---
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: 47.08
---

<!-- 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: 47.08
- Rouge2: 23.2603
- Rougel: 39.2645
- Rougelsum: 43.2898
- 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          | 46.7443 | 22.8826 | 38.9466 | 42.862    | 16.9634 |
| 1.46          | 0.16  | 100  | 1.4199          | 46.7723 | 22.8011 | 39.0224 | 42.9095   | 17.2393 |
| 1.4515        | 0.24  | 150  | 1.4147          | 46.6593 | 23.027  | 38.9378 | 42.8492   | 17.1245 |
| 1.4679        | 0.33  | 200  | 1.4121          | 46.8312 | 22.8345 | 39.1545 | 43.2035   | 17.3431 |
| 1.451         | 0.41  | 250  | 1.4109          | 46.826  | 23.038  | 39.2744 | 43.3106   | 17.2686 |
| 1.4434        | 0.49  | 300  | 1.4040          | 46.6744 | 23.0221 | 39.3167 | 43.1835   | 16.9158 |
| 1.4417        | 0.57  | 350  | 1.4007          | 46.851  | 23.0448 | 39.2346 | 43.2396   | 17.1172 |
| 1.4781        | 0.65  | 400  | 1.3952          | 46.7831 | 23.1146 | 39.295  | 43.2256   | 17.2076 |
| 1.4626        | 0.73  | 450  | 1.3940          | 47.0933 | 23.2741 | 39.2954 | 43.3102   | 17.2222 |
| 1.4307        | 0.81  | 500  | 1.3955          | 46.8827 | 23.2016 | 39.2817 | 43.2379   | 17.2002 |
| 1.4586        | 0.9   | 550  | 1.3933          | 46.7152 | 23.1439 | 39.2576 | 43.1754   | 17.3040 |
| 1.4465        | 0.98  | 600  | 1.3905          | 46.8332 | 23.3356 | 39.2596 | 43.2472   | 17.3468 |
| 1.381         | 1.06  | 650  | 1.3953          | 46.9289 | 22.9605 | 39.0651 | 43.2085   | 17.4066 |
| 1.4125        | 1.14  | 700  | 1.3922          | 46.4822 | 23.0893 | 38.9024 | 42.9789   | 17.2381 |
| 1.3667        | 1.22  | 750  | 1.3922          | 47.2977 | 23.4064 | 39.5091 | 43.5742   | 17.2930 |
| 1.3878        | 1.3   | 800  | 1.3953          | 46.6405 | 23.2132 | 39.2853 | 43.3049   | 17.3358 |
| 1.3884        | 1.38  | 850  | 1.3931          | 46.9152 | 23.1594 | 39.1629 | 43.2254   | 17.3614 |
| 1.3766        | 1.47  | 900  | 1.3898          | 46.988  | 23.1708 | 39.2446 | 43.311    | 17.3333 |
| 1.3727        | 1.55  | 950  | 1.3889          | 46.6771 | 23.0915 | 39.0787 | 43.0184   | 17.3211 |
| 1.4001        | 1.63  | 1000 | 1.3859          | 47.08   | 23.2603 | 39.2645 | 43.2898   | 17.3333 |
| 1.3894        | 1.71  | 1050 | 1.3874          | 47.2134 | 23.3696 | 39.4356 | 43.5422   | 17.3297 |
| 1.3697        | 1.79  | 1100 | 1.3860          | 47.06   | 23.3769 | 39.3494 | 43.4113   | 17.3504 |
| 1.3886        | 1.87  | 1150 | 1.3862          | 47.0159 | 23.3728 | 39.3871 | 43.4016   | 17.3260 |
| 1.4037        | 1.95  | 1200 | 1.3861          | 47.0039 | 23.4055 | 39.3356 | 43.3787   | 17.3321 |


### Framework versions

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