|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
base_model: google/flan-t5-base |
|
|
model-index: |
|
|
- name: results |
|
|
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. --> |
|
|
|
|
|
# results |
|
|
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 3.1549 |
|
|
- Rouge1: 0.0992 |
|
|
- Rouge2: 0.0185 |
|
|
- Rougel: 0.0769 |
|
|
- Rougelsum: 0.0898 |
|
|
|
|
|
## 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: 0.0003 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 4 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
|
| 3.4344 | 1.0 | 1498 | 3.2018 | 0.1012 | 0.0173 | 0.0788 | 0.0920 | |
|
|
| 3.4054 | 2.0 | 2996 | 3.1860 | 0.0966 | 0.0176 | 0.0749 | 0.0876 | |
|
|
| 3.3838 | 3.0 | 4494 | 3.1767 | 0.0984 | 0.0180 | 0.0766 | 0.0892 | |
|
|
| 3.368 | 4.0 | 5992 | 3.1712 | 0.1013 | 0.0191 | 0.0785 | 0.0915 | |
|
|
| 3.3534 | 5.0 | 7490 | 3.1647 | 0.1007 | 0.0188 | 0.0781 | 0.0910 | |
|
|
| 3.3573 | 6.0 | 8988 | 3.1613 | 0.0992 | 0.0189 | 0.0770 | 0.0897 | |
|
|
| 3.3392 | 7.0 | 10486 | 3.1581 | 0.0999 | 0.0186 | 0.0778 | 0.0904 | |
|
|
| 3.3327 | 8.0 | 11984 | 3.1568 | 0.1006 | 0.0187 | 0.0778 | 0.0909 | |
|
|
| 3.3275 | 9.0 | 13482 | 3.1554 | 0.0983 | 0.0181 | 0.0763 | 0.0890 | |
|
|
| 3.3267 | 10.0 | 14980 | 3.1549 | 0.0992 | 0.0185 | 0.0769 | 0.0898 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.10.0 |
|
|
- Transformers 4.38.2 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
