8339        | 0.4   | 750  | 1.2968          | 0.6533 | 0.3761 | 0.5886 | 0.5885    | 0.5192 |
| 1.4045        | 0.53  | 1000 | 1.2796          | 0.6568 | 0.3798 | 0.5919 | 0.5918    | 0.5161 |
| 1.4045        | 0.66  | 1250 | 1.2723          | 0.6582 | 0.382  | 0.5938 | 0.5937    | 0.5134 |
| 1.3616        | 0.8   | 1500 | 1.2656          | 0.659  | 0.3833 | 0.5947 | 0.5947    | 0.5122 |
| 1.3616        | 0.93  | 1750 | 1.2627          | 0.6597 | 0.3836 | 0.5954 | 0.5953    | 0.5117 |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2