|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
base_model: google/flan-t5-xl |
|
model-index: |
|
- name: t5-xl-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. --> |
|
|
|
# t5-xl-v2 |
|
|
|
This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8350 |
|
- Rouge1: 29.9535 |
|
- Rouge2: 11.4157 |
|
- Rougel: 21.3830 |
|
- Rougelsum: 21.3793 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 24 |
|
- eval_batch_size: 32 |
|
- seed: 7 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:| |
|
| 2.1401 | 0.34 | 300 | 1.8438 | 30.0703 | 11.5959 | 21.6066 | 21.6053 | |
|
| 2.13 | 0.67 | 600 | 1.8369 | 29.9460 | 11.6006 | 21.6609 | 21.6625 | |
|
| 2.1364 | 1.01 | 900 | 1.8262 | 30.2597 | 11.8455 | 21.7202 | 21.7212 | |
|
| 2.1301 | 1.35 | 1200 | 1.8301 | 30.1492 | 11.6922 | 21.6115 | 21.6151 | |
|
| 2.146 | 1.68 | 1500 | 1.8350 | 29.9535 | 11.4157 | 21.3830 | 21.3793 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
