|
--- |
|
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 |
|
|
