|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- Summarization |
|
- generated_from_trainer |
|
datasets: |
|
- cnn_dailymail |
|
metrics: |
|
- rouge |
|
base_model: google/flan-t5-base |
|
model-index: |
|
- name: flan-t5-base-finetuned-QLoRA-v2 |
|
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-base-finetuned-QLoRA-v2 |
|
|
|
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the cnn_dailymail dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1284 |
|
- Rouge1: 0.2459 |
|
- Rouge2: 0.1133 |
|
- Rougel: 0.2014 |
|
- Rougelsum: 0.2312 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 3.2738 | 1.0 | 500 | 2.5624 | 0.2375 | 0.1097 | 0.1987 | 0.223 | |
|
| 1.8824 | 2.0 | 1000 | 1.2830 | 0.2419 | 0.11 | 0.1988 | 0.2278 | |
|
| 1.6192 | 3.0 | 1500 | 1.1527 | 0.2477 | 0.1149 | 0.2033 | 0.2325 | |
|
| 1.5256 | 4.0 | 2000 | 1.1284 | 0.2459 | 0.1133 | 0.2014 | 0.2312 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
