---
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
datasets:
- samsum
metrics:
- rouge
model-index:
- name: flan-t5-base-samsum
  results:
  - task:
      name: Sequence-to-sequence Language Modeling
      type: text2text-generation
    dataset:
      name: samsum
      type: samsum
      config: samsum
      split: test
      args: samsum
    metrics:
    - name: Rouge1
      type: rouge
      value: 47.0919
---

<!-- 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-samsum

This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3859
- Rouge1: 47.0919
- Rouge2: 23.2123
- Rougel: 39.2407
- Rougelsum: 43.2174
- Gen Len: 17.3333

## 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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 1.5121        | 0.08  | 50   | 1.4287          | 46.7806 | 22.8207 | 38.9302 | 42.7835   | 16.9634 |
| 1.46          | 0.16  | 100  | 1.4199          | 46.826  | 22.7844 | 39.0295 | 42.8573   | 17.2393 |
| 1.4515        | 0.24  | 150  | 1.4147          | 46.6646 | 22.9602 | 38.9391 | 42.8187   | 17.1245 |
| 1.4679        | 0.33  | 200  | 1.4121          | 46.8291 | 22.7922 | 39.1404 | 43.1542   | 17.3431 |
| 1.451         | 0.41  | 250  | 1.4109          | 46.8103 | 23.0066 | 39.2832 | 43.2411   | 17.2686 |
| 1.4434        | 0.49  | 300  | 1.4040          | 46.6321 | 22.989  | 39.3016 | 43.0997   | 16.9158 |
| 1.4417        | 0.57  | 350  | 1.4007          | 46.8538 | 22.9937 | 39.2135 | 43.1728   | 17.1172 |
| 1.4781        | 0.65  | 400  | 1.3952          | 46.8055 | 23.036  | 39.2961 | 43.1755   | 17.2076 |
| 1.4626        | 0.73  | 450  | 1.3940          | 47.0996 | 23.2205 | 39.3007 | 43.2286   | 17.2222 |
| 1.4307        | 0.81  | 500  | 1.3955          | 46.8877 | 23.1402 | 39.2634 | 43.1279   | 17.2002 |
| 1.4586        | 0.9   | 550  | 1.3933          | 46.7191 | 23.1291 | 39.2437 | 43.1183   | 17.3040 |
| 1.4465        | 0.98  | 600  | 1.3905          | 46.8651 | 23.29   | 39.2514 | 43.2025   | 17.3468 |
| 1.381         | 1.06  | 650  | 1.3953          | 46.9166 | 22.9547 | 39.0439 | 43.1589   | 17.4066 |
| 1.4125        | 1.14  | 700  | 1.3922          | 46.5286 | 23.0552 | 38.9056 | 42.9298   | 17.2381 |
| 1.3667        | 1.22  | 750  | 1.3922          | 47.3239 | 23.3549 | 39.4725 | 43.518    | 17.2930 |
| 1.3878        | 1.3   | 800  | 1.3953          | 46.6837 | 23.1602 | 39.2578 | 43.2195   | 17.3358 |
| 1.3884        | 1.38  | 850  | 1.3931          | 46.9537 | 23.0894 | 39.1676 | 43.1687   | 17.3614 |
| 1.3766        | 1.47  | 900  | 1.3898          | 46.9996 | 23.1407 | 39.2222 | 43.237    | 17.3333 |
| 1.3727        | 1.55  | 950  | 1.3889          | 46.6936 | 23.0454 | 39.0579 | 42.9472   | 17.3211 |
| 1.4001        | 1.63  | 1000 | 1.3859          | 47.0919 | 23.2123 | 39.2407 | 43.2174   | 17.3333 |
| 1.3894        | 1.71  | 1050 | 1.3874          | 47.2229 | 23.35   | 39.4333 | 43.4876   | 17.3297 |
| 1.3697        | 1.79  | 1100 | 1.3860          | 47.0872 | 23.3503 | 39.3371 | 43.3444   | 17.3504 |
| 1.3886        | 1.87  | 1150 | 1.3862          | 47.0516 | 23.3487 | 39.3653 | 43.3272   | 17.3260 |
| 1.4037        | 1.95  | 1200 | 1.3861          | 47.05   | 23.3672 | 39.3131 | 43.3233   | 17.3321 |


### Framework versions

- Transformers 4.33.2
- Pytorch 2.0.0+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3