|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flanT5_small_title_desc |
|
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. --> |
|
|
|
# flanT5_small_title_desc |
|
|
|
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: 0.0198 |
|
- Rouge1: 2.9385 |
|
- Rouge2: 1.7278 |
|
- Rougel: 2.3658 |
|
- Rougelsum: 2.5451 |
|
- Gen Len: 18.9634 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 0.0781 | 1.0 | 2020 | 0.0496 | 2.2624 | 1.1169 | 1.781 | 1.9142 | 18.8670 | |
|
| 0.0476 | 2.0 | 4040 | 0.0309 | 2.635 | 1.4254 | 2.1038 | 2.2632 | 18.9406 | |
|
| 0.0366 | 3.0 | 6060 | 0.0238 | 2.8703 | 1.642 | 2.284 | 2.4596 | 18.8908 | |
|
| 0.0327 | 4.0 | 8080 | 0.0207 | 2.9212 | 1.7136 | 2.3494 | 2.5265 | 18.9626 | |
|
| 0.0308 | 5.0 | 10100 | 0.0198 | 2.9385 | 1.7278 | 2.3658 | 2.5451 | 18.9634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|