|
--- |
|
license: apache-2.0 |
|
base_model: google/flan-t5-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- billsum |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: 3_loa |
|
results: [] |
|
library_name: peft |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# 3_loa |
|
|
|
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the billsum dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5159 |
|
- Rouge1: 0.2005 |
|
- Rouge2: 0.1122 |
|
- Rougel: 0.1739 |
|
- Rougelsum: 0.1738 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 2.0741 | 1.0 | 989 | 1.7085 | 0.2064 | 0.1145 | 0.1771 | 0.1771 | 19.0 | |
|
| 1.8521 | 2.0 | 1978 | 1.6510 | 0.2021 | 0.109 | 0.1744 | 0.1743 | 19.0 | |
|
| 1.7753 | 3.0 | 2967 | 1.6182 | 0.2015 | 0.1099 | 0.1742 | 0.1742 | 19.0 | |
|
| 1.7481 | 4.0 | 3956 | 1.5940 | 0.1995 | 0.1102 | 0.1736 | 0.1737 | 19.0 | |
|
| 1.6966 | 5.0 | 4945 | 1.5771 | 0.1999 | 0.1112 | 0.1739 | 0.1738 | 19.0 | |
|
| 1.7107 | 6.0 | 5934 | 1.5629 | 0.1974 | 0.1091 | 0.1721 | 0.1721 | 19.0 | |
|
| 1.6905 | 7.0 | 6923 | 1.5527 | 0.1993 | 0.1091 | 0.1737 | 0.1737 | 19.0 | |
|
| 1.6341 | 8.0 | 7912 | 1.5475 | 0.1994 | 0.11 | 0.1732 | 0.1731 | 19.0 | |
|
| 1.6649 | 9.0 | 8901 | 1.5422 | 0.1978 | 0.109 | 0.1726 | 0.1722 | 19.0 | |
|
| 1.6338 | 10.0 | 9890 | 1.5339 | 0.2009 | 0.1125 | 0.1748 | 0.1744 | 19.0 | |
|
| 1.6545 | 11.0 | 10879 | 1.5310 | 0.201 | 0.1138 | 0.1759 | 0.1757 | 19.0 | |
|
| 1.6617 | 12.0 | 11868 | 1.5323 | 0.2026 | 0.1152 | 0.1762 | 0.1761 | 19.0 | |
|
| 1.629 | 13.0 | 12857 | 1.5245 | 0.202 | 0.1143 | 0.1752 | 0.1751 | 19.0 | |
|
| 1.6202 | 14.0 | 13846 | 1.5214 | 0.2021 | 0.1138 | 0.1752 | 0.1751 | 19.0 | |
|
| 1.6127 | 15.0 | 14835 | 1.5206 | 0.2013 | 0.113 | 0.1746 | 0.1743 | 19.0 | |
|
| 1.6072 | 16.0 | 15824 | 1.5171 | 0.1991 | 0.1112 | 0.1731 | 0.1727 | 19.0 | |
|
| 1.6032 | 17.0 | 16813 | 1.5180 | 0.1997 | 0.1126 | 0.1737 | 0.1735 | 19.0 | |
|
| 1.6103 | 18.0 | 17802 | 1.5169 | 0.1999 | 0.1128 | 0.1741 | 0.1738 | 19.0 | |
|
| 1.5956 | 19.0 | 18791 | 1.5160 | 0.2008 | 0.1128 | 0.1743 | 0.174 | 19.0 | |
|
| 1.5981 | 20.0 | 19780 | 1.5159 | 0.2005 | 0.1122 | 0.1739 | 0.1738 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.4.0 |
|
- Transformers 4.31.0 |
|
- Pytorch 1.13.1.post200 |
|
- Datasets 2.10.0 |
|
- Tokenizers 0.13.2 |
|
|
