|
--- |
|
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 |
|
|
