|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: ADL_HW2_MT5 |
|
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. --> |
|
|
|
# ADL_HW2_MT5 |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.5085 |
|
- Rouge1: 13.6234 |
|
- Rouge2: 4.8107 |
|
- Rougel: 13.4828 |
|
- Rougelsum: 13.4694 |
|
|
|
## 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: 5.6e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:| |
|
| 6.652 | 1.0 | 340 | 3.9727 | 10.0329 | 3.8308 | 9.954 | 9.9802 | |
|
| 4.5708 | 2.0 | 680 | 3.7827 | 11.1164 | 4.1328 | 11.0046 | 11.0159 | |
|
| 4.3069 | 3.0 | 1020 | 3.6472 | 12.405 | 4.4789 | 12.2766 | 12.308 | |
|
| 4.1563 | 4.0 | 1360 | 3.5830 | 12.6726 | 4.5588 | 12.5504 | 12.5738 | |
|
| 4.0715 | 5.0 | 1700 | 3.5509 | 12.6934 | 4.7831 | 12.5682 | 12.5705 | |
|
| 4.0094 | 6.0 | 2040 | 3.5241 | 13.3107 | 4.8201 | 13.198 | 13.2002 | |
|
| 3.9728 | 7.0 | 2380 | 3.5153 | 13.3888 | 4.7922 | 13.2839 | 13.2947 | |
|
| 3.9505 | 8.0 | 2720 | 3.5085 | 13.6234 | 4.8107 | 13.4828 | 13.4694 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|