|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-small-lit-simplif |
|
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. --> |
|
|
|
# flan-t5-small-lit-simplif |
|
|
|
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8832 |
|
- Rouge1: 57.5616 |
|
- Rouge2: 43.0588 |
|
- Rougel: 54.6246 |
|
- Rougelsum: 54.8382 |
|
- Gen Len: 18.4914 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 1.3943 | 1.0 | 698 | 1.0480 | 57.3763 | 43.1329 | 54.1155 | 54.4964 | 18.6571 | |
|
| 1.1857 | 2.0 | 1396 | 0.9521 | 57.315 | 43.2483 | 54.4032 | 54.7664 | 18.6771 | |
|
| 1.0406 | 3.0 | 2094 | 0.9075 | 57.6951 | 43.4451 | 54.8174 | 55.0469 | 18.5343 | |
|
| 0.9861 | 4.0 | 2792 | 0.8873 | 57.8533 | 43.409 | 54.7583 | 55.0156 | 18.5971 | |
|
| 0.9592 | 5.0 | 3490 | 0.8832 | 57.5616 | 43.0588 | 54.6246 | 54.8382 | 18.4914 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
