|
--- |
|
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 |
|
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 |
|
|
|
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: 1.5612 |
|
- Rouge1: 0.2459 |
|
- Rouge2: 0.1153 |
|
- Rougel: 0.1998 |
|
- Rougelsum: 0.2294 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 15.0637 | 1.0 | 125 | 14.5380 | 0.2315 | 0.0949 | 0.1776 | 0.2084 | |
|
| 11.8916 | 2.0 | 250 | 11.5849 | 0.2319 | 0.0957 | 0.1818 | 0.2077 | |
|
| 7.8325 | 3.0 | 375 | 5.8491 | 0.2294 | 0.0978 | 0.1839 | 0.2098 | |
|
| 3.6167 | 4.0 | 500 | 2.9519 | 0.2345 | 0.1096 | 0.1915 | 0.2195 | |
|
| 3.0365 | 5.0 | 625 | 2.3695 | 0.2391 | 0.1132 | 0.1964 | 0.2228 | |
|
| 2.7862 | 6.0 | 750 | 1.9609 | 0.2428 | 0.1163 | 0.1981 | 0.2258 | |
|
| 2.5261 | 7.0 | 875 | 1.7701 | 0.2462 | 0.1137 | 0.1979 | 0.2292 | |
|
| 2.3319 | 8.0 | 1000 | 1.6463 | 0.2459 | 0.1142 | 0.1995 | 0.2294 | |
|
| 2.355 | 9.0 | 1125 | 1.5820 | 0.2442 | 0.114 | 0.1998 | 0.2279 | |
|
| 2.323 | 10.0 | 1250 | 1.5612 | 0.2459 | 0.1153 | 0.1998 | 0.2294 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.37.0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.15.1 |
