|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: flan-t5-large-extraction-cnndm_4000-all |
|
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-large-extraction-cnndm_4000-all |
|
|
|
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7290 |
|
- Rouge1: 35.0775 |
|
- Rouge2: 15.2209 |
|
- Rougel: 30.1796 |
|
- Rougelsum: 30.1599 |
|
- 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: 8 |
|
- eval_batch_size: 24 |
|
- seed: 1799 |
|
- 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 | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| 2.1464 | 0.4 | 200 | 1.8323 | 35.2242 | 15.3495 | 30.142 | 30.1331 | 19.0 | |
|
| 1.9817 | 0.8 | 400 | 1.7729 | 34.3798 | 14.7287 | 29.5447 | 29.6052 | 18.986 | |
|
| 1.8842 | 1.2 | 600 | 1.7602 | 34.5807 | 15.1707 | 29.7768 | 29.8081 | 18.986 | |
|
| 1.8129 | 1.6 | 800 | 1.7629 | 34.5103 | 15.231 | 29.9182 | 29.9333 | 19.0 | |
|
| 1.8238 | 2.0 | 1000 | 1.7290 | 35.0775 | 15.2209 | 30.1796 | 30.1599 | 19.0 | |
|
| 1.7199 | 2.4 | 1200 | 1.7354 | 34.6552 | 15.7256 | 30.1894 | 30.2207 | 18.998 | |
|
| 1.7128 | 2.8 | 1400 | 1.7407 | 34.7198 | 15.5771 | 30.0585 | 30.0442 | 19.0 | |
|
| 1.6816 | 3.2 | 1600 | 1.7508 | 34.9611 | 15.5792 | 30.3518 | 30.3638 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
